DETAILED ACTION
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 .
Applicant(s) Response to Official Action
The response filed on 03/11/2026 has been entered and made of record.
Response to Arguments/Amendments
Presented arguments have been fully considered, but some are rendered moot in view of the new ground(s) of rejection necessitated by amendment(s) initiated by the applicant(s). Examiner fully addresses below any arguments that were not rendered moot.
Claim Rejections - 35 USC § 112
Summary of Arguments:
Regarding claims 21, 23, 24, 26, 29, 31, 32, 34, 37, 38, and 41-47 Applicant argues that the claim recites an embodiment supported by a combination of Fig. 8 and Fig 2. In para. 0121, the specification states that “In an embodiment, a binary decision tree may be designed to interface with different models and approaches, including an intermediate decision approach of Fig. 2 for an iris liveness detection...” In the claim, the “classifying… to predict whether an image is a presentation attack” represents node 802 (“Root node 802 is used to determine whether an incoming image depicts a live iris or a presentation attack image.”, Specification, para. 0122) of Fig. 8 as an intermediate decision prior to step 218 of Fig. 2.
Support for “upon determining that the second feature vector is classified as a live image,” is represented by the “Yes” decision between node 802 and node 804. “Determining that the eye of the live face corresponds to the user’s eye based at least in part on a comparison of the first set of feature vectors and the second feature vector” is represented by node 804 and step 218 of Fig. 2. As described in the Specification, “if it was determined that the incoming image is an image of a live person, then, in intermediary decision node 804, one or more image recognition modules are invoked to perform an iris recognition on the incoming image.” (Specification, para 0123)
The use of a trained model for the classification is disclosed in para. 0084, which explains that “The vectors… may be used to train an image classifier to predict whether other images most likely depict the user of the mobile device or whether the other images are presentation attacks on the device.” (Specification, para. 0084) Trained model feature vectors for a live user may be calculated when the user's mobile device is configured to implement an iris liveness detection approach. The vectors may be generated based on one or more images depicting for example, facial features of the user, and may be used to train an image classifier to predict whether other images most likely depict the user of the mobile device or whether the other images are presentation attacks on the device.
The Office action further suggests a lack of support for limitations reciting that the image data represents a portion of the user’s face comprising at least one nose or an entire face (claims 42-47). Paragraph [0084] describes generating vectors from “images depicting for example, facial features of the user,” and paragraph [0027] describes trained model feature vectors “generated based on images depicting an owner of a mobile device.” These disclosures encompass images of faces and facial features and thus reasonably convey possession of image data that represents a portion of the user’s face comprising a nose or an entire face. (Specification, paragraphs [0084], [0027]).
Examiner’s Response:
[AltContent: textbox (216 Retrieve Trained Model Feature Vectors from Storage unit)][AltContent: textbox (Attack)][AltContent: oval][AltContent: textbox (Dq,live<β ?
802)][AltContent: textbox ()][AltContent: arrow][AltContent: arrow][AltContent: arrow][AltContent: textbox (218 Determine a Distance Metric (DM) based on Feature Vector and the Trained Model Feature Vectors and 804 Change in Pupil Characteristic?)][AltContent: textbox (Yes
)][AltContent: textbox (No
)][AltContent: textbox (220
DM>Threshold)][AltContent: arrow][AltContent: arrow][AltContent: textbox (222 The RGB/NIR Pair Depicts a Live Person)][AltContent: textbox (224 The RGB/NIR Pair Does Not Depict a Live Person)][AltContent: arrow]
Examiner respectfully disagrees. Regarding claims 21, 29 and 34, Examiner did not find node 804 and step 218 of Fig. 2 along with corresponding ¶’s to be adequate support for “determining that the eye of the live face corresponds to the user’s eye based at least in part on a comparison of the first set of feature vectors and the second feature vector” as illustrated above. Step 218 (fig. 2) only compute the distance metric DM as a deviation (error) d measured as the square root of the entropy approximation to the logarithm of evidence ratio when testing whether the query image can be represented as the same underlying distribution of the live images. This can be mathematically represented as dq,db (¶0088, equations(7-8)). Root node 802 also relies on the same distance metric dq,db (i.e. Root node 802 is used to determine whether an incoming image depicts a live iris or a presentation attack image. This may be determined based on a distance metric dq,db computed using expressions (7)-(8) described above, and where q represents an incoming image (a query image) and db represents a feature vector Fdb described above- ¶0122). In both node 802 and step 220 are determining whether the presented image is a live image based on the same distance metric but seemingly using the same threshold (i.e. In step 220 of stage 212, a distance metric dq,db computed using expressions (7)-(8) is used to determine whether an incoming query image depicts a live person. If dq,db<β, where β∈˜ is a predetermined certain threshold, then, in step 222, it is determined that the query image depicts a live person- ¶0090… In root node 802, a decision is made whether dq,db<β, where β∈˜ and corresponds to a predetermined threshold value. If dq,db<β, then it may be concluded that the incoming image depicts a live person- ¶0123). Therefore, the Applicant’s claim construction seems to suggest that “determining whether images depict a live person or are part of a presentation attack” is being performed twice.
