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 .
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.
Claim(s) 9-11, 21-23, 28-30, and 32 are rejected under 35 U.S.C. 103 as being unpatentable over Wu (US 20160055371) in view of Li (US 20180120594).
Regarding claim 9:
Wu discloses: a mobile apparatus comprising: a processor and a non-transitory computer-readable medium (FIG. 1, ¶ [0017] “An embodiment of the invention provides smart glasses including an image capturing unit, a storage unit, a display unit, and a processing unit.” A mobile apparatus includes “smart glasses”); comprising instructions that, when executed by the processor, cause the mobile apparatus to:
provide a first faceprint from a library of faceprints to a smart glasses device (¶ [0017] “…The storage unit is configured to store a database, and the database records a plurality of profile information and business card information corresponding to each of the profile information.”; ¶ [0011] “…Then, facial features of each of the recognized faces are compared with those of the profile information in the database to find the profile information matching the facial features”; in order to perform a comparison between facial features and other facial features stored in the database, the facial feature in the database must be retrieved, FIG. 2, step S206 and ¶ 0042]);
cause the smart glasses device to perform targeted facial recognition for the first faceprint (¶ [0017] “…The processing unit is coupled to the image capturing unit, the storage unit, and the display unit, and is configured to recognize at least one face appearing in the image captured by the image capturing unit, and compare the facial features of each of the recognized faces with those of the profile information in the database to find the profile information matching the facial features. In particular, if the profile information matching the facial features is found” in order to perform the comparison, facial recognition on the profile information must be performed; FIG.2, step S204 and ¶ [0041]);
obtain a second faceprint from the smart glasses device (¶ [0017] “…The processing unit is coupled to the image capturing unit, the storage unit, and the display unit, and is configured to recognize at least one face appearing in the image captured by the image capturing unit, and compare the facial features of each of the recognized faces with those of the profile information in the database to find the profile information matching the facial features. In particular, if the profile information matching the facial features is found” in order to perform the comparison, facial recognition on the profile information must be performed; FIG. 2, step S202 and ¶ [0040]);
and determine whether to add the second faceprint to the library of faceprints (¶ [0017] “…if profile information matching the facial features is not found, the processing unit recognizes the business card information of a business card appearing in the image captured by the image capturing unit, and associates the recognized business card information with the recognized face”. FIG. 2, step S212.; ¶ [0044] “…if the profile information matching the facial features is not found, the processing unit 14 further recognizes the business card appearing in the image captured by the image capturing unit 11 to obtain the business card information, and then associates the recognized business card information with the recognized face and writes the association into the database (step S212).” When the newly captured image contains a face that is not in the database, the facial image and the business card are associated with each other and stored in the database);
Wu does not specifically teach that the smart glasses device is a different device from the mobile apparatus.
However, in the same field of endeavor, Li teaches: where the smart glasses device is a different device from the mobile apparatus (¶ [0080] “…The server is in communicative connection with a mobile phone comprising a detection device 18 and a recognition device 20. The glasses in FIG. 3 is a portion other than the detection device 18 and the recognition device 20. The glasses in FIG. 3 is used for human face recognition, text recognition (translation) and image recognition (for example, the difference between an image and an image used for comparison).”; ¶ [0064] “…According to the embodiment, the detection device 18 and the recognition device 20 are external, and the main effect thereof is to be able to effectively reduce the weight of the smart glasses 10”; ¶ [0066] “The first comparison image mentioned above is stored in a retrieval database, and the retrieval database may be chosen to be provided locally or at a cloud end”).
Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Wu to incorporate the teachings of Li by including: the smart glasses device is a different device from the mobile apparatus in order to be able to effectively reduce the weight of the smart glasses as disclosed by Li.
Regarding claim 10:
Wu in view of Li discloses the limitations of claim 9 as applied above.
Wu further discloses: where the library of faceprints is associated with a user (¶ [0036], ¶ [0042] – ¶ [0043], and ¶ [0023]. Disclose that the database is pre-established by a user and stores info about “people that the user met” (contacts); therefore associated with the user).
Regarding claim 11:
Wu in view of Li discloses the limitations of claim 9 as applied above.
Li teaches: where the library of faceprints is associated with an external database stored on a storage device that is different from the mobile apparatus and the smart glasses device (¶ [0020] “a retrieval database, located locally or at a cloud end, the retrieval database storing the first comparison image for comparing with the human face image and the second comparison image for comparing with the foreign language image”; ¶ [0021] “…the retrieval database receives at least one of the following human face images as the first comparison image”; (¶ [0080] “…The server is in communicative connection with a mobile phone comprising a detection device 18 and a recognition device 20. The glasses in FIG. 3 is a portion other than the detection device 18 and the recognition device 20. The glasses in FIG. 3 is used for human face recognition, text recognition (translation) and image recognition (for example, the difference between an image and an image used for comparison).”; ¶ [0064] “…According to the embodiment, the detection device 18 and the recognition device 20 are external, and the main effect thereof is to be able to effectively reduce the weight of the smart glasses 10”; ¶ [0066] “The first comparison image mentioned above is stored in a retrieval database, and the retrieval database may be chosen to be provided locally or at a cloud end. The first comparison image in the retrieval database is from: a human face image which is fully shared, a human face image which is shared within a particular range and within an acquisition permission, a human face image which is received passively and a human face image which is actively photographed.”).
