Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 22 – 41 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims of U.S. Patent No. 12254072, 11790066, 11122078. Although the claims at issue are not identical, they are not patentably distinct from each other because application claims are anticipated by below indicated patent claims.
Instant App. 19044290
Patent #: 12254072
Patent #: 11790066
Patent #: 11122078
22. (New) An authentication system for privacy-enabled authentication, the system comprising: at least one processor operatively connected to a memory, the at least one processor, when executing, configured to: filter identification information used in subsequent enrollment, identification, or authentication functions instantiate one or more pre-trained neural networks, including a first pre-trained helper network associated with identification information of a first type, wherein the first pre-trained helper network is configured to: evaluate an unknown identification sample of the first type based on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated; execute at least a probabilistic evaluation of the unknown identification sample that includes a determination of a probability that the unknown identification sample improves or hinders the subsequent enrollment, authentication, or identification functions; validate the unknown information sample for use in subsequent enrollment, identification, or authentication, responsive to a determination that the unknown identification sample meets the evaluation criteria based, at least in part, on output from the first pre-trained helper network; and reject the unknown identification sample for use in subsequent enrollment, identification, or authentication, responsive to a determination that the unknown identification sample fails the evaluation criteria based, at least in part, on output from the first pre-trained helper network.
23. (New) The system of claim 22, wherein the first pre-trained helper network is configured to evaluate image-based information samples.
24. (New) The system of claim 23, wherein the first pre-trained helper network is configured to evaluate image properties associated with the unknown image sample.
25. (New) The system of claim 24, wherein the first pre-trained helper network is trained on images having properties that include at least one of blur that reduces identification capability, insufficient presence of landmarks in an input image, sufficient presence of landmarks, masked subjects, subjects wearing glasses, eye open state, or capture distance.
26. (New) The system of claim 22, wherein the at least one processor is configured to host a data authentication service configured to return status regarding validation or rejection of authentication information.
27. (New) The system of claim 22, wherein the one or more pre-trained neural networks including a second pre-trained helper network associated with identification information of a second type.
28. (New) The system of claim 22, wherein the first pre-trained helper network is configured to identify bad, good, and spoofed information samples, wherein bad information samples reduce identification accuracy of the subsequent authentication or identification processing neural networks.
29. (New) The system of claim 22, wherein the first pre-trained helper network is configured to: process a video or image input as identification information; and determine that the video or image input is valid, invalid, or a presentation attack.
30. (New) A computer implemented method for privacy-enabled authentication, the method comprising: filtering, by at least one processor, identification information used in subsequent enrollment, identification, or authentication functions; instantiating, by the at least one processor, one or more pre-trained neural networks, including a first pre-trained helper network associated with identification information of a first type, wherein the first pre-trained helper network is pre-trained on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated; evaluating, by the first pre-trained helper network, an unknown identification sample of the first type, responsive to input of the unknown identification sample of the first type to the first pre- trained helper network; executing, by the first pre-trained helper network, at least a probabilistic evaluation of the unknown identification sample that includes determining a probability that the unknown identification sample improves or hinders subsequent enrollment, authentication, or identification functions; and determining, by the first pre-trained helper network, if the unknown identification sample meets the evaluation criteria and validating the unknown identification sample for use in subsequent enrollment, identification, or authentication, or determining if the unknown identification sample does not meet the evaluation criteria and rejecting the unknown identification sample for use in subsequent enrollment, identification, or authentication.
31. (New) The method of claim 30, wherein the act of evaluating includes evaluating, by the first pre-trained helper network, image-based identification samples.
32. (New) The method of claim 31, wherein the act of evaluating includes evaluating, by the first pre-trained helper network, image properties associated with the unknown image sample.
33. (New) The method of claim 32, wherein the first pre-trained helper network is trained on images having properties that include at least one of blur that reduces identification capability, insufficient presence of landmarks in an input image, sufficient presence of landmarks, masked subjects, subjects wearing glasses, eye open state, or capture distance.
34. (New) The method of claim 30, wherein the method further comprises: hosting, by the at least one processor, a data authentication service configured to return status regarding validation or rejection of authentication information.
35. (New) The method of claim 30, wherein the act of instantiating includes, by the at least one processor, including a second pre-trained helper network associated with identification information of a second type.
36. (New) The method of claim 30, wherein the method further comprises: identifying, by the first pre-trained helper network, bad, good, and spoofed information samples, wherein bad information samples reduce identification accuracy of the subsequent authentication or identification processing neural networks.
37. (New) The method of claim 30, wherein the method further comprises: processing, by the first pre-trained helper network, a video or image input as identification information; and determining, by the first pre-trained helper network, whether the video or image input is valid, invalid, or a presentation attack.
38. (New) A non-transitory computer-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform a method for privacy- enabled authentication, the method comprising: filtering identification information used in subsequent enrollment, identification, or authentication functions; instantiating a first pre-trained helper network associated with identification information of a first type, wherein the first pre-trained helper network is pre-trained on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated; evaluating an unknown identification sample of the first type, responsive to input of the unknown identification sample of the first type to the first pre-trained helper network; executing, at least a probabilistic evaluation of the unknown identification sample that includes determining a probability that the unknown identification sample improves or hinders the subsequent enrollment, authentication, or identification functions; and determining if the unknown identification sample meets the evaluation criteria and validating the unknown identification sample for use in subsequent enrollment, identification, or authentication, or determining if the unknown identification sample does not meet the evaluation criteria and rejecting the unknown identification sample for use in subsequent enrollment, identification, or authentication.
39. (New) The medium of claim 38, wherein the first pre-trained helper network is configured to evaluate image-based information samples.
40. (New) The medium of claim 39, wherein the first pre-trained helper network is configured to evaluate image properties associated with the unknown image sample.