Examiner acknowledges that ¶0121 mentions the possibilities of integrating a binary decision tree for the embodiment described in fig. 2; however, the example of fig. 8 described in ¶0122-0126 is only an example binary decision tree used to determine whether images depict a live person or are part of a presentation attack. ¶0122-0126 does not provide support for the integration of the embodiment described in fig. 8 with the embodiment fig. 2 as claimed. The only reasonable insertion of node 802-804-806-808-810 into fig. 2 would be a replacement of steps 220 and beyond since node 802of fig. 8 is similar to step 220 as it is also a binary decision point.
¶0084 discloses training an “an image classifier to predict whether other images most likely depict the user of the mobile device or whether the other images are presentation attacks on the device” using “Trained model feature vectors”. ¶0084 does not describe “classifying, using an image classifier trained to predict whether an image is a presentation attack, the second feature vector as from either a live image or a presentation attack”. This is contradictory to applicant own remarks that “classifying, using an image classifier trained to predict whether an image is a presentation attack, the second feature vector as from either a live image or a presentation attack” represents node 802 which uses as a classifier which uses a distance metric(¶0021, fig. 2, fig. 8).
¶0084 and ¶0027 does not provide support for using nose portion or the entire face in the image of the user to compute the claimed vectors for eye/iris liveness detection. Fig. 2, which Applicant relied to so far, uses the eye-iris region to compute the different vectors (¶0058), there is no mentioned of any other parts of the user’s face, let alone the user’s entire face.
Accordingly, Examiner maintains the rejections.
Claim Rejections - 35 USC § 103
Summary of Arguments:
Regarding claims 21, 23, 24, 26, 29, 31, 32, 34, 37, 38, and 41-47 Applicant disagrees with the Examiner’s Claim Interpretation in light of the original disclosure and submits that the claim recites an embodiment supported by a combination of Fig. 8 and Fig 2. In para. 0121, the specification states that “In an embodiment, a binary decision tree may be designed to interface with different models and approaches, including an intermediate decision approach of Fig. 2 for an iris liveness detection…” In the claim, the “classifying… to predict whether an image is a presentation attack” represents node 802 (“Root node 802 is used to determine whether an incoming image depicts a live iris or a presentation attack image.”, Specification, para. 0122) of Fig. 8 as an intermediate decision prior to step 218 of Fig. 2.
Examiner’s Response:
Examiner respectfully disagrees. Regarding claims 21, 23, 24, 26, 29, 31, 32, 34, 37, 38, and 41-47 Examiner contends the Claim Interpretation provided is clear concise and consistent with the original disclosure. The Applicant’s disagreement does not constitute an argument that can be responded to.
Since no significant amendments, consistent with the original disclosure, were entered to preclude the Examiner from the contended interpretations. Accordingly, Examiner maintains the prior art rejections.
Claim Interpretation
In light of the original disclosure, the Examiner will interpret the claim element “second image data representing at least a portion of a live face comprising an eye” as image data acquired live during step 204 of stage 202 (i.e. fig. 2) or step 902 (i.e. fig. 9… Once a good quality eye region is detected, both RGB and NIR images of the eye region are acquired… These two images, Iv and Ii are fused to make a hyperspectral image Ih- page 97, section A; provisional specs); while interpreting the claim element “first image data representing at least a portion of the user’s face comprising a user's eye” as image data used to generate and store “one or more trained model feature vectors” (i.e. The trained model feature vectors may be generated based on images depicting an owner of a mobile device- ¶0026, Application as filed… The training feature vectors for the live user are calculated while the iris enrolling stage- page 98, section C.; Provisional Specs). It is to be noted the independent claims recite “second image data representing at least a portion of a live face comprising an eye”, this seems to suggest, in this claim, only image comprising portion of a live face’s will be presented to the iris liveness system/method; therefore, it can be interpreted that the classifier will always classify the “second feature vector as from a live image”.
Claims 42-47 recite “wherein the at least a portion of the user's face comprises an entire face/at least one nose”. The Examiner, will contemplate interpreting the combine limitation “generating a second feature vector based on the second image data (representing at least a portion of a live face wherein the at least a portion of the user's face comprises an entire face/at least one nose)” as using the eye portion of the “second image data representing at least a portion of a live face, wherein the at least a portion of the user's face comprises an entire face/at least one nose”. This interpretation is consistent with ¶0059 Applicant’s original disclosure.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 21, 23, 24, 26, 29, 31, 32, 34, 37, 38 and 41-47 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. Applicant has not pointed out where the new (or amended) claim is supported, nor does there appear to be a written description of the following claim limitations in the application as filed:
classifying, using an image classifier trained to predict whether an image is a presentation attack, the second feature vector as from either a live image or a presentation attack; upon determining that the second feature vector is classified as a live image, determining that the eye of the live face corresponds to the user's eye based at least in part on a comparison of the first set of feature vectors and the second feature vector (claims 21, 29 and 34);
wherein the at least a portion of the user's face comprises at least one nose (Claims 42, 44 and 46); and
wherein the at least a portion of user's face comprises an entire face (Claim 43, 45 and 47).
The Examiner did not find in the original disclosure the sequence of steps “classifying, using an image classifier trained to predict whether an image is a presentation attack, the second feature vector as from either a live image or a presentation attack; upon determining that the second feature vector is classified as a live image, determining that the eye of the live face corresponds to the user's eye based at least in part on a comparison of the first set of feature vectors and the second feature vector” (claims 21, 29 and 34). It seems that the limitation “classifying, using an image classifier trained to predict whether an image is a presentation attack, the second feature vector as from either a live image or a presentation attack” corresponds to step 220 in fig. 2 or step 914 in fig. 9 (applicant’s original disclosure), wherein the distance metric (DM=dq,db- eq. 7-8) is calculated based on the feature vector (Fq- ¶0088) of a query image (i.e. “second feature vector”) and the trained model feature vector (Fdb- ¶0088) (i.e. “first set of one or more feature vectors”). The following step, separate from the preceding step, “upon determining that the second feature vector is classified as a live image, determining that the eye of the live face corresponds to the user's eye based at least in part on a comparison of the first set of feature vectors and the second feature vector” was not found as claimed in the original disclosure. More particularly, let’s denote as fmatch(Fq, Fdb) as the later mentioned step, no such step/function that requires Fq and Fdb was found in the original disclosure.
For the purpose of examining, Examiner will contemplate interpreting “determining that the eye of the live face corresponds to the user's eye based at least in part on a comparison of the first set of feature vectors and the second feature vector” as determining that the eye of the live face corresponds to the user's eye based on when it is determined that the presented image is a live image, wherein determining that the presented image is a live image is based on the first set of feature vectors and the second feature vector.
Claim Rejections - 35 USC § 103
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 of this title, 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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
Claims 21, 23, 24, 29, 31, 32, 34, 37 and 42-49 are rejected under 35 U.S.C. 103 as being unpatentable over Chen Feng [US 20160019420 A1: and incorporated by reference Tao Sheng US 20130272570 A1, hereafter Tao: all already of record] in view Rahib Hidayat Abiyev et al. [Neural network based biometric personal identification with fast iris segmentation: already of record].