41. (New) The medium of claim 40, wherein the first pre-trained helper network is trained on images having properties that include at least one of: blur that reduces identification capability, insufficient presence of landmarks in an input image, sufficient presence of landmarks, masked subjects, subjects wearing glasses, eye open state, or capture distance.
22. An authentication system for privacy-enabled authentication, the system comprising:
at least one processor operatively connected to a memory;
an authentication data gateway, executed by the at least one processor, configured to filter identification information used in enrollment, identification, or authentication functions of subsequent neural networks, the authentication data gateway comprising at least:
a first pre-trained validation helper network associated with identification information of a first type, wherein the first pre-trained validation helper network is configured to:
evaluate an unknown identification sample of the first type, responsive to input of the unknown identification sample of the first type to the first pre-trained validation helper network, wherein evaluation is based on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticate and identify spoofed information samples, which includes improper submission of valid identification information or indirect capture of valid authentication information;
wherein the authentication data gateway is further configured to:
validate the unknown information sample for use in subsequent enrollment, identification, or authentication, responsive to a determination that the unknown identification sample meets the evaluation criteria;
reject the unknown identification sample for use in subsequent enrollment, identification, or authentication, responsive to a determination that the unknown identification sample fails the evaluation criteria; and
as part of validation or rejection, execute at least a probabilistic evaluation of the unknown identification sample that includes generation of an output probability by the first pre-trained validation helper network that the unknown identification sample improves or hinders subsequent authentication or identification.
23. The system of claim 22, wherein the first pre-trained validation helper network is configured to identify bad information samples, wherein bad information samples reduce identification accuracy of the subsequent authentication or identification processing neural networks.
24. The system of claim 22, wherein the first pre-trained validation helper network is configured to identify good information samples, wherein good identification samples improve identification accuracy of the subsequent neural networks.
25. (Cancelled)
26. (Cancelled)
27. The system of claims 22, wherein the authentication data gateway further comprises a plurality of pre-trained validation helper networks associated with respective identification information types; wherein the plurality of validation helper networks are trained to generate an evaluation of an unknown identification sample of the respective identification information type and output a probability the respective unknown identification samples is valid or invalid.
28. The system of claim 22, wherein the first pre-trained validation helper network is configured to:
process a video or image input as identification information; and
output a probability that the video or image input is invalid.
29. The system of claim 22, wherein the first pre-trained validation helper network is configured to:
process a video or image input as identification information, and
output a probability that the video or image input is a presentation attack.
30. The system of claim 22, wherein the authentication data gateway further comprises a first pre-trained geometry helper network configured to:
process identification information of the first type,
accept as input unencrypted identification information of the fist type, and
communicate processed identification information of the first type to the first pre-trained validation helper network.
31. The system of claim 30, wherein the authentication data gateway further comprises a plurality of pre-trained geometry helper networks configured to:
process identification information of a respective first type,
accept as input unencrypted identification information of the respective type, and
communicate processed identification information of the respective type to an associated pre-trained validation helper network for validating the respective type.
32. (Currently Amended) A computer implemented method for privacy-enabled authentication, the method comprising:
filtering, by at least one processor, identification information used in enrollment, identification, or authentication functions of subsequent neural networks;
instantiating, by the at least one processor, a first pre-trained validation helper network associated with identification information of a first type, wherein the first pre-trained validation helper network is pre-trained on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated
evaluating, by the first pre-trained validation helper network, an unknown identification sample of the first type, responsive to input of the unknown identification sample of the first type to the first pre-trained validation helper network;
determining, by the first pre-trained validation helper network, if the unknown identification sample meets the evaluation criteria and validating the unknown identification sample for use in subsequent enrollment, identification, or authentication, or determining if the unknown identification sample does not meet the evaluation criteria and rejecting the unknown identification sample for use in subsequent enrollment, identification, or authentication, the determining including for samples that do not meet the evaluation criteria identifying spoofed information samples, wherein the spoofed information samples include improper submission of valid identification information or indirect capture of valid authentication information; and
generating, by the first pre-trained validation helper network, as part of the acts of validating or rejecting at least a probabilistic evaluation of the unknown identification sample that includes generating an output probability by the first pre-trained validation helper network that the unknown identification sample improves or hinders subsequent authentication or identification.
33. The method of claim 32, wherein the act of determining includes identifying, by the first pre-trained validation helper network, bad information samples, wherein bad information samples reduce identification accuracy of the subsequent neural networks.
34. The method of claim 32, wherein the act of determining includes identifying, by the first pre-trained validation helper network, good information samples, wherein good identification samples improve identification accuracy of the subsequent neural networks.
35. (Cancelled)
36. (Cancelled)
37. The method of claims 32, wherein the method further comprises instantiating a plurality of pre-trained validation helper networks associated with respective identification information types; wherein the plurality of validation helper networks are trained on evaluation criteria independent of a subject of the identification information seeking to be enrolled, identified, or authenticated, and are configured to generate at least a binary evaluation of an unknown identification sample of the respective identification information type as valid or invalid identification information.
38. The method of claim 32, wherein the method further comprises:
processing, by the first pre-trained validation helper network, a video or image input as identification information; and
generating a probability that the video or image input is invalid.
39. The method of claim 32, wherein the method further comprises:
processing, by the first pre-trained validation helper network, a video or image input as identification information, and
generating a probability that the video or image input is a presentation attack.
40. The method of claim 32, wherein the method further comprises instantiating, by the at least one processor, a first pre-trained geometry helper network configured to process identification information of the first type, accept as input unencrypted identification information of the fist type, and communicate processed identification information of the first type to the first pre-trained validation helper network.
41. The method of claim 40, wherein the method further comprises instantiating, by the at least one processor, a plurality of pre-trained geometry helper networks configured to process identification information of a respective first type, accept as input unencrypted identification information of the respective type, and communicate processed identification information of the respective type to an associated pre-trained validation helper network for validating the respective type.