Regarding claim 21, Chen teaches and/or suggests:
21. (Currently Amended) An electronic device (i.e. Certain aspects relate to systems and techniques for generating high resolution iris templates and for detecting spoofs, enabling more reliable and secure iris authentication- Abstract) comprising:
an image sensor (i.e. front-facing camera 150- ¶0032... camera 212- fig. 2, ¶0036); one or more processors; and one or more computer-readable media storing instructions that (i.e. Another aspect relates to a non-transitory computer-readable medium storing instructions that, when executed, configure at least one processor to perform operations comprising receiving image data of an eye- ¶0009), when executed by the one or more processors, cause the electronic device to perform operations comprising:
generating, at a first time and using the image sensor (i.e. In some embodiments, blocks 310 and 315 can be performed independently of some other portions of the process 300, for example during generation of an initial iris template of a user of the system 200 for storage and use in future identity authentication- ¶0050), first image data (i.e. NIR image data- ¶0025) representing at least a portion of a user’s face, comprising a user’s(i.e. Accordingly, one aspect relates to a system for multispectral fake iris detection, the system comprising at least one image sensor configured for capture of image data of an eye of a user, the eye including an iris region and a sclera region, the image data including at least a near-infrared (NIR) channel and a red channel- ¶0007) eye (i.e. In some embodiments, camera 212 can capture a number of image frames for each of RGB and NIR image data, such as in a video recording mode- ¶0037), the first image data (i.e. Pairs of visible light (RGB) and near-infrared (NIR) images can be captured by the iris authentication system for use in iris authentication- ¶0025) being associated with a first image type (i.e. near-infrared (NIR) images- ¶0025);
generating a first set of one or more feature vectors based on the first image data (i.e. an initial iris template of a user of the system 200 for storage and use in future identity authentication- ¶0050));
storing the first set of one or more feature vectors (i.e. a stored iris template- ¶0054);
generating, at a second time and using the image sensor, second image data representing at least a portion of a live face comprising an eye(i.e. In some embodiments, camera 212 can capture a number of image frames for each of RGB and NIR image data, such as in a video recording mode- ¶0037), the second image data(i.e. Pairs of visible light (RGB) and near-infrared (NIR) images can be captured by the iris authentication system for use in iris authentication- ¶0025) being associated with the first image type(i.e. near-infrared (NIR) images- ¶0025);
generating a second feature vector based on the second image (i.e. At block 325, in some embodiments the iris verification module 244 can use the NIR fused iris image (or an NIR image or data from the NIR channel of a four-channel image) to generate an unwrapped and normalized polar image of the feature pattern in the iris, encode the pattern of iris features to generate a template of the iris- ¶0052);
classifying, using an image classifier trained to predict whether an image is a presentation attack, the second feature vector as from either a live image or a presentation (i.e. A variety of materials and methods, from the inexpensive to the very sophisticated, can be used to circumvent traditional iris identification systems. Called “spoofs,” these fake irises range from images of irises reproduced on paper, spheres, or other materials to high-resolution iris reproductions on contact lenses that can even be worn and used, undetected, in access control environments that have trained attendants- ¶0005) attack(i.e. decision block 330, the authentication module 246 can determine whether the liveness score generated by liveness detection module 242 indicates a live iris. If the liveness score generated from the captured image data deviates from an expected liveness score value or range of values known to correspond to genuine live eyes then the process 300 can transition to block 345 and authentication module 246 may output an authentication fail indication. Although depicted as being performed after block 325, in some embodiments the decision of block 330 can be made after the liveness detection of block 320. If the imaged iris fails the liveness detection, authentication module 246 may output an authentication fail indication at block 345 without the system 200 performing iris verification at block 325, conserving processing resources and time as well as battery life of a mobile device implementing the system 200. Accordingly, in some embodiments of the process 300, blocks 325 and 335 may be optional- ¶0053);