22. An authentication system for privacy-enabled authentication, the system comprising:
at least one processor operatively connected to a memory;
an authentication data gateway, executed by the at least one processor, configured to filter identification information used in enrollment, identification, or authentication functions of subsequent neural networks, the authentication data gateway comprising at least a plurality of pre-trained validation helper networks, including:
a first pre-trained validation helper network associated with identification information of a first type, wherein the first pre-trained validation helper network is configured to:
evaluate an unknown identification sample of the first type, responsive to input of the unknown identification sample of the first type to the first pre-trained validation helper network, wherein evaluation is based on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated;
wherein the authentication data gateway is further configured to:
validate the unknown information sample for use in subsequent enrollment, identification, or authentication, responsive to a determination that the unknown identification sample meets the evaluation criteria;
reject the unknown identification sample for use in subsequent enrollment, identification, or authentication, responsive to a determination that the unknown identification sample fails the evaluation criteria; and
as part of validation or rejection, execute at least an
wherein the plurality of pre-trained validation helper networks are associated with respective identification information types and the plurality of validation helper networks are trained to generate an evaluation of an unknown identification sample of the respective identification information type and output a probability the respective unknown identification samples is valid or invalid.
23. The system of claim 22, wherein the first pre-trained validation helper network is configured to identify bad information samples, wherein bad information samples reduce identification accuracy of the subsequent neural networks.
24. The system of claim 22, wherein the first pre-trained validation helper network is configured to identify good information samples, wherein good identification samples improve identification accuracy of the subsequent neural networks.
25. The system of claim 22, wherein the first pre-trained validation helper network is configured to identify spoofed information samples.
26. The system of claim 25, wherein the spoofed information samples include improper submission of valid identification information or indirect capture of valid authentication information.
27. (Cancelled)
28. The system of claim 22, wherein the first pre-trained validation helper network is configured to:
process a video or image input as identification information; and
output a probability that the video or image input is invalid.
29. The system of claim 22, wherein the first pre-trained validation helper network is configured to:
process a video or image input as identification information, and
output a probability that the video or image input is a presentation attack.
30. The system of claim 22, wherein the authentication data gateway further comprises a first pre-trained geometry helper network configured to:
process identification information of the first type,
accept as input unencrypted identification information of the fist type, and
communicate processed identification information of the first type to the first pre-trained validation helper network.
31. The system of claim 30, wherein the authentication data gateway further comprises a plurality of pre-trained geometry helper networks configured to:
process identification information of a respective first type,
accept as input unencrypted identification information of the respective type, and
communicate processed identification information of the respective type to an associated pre-trained validation helper network for validating the respective type.
32. A computer implemented method for privacy-enabled authentication, the method comprising:
filtering, by at least one processor, identification information used in enrollment, identification, or authentication functions of subsequent neural networks;
instantiating, by the at least one processor, a first pre-trained validation helper network associated with identification information of a first type, wherein the first pre-trained validation helper network is pre-trained on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated
evaluating, by the first pre-trained validation helper network, an unknown identification sample of the first type, responsive to input of the unknown identification sample of the first type to the first pre-trained validation helper network;
determining, by the first pre-trained validation helper network, if the unknown identification sample meets the evaluation criteria and validating the unknown identification sample for use in subsequent enrollment, identification, or authentication, or if the unknown identification sample fails the evaluation criteria and rejecting the unknown identification sample for use in subsequent enrollment, identification, or authentication; and
generating, by the first pre-trained validation helper network, as part of the acts of validating or rejecting at least an
instantiating a plurality of pre-trained validation helper networks, including the first pre-trained validation helper network, associated with respective identification information types, wherein the plurality of validation helper networks are trained on evaluation criteria independent of a subject of the identification information seeking to be enrolled, identified, or authenticated, and are configured to generate at least an
33. The method of claim 32, wherein the act of determining includes identifying, by the first pre-trained validation helper network, bad information samples, wherein bad information samples reduce identification accuracy of the subsequent neural networks.
34. The method of claim 32, wherein the act of determining includes identifying, by the first pre-trained validation helper network, good information samples, wherein good identification samples improve identification accuracy of the subsequent neural networks.
35. The method of claim 32, wherein the method further comprises identifying, by the first pre-trained validation helper network, spoofed information samples.
36. The method of claim 35, wherein the spoofed information samples include improper submission of valid identification information or indirect capture of valid authentication information.
37. (Cancelled)
38. The method of claim 32, wherein the method further comprises:
processing, by the first pre-trained validation helper network, a video or image input as identification information; and
generating a probability that the video or image input is invalid.
39. The method of claim 32, wherein the method further comprises:
processing, by the first pre-trained validation helper network, a video or image input as identification information, and
generating a probability that the video or image input is a presentation attack.
40. The method of claim 32, wherein the method further comprises instantiating, by the at least one processor, a first pre-trained geometry helper network configured to process identification information of the first type, accept as input unencrypted identification information of the fist type, and communicate processed identification information of the first type to the first pre-trained validation helper network.
41. The method of claim 40, wherein the method further comprises instantiating, by the at least one processor, a plurality of pre-trained geometry helper networks configured to process identification information of a respective first type, accept as input unencrypted identification information of the respective type, and communicate processed identification information of the respective type to an associated pre-trained validation helper network for validating the respective type.
1. An authentication system for privacy-enabled authentication, the system comprising:
at least one processor operatively connected to a memory;
an authentication data gateway, executed by the at least one processor, configured to filter identification information used in enrollment, identification, or authentication functions of subsequent neural networks, the authentication data gateway comprising at least:
a first pre-trained validation helper network associated with identification information of a first type comprising voice identification information, wherein the first pre-trained validation helper network is configured to:
evaluate an unknown identification sample of the first type, responsive to input of the unknown information sample of the first type to the first pre-trained validation helper network, wherein the first pre-trained validation helper network is pre-trained on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated;
responsive to a determination that evaluation criteria,
responsive to a determination that the unknown information sample for use in subsequent enrollment, identification, or authentication; and
generate at least a binary evaluation of the unknown identification information sample based on the determination of the evaluation criteria, wherein the at least the binary evaluation includes generation of an output probability by the first pre-trained validation helper network that the unknown identification information sample is valid or invalid.
2. The system of claim 1, wherein the first pre-trained validation helper network is configured to identify bad information samples, wherein bad information samples reduce identification accuracy of the subsequent neural networks.
3. The system of claim 1, wherein the first pre-trained validation helper network is configured to identify good information samples, wherein good identification samples improve identification accuracy of the subsequent neural networks.
4. The system of claim 1, wherein the first pre-trained validation helper network is configured to identify spoofed information samples.
5. The system of claim 4, wherein the spoofed information samples include improper submission of valid identification information or indirect capture of valid authentication information.
6. The system of claims 1, wherein the authentication data gateway further comprises at least a second information sample of the second
7. The system of claim 6 [[
process a video or image input as identification information; and
output a probability that the video or image input is invalid.
8. The system of claim 6 [[
process a video or image input as identification information, and
output a probability that the video or image input is a presentation attack.
9. The system of claim 6 [[
process identification information of the
accept as input unencrypted identification information of the
communicate processed identification information of the
10. (Cancelled).
11. A computer implemented method for privacy-enabled authentication, the method comprising:
filtering, by at least one processor, identification information used in enrollment, identification, or authentication functions of subsequent neural networks;
instantiating, by the at least one processor, a first pre-trained validation helper network associated with identification information of a first type comprising voice identification information, wherein the first pre-trained validation helper network is pre-trained on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated;
evaluating, by the first pre-trained validation helper network, an unknown identification sample of the first type, responsive to input of the unknown information sample of the first type to the first pre-trained validation helper network;
in response to determining, by the first pre-trained validation helper network, use in subsequent enrollment, identification, or authentication; and
generating, by the first pre-trained validation helper network, at least a binary evaluation of the unknown identification information sample based on the determination of the evaluation criteria, wherein generating the at least the binary evaluation includes generating an output probability by the first pre-trained validation helper network that the unknown identification information sample is valid or invalid.
12. The method of claim 11, wherein the act of determining includes identifying, by the first pre-trained validation helper network, bad information samples, wherein bad information samples reduce identification accuracy of the subsequent neural networks.
13. The method of claim 11, wherein the act of determining includes identifying, by the first pre-trained validation helper network, good information samples, wherein good identification samples improve identification accuracy of the subsequent neural networks.
14. The method of claim 11, wherein the method further comprises identifying, by the first pre-trained validation helper network, spoofed information samples.
15. The method of claim 14, wherein the spoofed information samples include improper submission of valid identification information or indirect capture of valid authentication information.
16. The method of claims 11, wherein the method further comprises:
instantiating at least a second enrolled, identified, or authenticated, and
generating at least a binary evaluation of an unknown identification information sample of the second
17. The method of claim 16 [[11]], wherein the method further comprises:
processing, by the network, a video or image input as identification information; and
generating a probability that the video or image input is invalid.
18. The method of claim 16 [[11]], wherein the method further comprises:
processing, by the
generating a probability that the video or image input is a presentation attack.
19. The method of claim 16 [[11]], wherein the method further comprises instantiating, by the at least one processor, a first pre-trained geometry helper network configured to process identification information of the
20. (Cancelled).
21. An authentication system for privacy-enabled authentication, the system comprising:
at least one processor operatively connected to a memory;
an authentication data gateway, executed by the at least one processor, configured to filter identification information used in enrollment or identification functions of subsequent neural networks, the authentication data gateway comprising at least:
a first pre-trained validation helper network associated with identification information of a first type comprising voice identification information, wherein the first pre-trained validation helper network is further configured to:
evaluate identification information of the first type, wherein the first pre-trained validation helper network is trained on plaintext instances of good, bad, and spoofed identification samples, wherein good identification samples improve identification accuracy of the subsequent neural networks and bad identification samples reduce identification accuracy of the subsequent neural networks;
responsive to input of an unknown identification sample to the first pre-trained validation helper network, identify any bad information samples, good information samples, and spoofed information samples, regardless of a subject of the unknown identification sample; and
validate good information samples for use by subsequent neural network and reject bad and spoofed information samples from further processing based on at least a binary evaluation of the information sample, wherein the at least the binary evaluation includes generation of an output probability by the first pre-trained validation helper network that the unknown identification information sample is good or bad.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 22 – 41 is/are rejected under 35 U.S.C. 103 as being unpatentable over Belli et al (US 20220327189), Bel, Makhija et al (US 20210182659), Mak and Gottemukkula et al (US 9390327), Gott.
Claim 22: Bel teaches an authentication system for privacy-enabled authentication, the system comprising: at least one processor operatively connected to a memory, the at least one processor, when executing, configured to [Fig. 10]: instantiate one or more pre-trained neural networks, including a first pre-trained helper network associated with identification information of a first type, wherein the first pre-trained helper network is configured to: evaluate an unknown identification sample of the first type based on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated; ([089] a plurality of neural processing units (NPU) are instantiated. [041] The features extracted by the convolutional neural networks may also or alternatively include abstract, high-level combinations of features and shapes identified in the received query image and the enrollment images. [045] Feature infusion stage generally combines the extracted features for the received image generated in feature extraction stage and the combined feature representation of the plurality of enrollment images generated in feature aggregation stage into data that can be used by MLP to determine whether the received query image is from a real fingerprint or a copy of the real fingerprint. [047] plurality of CNNs are pre-trained on query images as part of an anti-spoofing protection model; [069] M-dimensional Gaussian distribution with independent dimensions can model the feature representation; [092] Such NPUs are configured to input a new piece of data and rapidly process it through an already trained model (i.e., pre-trained model) to generate a model output (e.g., an inference)).