upon determining that the second feature vector is classified as a live image (i.e. 330[Wingdings font/0xE0]YES[Wingdings font/0xE0]335- fig. 3), determining that the eye of the live face corresponds to the user's eye (i.e. If the iris is real, then the system can perform iris feature matching to determine whether the iris matches a user iris stored in a template. A real iris that matches a stored template iris can result in user authentication- ¶0027) based at least in part on a comparison of the first set of feature vectors (i.e. a stored iris template- ¶0054) and the second feature (i.e. template generated from the imaged iris- ¶0054) vector (i.e. The encoded features of the iris template can be compared to a stored template using Hamming distance in some embodiments to generate a quantitative assessment of likeness- ¶0052... At block 335 the authentication module 246 can determine whether the output of the iris verification module 244 indicates a match between the template generated from the imaged iris and a stored iris template. In some embodiments the iris verification module 244 can use Hamming distance to output a match score representing the level of statistical significance between the current iris template and the stored iris template. Hamming distance is the measurement of the number of bits between two templates which are not the same. Hence match scores based on Hamming distance are dissimilarity score, and the lower the score between two templates, the more likely they are from the same user- ¶0054); and
unlocking the electronic device in response to the determination that the eye of the live face corresponds to the user's eye (i.e. At block 301 the multispectral iris authentication system 200 can receive an authentication request to authenticate the identity of a user. For example, the authentication request can be triggered in various embodiments by a user request to unlock a digitally locked mobile device, log in to a secure account, enter a secure location, or the like- ¶0047... At block 301 the multispectral iris authentication system 200 can receive an authentication request to authenticate the identity of a user. For example, the authentication request can be triggered in various embodiments by a user request to unlock a digitally locked mobile device, log in to a secure account, enter a secure location, or the like- ¶0055).
However, Chen does not teach explicitly:
providing the first image data to a trained model, wherein the model is trained to produce feature vectors based upon images of at least portions of faces comprising at least one eye.
In the same field of endeavor, Rahib teaches:
providing the first image data to a trained model, wherein the model is trained to produce feature vectors based upon images of at least portions of faces comprising at least one eye (i.e. Located iris is extracted from an eye image, and, after normalization and enhancement, it is represented by a data set. Using this data set a Neural Network (NN) is used for the classification of iris patterns- Abstract... During training the value of the following cost function is calculated Eq. (10)... Here n is the number of output signals of the network and d and Pk Pk are the desired and the current output values of the network, respectively- § 3.2).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Chen with the teachings of Rahib to improve computational power of neural network and to decrease training error (Rahib- page 22 col 1).
Regarding claim 23, Chen and Rahib teach all the limitations of claim 21 and Chen further teaches:
wherein: the first image type is near infra-red(i.e. In some embodiments, camera 212 can capture a number of image frames for each of RGB and NIR image data, such as in a video recording mode- ¶0037).
Regarding claim 24, Chen and Rahib teach all the limitations of claim 21 and Chen further teaches:
the image sensor comprises a red-green-blue/near infra-red hybrid sensor (i.e. the image capture stage 210 can be accomplished by a camera 212 including an RGB-IR or RGBN image sensor 214 and an NIR flash LED 216. In other embodiments separate NIR and RGB sensors can be used to capture the images for iris authentication- ¶0037).
Regarding claim 29, method claim 29 corresponds to apparatus claim 21, and therefore is also rejected for the same reasons of obviousness as listed above.
Regarding claim 31, method claim 31 corresponds to apparatus claim 23, and therefore is also rejected for the same reasons of obviousness as listed above.
Regarding claim 32, method claim 32 corresponds to apparatus claim 24, and therefore is also rejected for the same reasons of obviousness as listed above.