execute at least a probabilistic evaluation of the unknown identification sample that includes a determination of a probability that the unknown identification sample improves or hinders the subsequent enrollment, authentication, or identification functions; ([067, Fig. 8] a combined vector with dimensions M×1, with each value in the combined vector being calculated as a log likelihood of a probability that x is from a real fingerprint, conditioned on μ and σ (i.e., as log p(x|μ, σ)). Mean feature vector and standard deviation vector may be interpreted as a representation of expected features of a live datapoint (e.g., an image captured of a real fingerprint as opposed to a copy of the real fingerprint); [077] By spatially aligning the query and enrollment images, the output of the matcher algorithm may improve the performance of a personalized anti-spoofing protection model used to determine whether the query image is from a real fingerprint or a copy of the real fingerprint based on features of the enrollment fingerprint images. [092] a neural processing units (NPUs) may thus be configured to input a new piece of data and rapidly process it through an already trained model to generate a model output).
validate the unknown information sample for use in subsequent enrollment, identification, or authentication, responsive to a determination that the unknown identification sample meets the evaluation criteria based, at least in part, on output from the first pre-trained helper network; ([047] After the combined feature representation is generated, an artificial neural network, such as MLP, can use the combined feature representation to determine whether the received query fingerprint image is from a real fingerprint or a copy of the real fingerprint. The output of the artificial neural network (e.g., the determination of whether the received query fingerprint image is from a real fingerprint or a copy of the real fingerprint) may be used to take one or more actions to allow or block access to a protected computing resource. [092] a neural processing units (NPUs) may thus be configured to input a new piece of data and rapidly process it through an already trained model to generate a model output).
Bel is silent on filter identification information used in subsequent enrollment, identification, or authentication functions.
But analogous art Mak teaches filter identification information used in subsequent enrollment, identification, or authentication functions ([072] In step 303, supplier name is cleansed where Parent master data enables enriching parent information using supplier Data in 303A and cleaning Parent name).
Therefore, it is prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Bel to include the idea of filtering id information as taught by Mak so that the graph (or edge or relationship) directly relates data items in the datastore [075].
Bel and Mak are silent on and reject the unknown identification sample for use in subsequent enrollment, identification, or authentication, responsive to a determination that the unknown identification sample fails the evaluation criteria based, at least in part, on output from the [first pre-trained helper] network.
But analogous art Gott teaches reject the unknown identification sample for use in subsequent enrollment, identification, or authentication, responsive to a determination that the unknown identification sample fails the evaluation criteria based, at least in part, on output from the [first pre-trained helper] network. (C18L52-62: A RANSAC outlier detection method can reject outliers that do not fit a hypothesized geometric transformation between the corresponding points in a matched point pair, e.g., in terms of geometries of ocular regions of interest encoded in enrollment and verification templates via vascular patterns).
Therefore, it is prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined inventions of Bel and Mak to include the idea of reject samples based on criteria as taught by Gott so that Hypothesis based outlier detection and image registration methods, such as RANSAC, can be used to identify one or more affine transformations or similar transformations that produce transformed template locations with the most inlier point pairs (C19L3-7).
Claim 23: the combination of Bel, Mak and Gott teaches the system of claim 22, wherein the first pre-trained helper network is configured to evaluate image-based information samples. (Bel: [07] receiving an image...; extracting, through a first artificial neural network, features for at least the received image; ... and the combined feature representation of the plurality of enrollment biometric data source images as input into a second artificial neural network...).
Claim 24: the combination of Bel, Mak and Gott teaches the system of claim 23, wherein the first pre-trained helper network is configured to evaluate image properties associated with the unknown image sample. (Bel: [036] Features may be extracted for the received image and for images in an enrollment image set using neural networks using different weights or using the same weights. In some aspects, features may be extracted for the images in the enrollment image set a priori (e.g., when a user enrolls a finger for use in fingerprint authentication, enrolls an iris for use in iris authentication, enrolls a face for use in facial recognition-based authentication, etc.). Features may be extracted for the images in the enrollment image set based on a non-image representation of the received image (also referred to as a query image) when a user attempts to authenticate through a biometric authentication pipeline; [092] a neural processing units (NPUs) may thus be configured to input a new piece of data (i.e., unknown) and rapidly process it through an already trained model to generate a model output (e.g., an inference)).
Claim 25: the combination of Bel, Mak and Gott teaches the system of claim 24, wherein the first pre-trained helper network is trained on images having properties that include at least one of blur that reduces identification capability, insufficient presence of landmarks in an input image, sufficient presence of landmarks, masked subjects, subjects wearing glasses, eye open state, or capture distance. (Bel: [030] This anti-spoofing protection model may be trained generically based on a predefined training data set to determine whether the captured sample 202 is from a real finger or a fake finger… For example, users may have varying skin characteristics that may affect the data captured in sample, such as dry skin, oily skin, or the like. Users with dry skin may, for example, cause generation of a sample with less visual acuity than users with oily skin. [032] anti-spoofing protection models may be inaccurate, because the training data set used to train these models may not account for natural variation between users that may change the characteristics of a sample captured for different users. For examples, users may have varying levels of contrast in iris color that may cause the generation of samples with differing levels of visual acuity, may wear glasses or other optics that affect the details captured in a sample, or the like).
Claim 26: the combination of Bel, Mak and Gott teaches the system of claim 22, wherein the at least one processor is configured to host a data authentication service configured to return status regarding validation or rejection of authentication information. (Bel: [047] After the combined feature representation 510 is generated, an artificial neural network, such as MLP 520, can use the combined feature representation 510 to determine whether the received query fingerprint image is from a real fingerprint or a copy of the real fingerprint. The output of the artificial neural network (e.g., the determination of whether the received query fingerprint image is from a real fingerprint or a copy of the real fingerprint) may be used to take one or more actions to allow or block access to a protected computing resource).
Claim 27: the combination of Bel, Mak and Gott teaches the system of claim 22, wherein the one or more pre-trained neural networks including a second pre-trained helper network associated with identification information of a second type. (Bel: [048] a second CNN 504 using a second set of parameters may be used to extract features from the plurality of enrollment images. In this example, CNNs 502 and 504 may use different weights and the same or different model architectures to extract visual features from query and enrollment images).
Claim 28: the combination of Bel, Mak and Gott teaches the system of claim 22, wherein the first pre-trained helper network is configured to identify bad, good, and spoofed information samples, wherein bad information samples reduce identification accuracy of the subsequent authentication or identification processing neural networks. (Bel: [023-24] The acceptable degree of similarity between a captured image and a reference image may be tailored to meet false acceptance rate (FAR) and false rejection rate (FRR) metrics ... biometric security systems may be fooled into falsely accepting spoofed biometric credentials, which may allow for unauthorized access to protected resources and other security breaches within a computing system… images or models of a user's face can be used to gain unauthorized access to a protected computing resource protected by a facial recognition system. [031-32] Thus, the accuracy of fingerprint authentication systems in identifying spoofing attacks is increased, which may increase the security of computing resources protected by fingerprint authentication systems).
Claim 29: the combination of Bel, Mak and Gott teaches the system of claim 22, wherein the first pre-trained helper network is configured to: process a video or image input as identification information; and determine that the video or image input is valid, invalid, or a presentation attack. (Bel: C23L13-29: Tiling can minimize registration artifacts. In some implementations, invalid tiles are identified and discarded from further analysis. For example, if the area corresponding to a particular tile does not include much visible eye vasculature, or includes a large portion of the skin or iris, the tile can be determined to be invalid. This validity determination can be made, for example, by comparing a sum of binary values of the area included in a tile to a threshold value, using eyelash detection algorithms, and/or using glare detection algorithms. In some implementations, a collection of aberration pixels (e.g. detected glare and eyelashes) that are within the white of eye, which in tum is determined by the segmentation process, can be generated. Whether one or more tiles are invalid can be determined based on the ratio of the number of aberration pixel counts to the number of the white of the eye pixels under the corresponding tiles).
Claim 30: Bel teaches a computer implemented method for privacy-enabled authentication, the method comprising: instantiating, by the at least one processor, one or more pre-trained neural networks, including a first pre-trained helper network associated with identification information of a first type, wherein the first pre-trained helper network is pre-trained on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated; evaluating, by the first pre-trained helper network, an unknown identification sample of the first type, responsive to input of the unknown identification sample of the first type to the first pre- trained helper network; executing, by the first pre-trained helper network, at least a probabilistic evaluation of the unknown identification sample that includes determining a probability that the unknown identification sample improves or hinders subsequent enrollment, authentication, or identification functions; and determining, by the first pre-trained helper network, if the unknown identification sample meets the evaluation criteria and validating the unknown identification sample for use in subsequent enrollment, identification, or authentication, or determining if the unknown identification sample does not meet the evaluation criteria. ([089] a plurality of NPUs may be instantiated. [041] The features extracted by the convolutional neural networks may also or alternatively include abstract, high-level combinations of features and shapes identified in the received query image and the enrollment images. [045] Feature infusion stage 430 generally combines the extracted features for the received image generated in feature extraction stage 410 and the combined feature representation of the plurality of enrollment images generated in feature aggregation stage 420 into data that can be used by MLP 440 to determine whether the received query image is from a real fingerprint or a copy of the real fingerprint. [047] plurality of CNNs 502 are pre-trained on query images as part of an anti-spoofing protection model; [067, Fig. 8] a combined vector 808 with dimensions M×1, with each value in the combined vector 808 being calculated as a log likelihood of a probability that x is from a real fingerprint, conditioned on μ and σ (i.e., as log p(x|μ, σ)). Mean feature vector 804 and standard deviation vector 806 may be interpreted as a representation of expected features of a live datapoint (e.g., an image captured of a real fingerprint as opposed to a copy of the real fingerprint); ; [069] M-dimensional Gaussian distribution with independent dimensions can model the feature representation; [077] By spatially aligning the query and enrollment images, the output of the matcher algorithm may improve the performance of a personalized anti-spoofing protection model used to determine whether the query image 902 is from a real fingerprint or a copy of the real fingerprint based on features of the enrollment fingerprint images. [092] a neural processing units (NPUs) may thus be configured to input a new piece of data and rapidly process it through an already trained model (i.e., pre-trained model) to generate a model output; [047] After the combined feature representation 510 is generated, an artificial neural network, such as MLP 520, can use the combined feature representation 510 to determine whether the received query fingerprint image is from a real fingerprint or a copy of the real fingerprint. The output of the artificial neural network (e.g., the determination of whether the received query fingerprint image is from a real fingerprint or a copy of the real fingerprint) may be used to take one or more actions to allow or block access to a protected computing resource. [092] a neural processing units (NPUs) may thus be configured to input a new piece of data and rapidly process it through an already trained model to generate a model output. [092] a neural processing units (NPUs) may thus be configured to input a new piece of data and rapidly process it through an already trained model to generate a model output).
Bel is silent on filtering, by at least one processor, identification information used in subsequent enrollment, identification, or authentication functions;
But analogous art Mak teaches filtering, by at least one processor, identification information used in subsequent enrollment, identification, or authentication functions; ([072] In step 303, supplier name is cleansed where Parent master data enables enriching parent information using supplier Data in 303A and cleaning Parent name).
Therefore, it is prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Bel to include the idea of filtering id information as taught by Mak so that the graph (or edge or relationship) directly relates data items in the datastore [075].
Bel and Mak are silent on and rejecting the unknown identification sample for use in subsequent enrollment, identification, or authentication.