Regarding claim 34, Chen teaches and/or suggests:
34. (Currently Amended) An electronic device (i.e. Certain aspects relate to systems and techniques for generating high resolution iris templates and for detecting spoofs, enabling more reliable and secure iris authentication- Abstract) comprising:
an image sensor (i.e. front-facing camera 150- ¶0032... camera 212- fig. 2, ¶0036); one or more processors; and one or more computer-readable media storing instructions that (i.e. Another aspect relates to a non-transitory computer-readable medium storing instructions that, when executed, configure at least one processor to perform operations comprising receiving image data of an eye- ¶0009), when executed by the one or more processors, cause the electronic device to perform operations comprising:
generating, at a first time and using the image sensor (i.e. In some embodiments, blocks 310 and 315 can be performed independently of some other portions of the process 300, for example during generation of an initial iris template of a user of the system 200 for storage and use in future identity authentication- ¶0050), first image data (i.e. NIR image data- ¶0025) representing at least a portion of a user’s face comprising a user’s(i.e. Accordingly, one aspect relates to a system for multispectral fake iris detection, the system comprising at least one image sensor configured for capture of image data of an eye of a user, the eye including an iris region and a sclera region, the image data including at least a near-infrared (NIR) channel and a red channel- ¶0007) eye (i.e. In some embodiments, camera 212 can capture a number of image frames for each of RGB and NIR image data, such as in a video recording mode- ¶0037);
generating a first set of one or more feature vectors based on the first image data (i.e. an initial iris template of a user of the system 200 for storage and use in future identity authentication- ¶0050);
storing the first set of one or feature vectors (i.e. a stored iris template- ¶0054);
generating, at a second time and using the image sensor, second image data representing at least a portion of a live face (i.e. In some embodiments, camera 212 can capture a number of image frames for each of RGB and NIR image data, such as in a video recording mode- ¶0037).
generating a second feature vector based on the second image data (i.e. At block 325, in some embodiments the iris verification module 244 can use the NIR fused iris image (or an NIR image or data from the NIR channel of a four-channel image) to generate an unwrapped and normalized polar image of the feature pattern in the iris, encode the pattern of iris features to generate a template of the iris- ¶0052);
classifying, using an image classifier trained to predict whether an image is a presentation attack, the second feature vector as from either a live image or a presentation (i.e. A variety of materials and methods, from the inexpensive to the very sophisticated, can be used to circumvent traditional iris identification systems. Called “spoofs,” these fake irises range from images of irises reproduced on paper, spheres, or other materials to high-resolution iris reproductions on contact lenses that can even be worn and used, undetected, in access control environments that have trained attendants- ¶0005) attack(i.e. decision block 330, the authentication module 246 can determine whether the liveness score generated by liveness detection module 242 indicates a live iris. If the liveness score generated from the captured image data deviates from an expected liveness score value or range of values known to correspond to genuine live eyes then the process 300 can transition to block 345 and authentication module 246 may output an authentication fail indication. Although depicted as being performed after block 325, in some embodiments the decision of block 330 can be made after the liveness detection of block 320. If the imaged iris fails the liveness detection, authentication module 246 may output an authentication fail indication at block 345 without the system 200 performing iris verification at block 325, conserving processing resources and time as well as battery life of a mobile device implementing the system 200. Accordingly, in some embodiments of the process 300, blocks 325 and 335 may be optional- ¶0053);
upon determining that the second feature vector is classified as a live image (i.e. 330[Wingdings font/0xE0]YES[Wingdings font/0xE0]335- fig. 3), determining that the eye of the live face corresponds to the user's eye (i.e. If the iris is real, then the system can perform iris feature matching to determine whether the iris matches a user iris stored in a template. A real iris that matches a stored template iris can result in user authentication- ¶0027) based at least in part on a comparison of the first set of feature vectors (i.e. a stored iris template- ¶0054) and the second feature (i.e. template generated from the imaged iris- ¶0054) vector (i.e. The encoded features of the iris template can be compared to a stored template using Hamming distance in some embodiments to generate a quantitative assessment of likeness- ¶0052... At block 335 the authentication module 246 can determine whether the output of the iris verification module 244 indicates a match between the template generated from the imaged iris and a stored iris template. In some embodiments the iris verification module 244 can use Hamming distance to output a match score representing the level of statistical significance between the current iris template and the stored iris template. Hamming distance is the measurement of the number of bits between two templates which are not the same. Hence match scores based on Hamming distance are dissimilarity score, and the lower the score between two templates, the more likely they are from the same user- ¶0054); and
unlocking the electronic device in response to the determination that the eye of the live face corresponds to the user's eye (i.e. At block 301 the multispectral iris authentication system 200 can receive an authentication request to authenticate the identity of a user. For example, the authentication request can be triggered in various embodiments by a user request to unlock a digitally locked mobile device, log in to a secure account, enter a secure location, or the like- ¶0047... At block 301 the multispectral iris authentication system 200 can receive an authentication request to authenticate the identity of a user. For example, the authentication request can be triggered in various embodiments by a user request to unlock a digitally locked mobile device, log in to a secure account, enter a secure location, or the like- ¶0055).