But analogous art Gott teaches and rejecting the unknown identification sample for use in subsequent enrollment, identification, or authentication. (C18L52-62: A RANSAC outlier detection method can reject outliers that do not fit a hypothesized geometric transformation between the corresponding points in a matched point pair, e.g., in terms of geometries of ocular regions of interest encoded in enrollment and verification templates via vascular patterns).
Therefore, it is prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined inventions of Bel and Mak to include the idea of reject samples based on criteria as taught by Gott so that Hypothesis based outlier detection and image registration methods, such as RANSAC, can be used to identify one or more affine transformations or similar transformations that produce transformed template locations with the most inlier point pairs (C19L3-7).
Claim 31: the combination of Bel, Mak and Gott teaches the method of claim 30, wherein the act of evaluating includes evaluating, by the first pre-trained helper network, image-based identification samples. (Bel: [07] receiving an image...; extracting, through a first artificial neural network, features for at least the received image; ... and the combined feature representation of the plurality of enrollment biometric data source images as input into a second artificial neural network...).
Claim 32: the combination of Bel, Mak and Gott teaches the method of claim 31, wherein the act of evaluating includes evaluating, by the first pre-trained helper network, image properties associated with the unknown image sample. (Bel: [036] Features may be extracted for the received image and for images in an enrollment image set using neural networks using different weights or using the same weights. In some aspects, features may be extracted for the images in the enrollment image set a priori (e.g., when a user enrolls a finger for use in fingerprint authentication, enrolls an iris for use in iris authentication, enrolls a face for use in facial recognition-based authentication, etc.). Features may be extracted for the images in the enrollment image set based on a non-image representation of the received image (also referred to as a query image) when a user attempts to authenticate through a biometric authentication pipeline; [092] a neural processing units (NPUs) may thus be configured to input a new piece of data (i.e., unknown) and rapidly process it through an already trained model to generate a model output (e.g., an inference)).
Claim 33: the combination of Bel, Mak and Gott teaches the method of claim 32, wherein the first pre-trained helper network is trained on images having properties that include at least one of blur that reduces identification capability, insufficient presence of landmarks in an input image, sufficient presence of landmarks, masked subjects, subjects wearing glasses, eye open state, or capture distance. (Bel: [030] This anti-spoofing protection model may be trained generically based on a predefined training data set to determine whether the captured sample 202 is from a real finger or a fake finger… For example, users may have varying skin characteristics that may affect the data captured in sample, such as dry skin, oily skin, or the like. Users with dry skin may, for example, cause generation of a sample with less visual acuity than users with oily skin. [032] anti-spoofing protection models may be inaccurate, because the training data set used to train these models may not account for natural variation between users that may change the characteristics of a sample captured for different users. For examples, users may have varying levels of contrast in iris color that may cause the generation of samples with differing levels of visual acuity, may wear glasses or other optics that affect the details captured in a sample, or the like).
Claim 34: the combination of Bel, Mak and Gott teaches the method of claim 30, wherein the method further comprises: hosting, by the at least one processor, a data authentication service configured to return status regarding validation or rejection of authentication information. (Bel: [047] After the combined feature representation 510 is generated, an artificial neural network, such as MLP 520, can use the combined feature representation 510 to determine whether the received query fingerprint image is from a real fingerprint or a copy of the real fingerprint. The output of the artificial neural network (e.g., the determination of whether the received query fingerprint image is from a real fingerprint or a copy of the real fingerprint) may be used to take one or more actions to allow or block access to a protected computing resource).
Claim 35: the combination of Bel, Mak and Gott teaches the method of claim 30, wherein the act of instantiating includes, by the at least one processor, including a second pre-trained helper network associated with identification information of a second type. (Bel: [048] a second CNN 504 using a second set of parameters may be used to extract features from the plurality of enrollment images. In this example, CNNs 502 and 504 may use different weights and the same or different model architectures to extract visual features from query and enrollment images).
Claim 36: the combination of Bel, Mak and Gott teaches the method of claim 30, wherein the method further comprises: identifying, by the first pre-trained helper network, bad, good, and spoofed information samples, wherein bad information samples reduce identification accuracy of the subsequent authentication or identification processing neural networks. (Bel: [023-24] The acceptable degree of similarity between a captured image and a reference image may be tailored to meet false acceptance rate (FAR) and false rejection rate (FRR) metrics ... biometric security systems may be fooled into falsely accepting spoofed biometric credentials, which may allow for unauthorized access to protected resources and other security breaches within a computing system… images or models of a user's face can be used to gain unauthorized access to a protected computing resource protected by a facial recognition system. [031-32] Thus, the accuracy of fingerprint authentication systems in identifying spoofing attacks is increased, which may increase the security of computing resources protected by fingerprint authentication systems).
Claim 37: the combination of Bel, Mak and Gott teaches the method of claim 30, wherein the method further comprises: processing, by the first pre-trained helper network, a video or image input as identification information; and determining, by the first pre-trained helper network, whether the video or image input is valid, invalid, or a presentation attack. (Bel: C23L13-29: Tiling can minimize registration artifacts. In some implementations, invalid tiles are identified and discarded from further analysis. For example, if the area corresponding to a particular tile does not include much visible eye vasculature, or includes a large portion of the skin or iris, the tile can be determined to be invalid. This validity determination can be made, for example, by comparing a sum of binary values of the area included in a tile to a threshold value, using eyelash detection algorithms, and/or using glare detection algorithms. In some implementations, a collection of aberration pixels (e.g. detected glare and eyelashes) that are within the white of eye, which in tum is determined by the segmentation process, can be generated. Whether one or more tiles are invalid can be determined based on the ratio of the number of aberration pixel counts to the number of the white of the eye pixels under the corresponding tiles).