However, Chen does not teach explicitly:
providing the first image data to a trained model, wherein the model is trained to produce feature vectors based upon images of at least portions of faces comprising at least one eye.
In the same field of endeavor, Rahib teaches:
providing the first image data to a trained model, wherein the model is trained to produce feature vectors based upon images of at least portions of faces comprising at least one eye (i.e. Located iris is extracted from an eye image, and, after normalization and enhancement, it is represented by a data set. Using this data set a Neural Network (NN) is used for the classification of iris patterns- Abstract... During training the value of the following cost function is calculated Eq. (10)... Here n is the number of output signals of the network and d and Pk Pk are the desired and the current output values of the network, respectively- § 3.2).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Chen with the teachings of Rahib to improve computational power of neural network and to decrease training error (Rahib- page 22 col 1).
Regarding claim 37, Chen and Rahib teach all the limitations of claim 34 and Chen further teaches:
wherein: the image sensor is a first type of image sensor; and the electronic device further comprises an additional image sensor, the additional image sensor being a second type that is different than the first type (i.e. In some embodiments, the camera 150 can include separate RGB and NIR sensors)- ¶0032.
Regarding claim 38, Chen and Rahib teach all the limitations of claim 34 and Chen further teaches:
the image sensor comprises a red-green-blue/near infra-red hybrid sensor (i.e. the image capture stage 210 can be accomplished by a camera 212 including an RGB-IR or RGBN image sensor 214 and an NIR flash LED 216. In other embodiments separate NIR and RGB sensors can be used to capture the images for iris authentication- ¶0037).
Regarding claim 42, Chen and Rahib teach all the limitations of claim 21 and Chen further teaches:
wherein the at least a portion of the user's face comprises at least one nose (i.e. In the iris tracking stage 220, a tracking module 221 can receive a number of RGB frames 222 and a number of NIR frames 224 from the camera 212.- ¶0038, fig. 2).
Regarding claim 43, Chen and Rahib teach all the limitations of claim 21 and Chen further teaches:
wherein the at least a portion of user's face comprises an entire face (i.e. In the iris tracking stage 220, a tracking module 221 can receive a number of RGB frames 222 and a number of NIR frames 224 from the camera 212.- ¶0038, fig. 2).
Regarding claim 44, Chen and Rahib teach all the limitations of claim 29 and Chen further teaches:
wherein the at least a portion of the user's face comprises at least one nose (i.e. In the iris tracking stage 220, a tracking module 221 can receive a number of RGB frames 222 and a number of NIR frames 224 from the camera 212.- ¶0038, fig. 2).
Regarding claim 45, Chen and Rahib teach all the limitations of claim 29 and Chen further teaches:
wherein the at least a portion of user's face comprises an entire face (i.e. In the iris tracking stage 220, a tracking module 221 can receive a number of RGB frames 222 and a number of NIR frames 224 from the camera 212.- ¶0038, fig. 2).
Regarding claim 46, Chen and Rahib teach all the limitations of claim 34 and Chen further teaches:
wherein the at least a portion of the user's face comprises at least one nose (i.e. In the iris tracking stage 220, a tracking module 221 can receive a number of RGB frames 222 and a number of NIR frames 224 from the camera 212.- ¶0038, fig. 2).
Regarding claim 47, Chen and Rahib teach all the limitations of claim 34 and Chen further teaches:
wherein the at least a portion of user's face comprises an entire face (i.e. In the iris tracking stage 220, a tracking module 221 can receive a number of RGB frames 222 and a number of NIR frames 224 from the camera 212.- ¶0038, fig. 2).
Regarding claim 46, Chen and Rahib teach all the limitations of claim 34 and Chen further teaches:
wherein the classifier trained to predict whether an image is a presentation attack comprises a binary decision tree.
Regarding claim 47, Chen and Rahib teach all the limitations of claim 34 and Chen further teaches:
wherein the classifier trained to predict whether an image is a presentation attack comprises a binary decision tree.
Regarding claim 48, Chen and Rahib teach all the limitations of claim 34 and Chen further teaches:
wherein the classifier trained to predict whether an image is a presentation attack comprises a binary decision tree (i.e. see decision blocks 330 and 335- fig. 3).
Regarding claim 49, Chen and Rahib teach all the limitations of claim 34 and Chen further teaches:
wherein the classifier trained to predict whether an image is a presentation attack comprises a binary decision tree (i.e. see decision blocks 330 and 335- fig. 3).
Claims 26 and 41 are rejected under 35 U.S.C. 103 as being unpatentable over Chen Feng [US 20160019420 A1: and incorporated by reference Tao Sheng US 20130272570 A1, hereafter Tao: all already of record] in view Rahib Hidayat Abiyev et al. [Neural network based biometric personal identification with fast iris segmentation] in view of Haoqiang Fan et al. [US 20170061251 A1: already of record].
Regarding claim 26, Chen and Rahib teach all the limitations of claim 21.
However, Chen and Rahib do not teach explicitly:
wherein determining that the eye of the live face corresponds the user's eye based in least in part on the change comprises determining that the change is equal to or less than a threshold change.
In the same field of endeavor, Fan teaches:
wherein determining that the eye of the live face corresponds user's eye based in least in part on the change comprises determining that the change is equal to or less than a threshold change (i.e. the liveness detection module 22 prompts displaying of the predetermined content, the predetermined content includes a target whose position changes. The feature signal determination unit 221 determines, based on the video data, a face image contained therein as the object to be detected; extracts position information of canthus and pupil in the face image; determines, based on the position information of canthus and pupil, a relative position sequence of the pupil in a time period of displaying the predetermined content; and determines a correlation coefficient between the relative position sequence of the pupil and a position sequence of the target whose position changes as the feature signal. The feature signal judgment unit 222 judges whether the correlation coefficient is greater than a first predetermined threshold, and if the correlation coefficient is greater than the first predetermined threshold, identifies that the object to be detected is a living body- ¶0050).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Chen and Rahib with the teaching of Fan to effectively differentiate a normal user from a picture, a video, or a mask and so on used by an attacker, and no specific cooperation is required from the user, and security and usability of the liveness detection system are improved (Fan- ¶0044).
Regarding claim 41, Chen and Rahib teach all the limitations of claim 29.
However, Chen and Rahib do not teach explicitly:
wherein determining that the unknown eye is the user's eye based in least in part on the change comprises determining that the change is equal to or less than a threshold change.
In the same field of endeavor, Fan teaches:
wherein determining that the unknown eye is the user's eye based in least in part on the change comprises determining that the change is equal to or less than a threshold change (i.e. the liveness detection module 22 prompts displaying of the predetermined content, the predetermined content includes a target whose position changes. The feature signal determination unit 221 determines, based on the video data, a face image contained therein as the object to be detected; extracts position information of canthus and pupil in the face image; determines, based on the position information of canthus and pupil, a relative position sequence of the pupil in a time period of displaying the predetermined content; and determines a correlation coefficient between the relative position sequence of the pupil and a position sequence of the target whose position changes as the feature signal. The feature signal judgment unit 222 judges whether the correlation coefficient is greater than a first predetermined threshold, and if the correlation coefficient is greater than the first predetermined threshold, identifies that the object to be detected is a living body- ¶0050).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Chen and Rahib with the teaching of Fan to effectively differentiate a normal user from a picture, a video, or a mask and so on used by an attacker, and no specific cooperation is required from the user, and security and usability of the liveness detection system are improved (Fan- ¶0044).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CLIFFORD HILAIRE whose telephone number is (571)272-8397. The examiner can normally be reached 5:30-1400.
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, SATH V PERUNGAVOOR can be reached at (571)272-7455. 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.
CLIFFORD HILAIRE
Primary Examiner
Art Unit 2488
/CLIFFORD HILAIRE/Primary Examiner, Art Unit 2488
Prosecution Insights