Claim 38: Bel teaches a non-transitory computer-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform a method for privacy-enabled authentication, the method comprising: instantiating a first pre-trained helper network associated with identification information of a first type, wherein the first pre-trained helper network is pre-trained on evaluation criteria that is independent of a subject of the identification information seeking to be enrolled, identified, or authenticated; evaluating an unknown identification sample of the first type, responsive to input of the unknown identification sample of the first type to the first pre-trained helper network; executing, at least a probabilistic evaluation of the unknown identification sample that includes determining a probability that the unknown identification sample improves or hinders the subsequent enrollment, authentication, or identification functions; and determining if the unknown identification sample meets the evaluation criteria and validating the unknown identification sample for use in subsequent enrollment, identification, or authentication, or determining if the unknown identification sample does not meet the evaluation criteria. ([089] a plurality of NPUs may be instantiated. [041] The features extracted by the convolutional neural networks may also or alternatively include abstract, high-level combinations of features and shapes identified in the received query image and the enrollment images. [045] Feature infusion stage 430 generally combines the extracted features for the received image generated in feature extraction stage 410 and the combined feature representation of the plurality of enrollment images generated in feature aggregation stage 420 into data that can be used by MLP 440 to determine whether the received query image is from a real fingerprint or a copy of the real fingerprint. [047] plurality of CNNs 502 are pre-trained on query images as part of an anti-spoofing protection model; [067, Fig. 8] a combined vector 808 with dimensions M×1, with each value in the combined vector 808 being calculated as a log likelihood of a probability that x is from a real fingerprint, conditioned on μ and σ (i.e., as log p(x|μ, σ)). Mean feature vector 804 and standard deviation vector 806 may be interpreted as a representation of expected features of a live datapoint (e.g., an image captured of a real fingerprint as opposed to a copy of the real fingerprint); [069] M-dimensional Gaussian distribution with independent dimensions can model the feature representation; [077] By spatially aligning the query and enrollment images, the output of the matcher algorithm may improve the performance of a personalized anti-spoofing protection model used to determine whether the query image 902 is from a real fingerprint or a copy of the real fingerprint based on features of the enrollment fingerprint images. [092] a neural processing units (NPUs) may thus be configured to input a new piece of data and rapidly process it through an already trained model (i.e., pre-trained model) to generate a model output; [047] After the combined feature representation 510 is generated, an artificial neural network, such as MLP 520, can use the combined feature representation 510 to determine whether the received query fingerprint image is from a real fingerprint or a copy of the real fingerprint. The output of the artificial neural network (e.g., the determination of whether the received query fingerprint image is from a real fingerprint or a copy of the real fingerprint) may be used to take one or more actions to allow or block access to a protected computing resource. [092] a neural processing units (NPUs) may thus be configured to input a new piece of data and rapidly process it through an already trained model to generate a model output).
Bel is silent on filtering identification information used in subsequent enrollment, identification, or authentication functions;
But analogous art Mak teaches filtering, by at least one processor, identification information used in subsequent enrollment, identification, or authentication functions; ([072] In step 303, supplier name is cleansed where Parent master data enables enriching parent information using supplier Data in 303A and cleaning Parent name).
Therefore, it is prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Bel to include the idea of filtering id information as taught by Mak so that the graph (or edge or relationship) directly relates data items in the datastore [075].
Bel and Mak are silent on and rejecting the unknown identification sample for use in subsequent enrollment, identification, or authentication.
But analogous art Gott teaches and rejecting the unknown identification sample for use in subsequent enrollment, identification, or authentication. (C18L52-62: A RANSAC outlier detection method can reject outliers that do not fit a hypothesized geometric transformation between the corresponding points in a matched point pair, e.g., in terms of geometries of ocular regions of interest encoded in enrollment and verification templates via vascular patterns).
Therefore, it is prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined inventions of Bel and Mak to include the idea of reject samples based on criteria as taught by Gott so that Hypothesis based outlier detection and image registration methods, such as RANSAC, can be used to identify one or more affine transformations or similar transformations that produce transformed template locations with the most inlier point pairs (C19L3-7).
Claim 39: the combination of Bel, Mak and Gott teaches the medium of claim 38, wherein the first pre-trained helper network is configured to evaluate image-based information samples. (Bel: [07] receiving an image...; extracting, through a first artificial neural network, features for at least the received image; ... and the combined feature representation of the plurality of enrollment biometric data source images as input into a second artificial neural network...).
Claim 40: the combination of Bel, Mak and Gott teaches the medium of claim 39, wherein the first pre-trained helper network is configured to evaluate image properties associated with the unknown image sample. (Bel: [092] a neural processing units (NPUs) may thus be configured to input a new piece of data (i.e., unknown) and rapidly process it through an already trained model to generate a model output (e.g., an inference)).
Claim 41: the combination of Bel, Mak and Gott teaches the medium of claim 40, wherein the first pre-trained helper network is trained on images having properties that include at least one of: blur that reduces identification capability, insufficient presence of landmarks in an input image, sufficient presence of landmarks, masked subjects, subjects wearing glasses, eye open state, or capture distance. (Bel: [030] This anti-spoofing protection model may be trained generically based on a predefined training data set to determine whether the captured sample 202 is from a real finger or a fake finger… For example, users may have varying skin characteristics that may affect the data captured in sample, such as dry skin, oily skin, or the like. Users with dry skin may, for example, cause generation of a sample with less visual acuity than users with oily skin. [032] anti-spoofing protection models may be inaccurate, because the training data set used to train these models may not account for natural variation between users that may change the characteristics of a sample captured for different users. For examples, users may have varying levels of contrast in iris color that may cause the generation of samples with differing levels of visual acuity, may wear glasses or other optics that affect the details captured in a sample, or the like).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO-892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Badri Champakesan whose telephone number is (571)270-3867. The examiner can normally be reached M-F: 8.30am-4.30pm (EST). Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jung Kim can be reached at (571) 272-3804. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/BADRINARAYANAN /Primary Examiner, Art Unit 2494.
Prosecution Insights