Regarding claim 21:
Wu discloses: a smart glasses device, comprising: a frame; a processor disposed about the frame; and a non-transitory computer-readable medium disposed about the frame (FIG. 1, ¶ [0017] “An embodiment of the invention provides smart glasses including an image capturing unit, a storage unit, a display unit, and a processing unit.” The smart glasses implies to have a frame); the non-transitory computer-readable medium comprising instructions that, when executed by the processor, cause the smart glasses device to:
receive a first faceprint from a library of faceprints from another device (¶ [0017] “…The storage unit is configured to store a database, and the database records a plurality of profile information and business card information corresponding to each of the profile information.”; ¶ [0011] “…Then, facial features of each of the recognized faces are compared with those of the profile information in the database to find the profile information matching the facial features”; in order to perform a comparison between facial features and other facial features stored in the database, the facial feature in the database must be retrieved, FIG. 2, step S206 and ¶ 0042]);;
perform targeted facial recognition for the first faceprint (¶ [0017] “…The processing unit is coupled to the image capturing unit, the storage unit, and the display unit, and is configured to recognize at least one face appearing in the image captured by the image capturing unit, and compare the facial features of each of the recognized faces with those of the profile information in the database to find the profile information matching the facial features. In particular, if the profile information matching the facial features is found” in order to perform the comparison, facial recognition on the profile information must be performed; FIG.2, step S204 and ¶ [0041]);
and send a second faceprint to the other device to add to the library of faceprints (¶ [0017] “…if profile information matching the facial features is not found, the processing unit recognizes the business card information of a business card appearing in the image captured by the image capturing unit, and associates the recognized business card information with the recognized face”. FIG. 2, step S212.; ¶ [0044] “…if the profile information matching the facial features is not found, the processing unit 14 further recognizes the business card appearing in the image captured by the image capturing unit 11 to obtain the business card information, and then associates the recognized business card information with the recognized face and writes the association into the database (step S212).”);
Wu does not specifically teach that the other device being different from the smart glasses device
However, in the same field of endeavor, Li teaches: the other device being different from the smart glasses device (¶ [0080] “…The server is in communicative connection with a mobile phone comprising a detection device 18 and a recognition device 20. The glasses in FIG. 3 is a portion other than the detection device 18 and the recognition device 20. The glasses in FIG. 3 is used for human face recognition, text recognition (translation) and image recognition (for example, the difference between an image and an image used for comparison).”; ¶ [0064] “…According to the embodiment, the detection device 18 and the recognition device 20 are external, and the main effect thereof is to be able to effectively reduce the weight of the smart glasses 10”; ¶ [0066] “The first comparison image mentioned above is stored in a retrieval database, and the retrieval database may be chosen to be provided locally or at a cloud end”).
Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Wu to incorporate the teachings of Li by including: the other device being different from the smart glasses device in order to be able to effectively reduce the weight of the smart glasses as disclosed by Li.
Regarding claim 22: the claims limitations are similar to those of claim 10; therefore, rejected in the same manner as applied above.
Regarding claim 23: the claims limitations are similar to those of claim 11; therefore, rejected in the same manner as applied above.
Regarding claim 28:
Wu discloses: a mobile apparatus, comprising: a housing; a processor disposed within the housing; and a non-transitory computer-readable medium disposed within the housing (FIG. 1, ¶ [0017] “An embodiment of the invention provides smart glasses including an image capturing unit, a storage unit, a display unit, and a processing unit.” The smart glasses implies to have a housing); the non-transitory computer-readable medium comprising instructions that, when executed by the processor, cause the mobile apparatus to
obtain a region-of-interest from a smart glasses device, the region-of- interest comprising facial data device (¶ [0017] “…The processing unit is coupled to the image capturing unit, the storage unit, and the display unit, and is configured to recognize at least one face appearing in the image captured by the image capturing unit, and compare the facial features of each of the recognized faces with those of the profile information in the database to find the profile information matching the facial features. In particular, if the profile information matching the facial features is found” in order to perform the comparison, facial recognition on the profile information must be performed; FIG. 2, step S202 and ¶ [0040]; step S206 and ¶ 0042].);
determine whether to add a first faceprint to a library of faceprints based on the region-of-interest (¶ [0017] “…if profile information matching the facial features is not found, the processing unit recognizes the business card information of a business card appearing in the image captured by the image capturing unit, and associates the recognized business card information with the recognized face”. FIG. 2, step S212.; ¶ [0044] “…if the profile information matching the facial features is not found, the processing unit 14 further recognizes the business card appearing in the image captured by the image capturing unit 11 to obtain the business card information, and then associates the recognized business card information with the recognized face and writes the association into the database (step S212).” When the newly captured image contains a face that is not in the database, the facial image and the business card are associated with each other and stored in the database). ;
and provide the first faceprint from the library of faceprints to the smart glasses device (¶ [0017] “…The storage unit is configured to store a database, and the database records a plurality of profile information and business card information corresponding to each of the profile information.”; ¶ [0011] “…Then, facial features of each of the recognized faces are compared with those of the profile information in the database to find the profile information matching the facial features”; in order to perform a comparison between facial features and other facial features stored in the database, the facial feature in the database must be retrieved, FIG. 2, step S206 and ¶ 0042]);
Wu does not specifically teach that the other device being different from the smart glasses device
However, in the same field of endeavor, Li teaches: the other device being different from the smart glasses device (¶ [0080] “…The server is in communicative connection with a mobile phone comprising a detection device 18 and a recognition device 20. The glasses in FIG. 3 is a portion other than the detection device 18 and the recognition device 20. The glasses in FIG. 3 is used for human face recognition, text recognition (translation) and image recognition (for example, the difference between an image and an image used for comparison).”; ¶ [0064] “…According to the embodiment, the detection device 18 and the recognition device 20 are external, and the main effect thereof is to be able to effectively reduce the weight of the smart glasses 10”; ¶ [0066] “The first comparison image mentioned above is stored in a retrieval database, and the retrieval database may be chosen to be provided locally or at a cloud end”).
Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Wu to incorporate the teachings of Li by including: the other device being different from the smart glasses device in order to be able to effectively reduce the weight of the smart glasses as disclosed by Li.
Regarding claim 29:
Wu discloses the limitations of claim 28 as applied above.
Wu further discloses: where the region-of-interest comprises extracted facial features (¶ [0041] “…the processing unit 14 recognizes the face appearing in the image via, for instance, the outline of the face, the positions and shapes of facial features, hairstyle, or skin color, and obtains the facial features of each of the faces.”).
Regarding claim 30:
Wu further discloses: where the determination is based on a quality of the second faceprint on a quality of the second faceprint (¶¶ [0013], [0019], and [0020] disclose that the enrollment decision is conditional on the quality of that face: face size within a preset range).
Regarding claim 32:
Wu discloses the limitations of claim 28 as applied above.
Wu further discloses: process the region-of-interest to obtain metadata (¶ [0044] “…the processing unit 14 further recognizes the business card appearing in the image captured by the image capturing unit 11 to obtain the business card information, and then associates the recognized business card information with the recognized face and writes the association into the database (step S212). The business card information is, for instance, the name of a person or a company, a phone, a fax, an address, a URL, a unified code, an email address, or other personal information obtained via, for instance, the optical character recognition (OCR) of an image captured by the image capturing unit 11, and the invention is not limited thereto.”);
and provide the metadata to the smart glasses device (¶ [0043] “…the processing unit 14 provides the business card information corresponding to the profile information to display on the display unit 13 to prompt the user (step S210), and the display method includes, for instance, directly displaying the image of the business card or displaying the business card information obtained from the business card, and the invention is not limited thereto. Accordingly, the user can see relevant information of people met in the display unit 13 and therefore recognize the person.”).
Claim(s) 12 and 24 are rejected under 35 U.S.C. 103 as being unpatentable over Wu (US 20160055371) in view of Li (US 20180120594) and Nelson (US 20190108492).
Regarding claim 12:
Wu in view of Li does not specifically teach: the instructions, when executed by the processor, further cause the mobile apparatus to: determine a scheduled meeting is within a threshold time period; select the first faceprint from the library of faceprints based on a scheduled meeting with a meeting attendee associated with the first faceprint, where providing the first faceprint is based on selecting the first faceprint.
However, in the same field of endeavor, Nelson teaches: determine a scheduled meeting is within a threshold time period (¶ [0347] “FIG. 17C is a block diagram that depicts example contents of meeting information 1732 in the form of a table, where each row corresponds to a particular electronic meeting. In the example depicted in FIG. 17C, meeting information 1732 includes a meeting ID, a meeting name, a meeting location, a date/time for the meeting, participants, and other information”; ¶ [0373] “IWB appliance 1710 may compare the current time to meeting date/time information for each of the electronic meetings represented in meeting information 1732 to determine whether an electronic meeting involving IWB appliance 1710 is scheduled at or near the current time. According to one embodiment, if the current time is within a specified amount of time of a scheduled time for a particular electronic meeting, then the particular electronic meeting is considered to be scheduled at or near the current time. The specified amount of time may be configurable, for example, by an administrative user of IWB appliance 1710, and may be stored as part of configuration data 1736. IWB appliance 1710 may also query a meeting or calendar system to determine whether an electronic meeting involving IWB appliance 1710 is scheduled at or near the current time. For example, IWB appliance 1710 may use an API provided by a meeting or calendar system to obtain meeting information.”)
select the first faceprint from the library of faceprints based on a scheduled meeting with a meeting attendee associated with the first faceprint; where providing the first faceprint is based on selecting the first faceprint (¶ [0347] “FIG. 17C is a block diagram that depicts example contents of meeting information 1732 in the form of a table, where each row corresponds to a particular electronic meeting. In the example depicted in FIG. 17C, meeting information 1732 includes a meeting ID, a meeting name, a meeting location, a date/time for the meeting, participants, and other information”; ¶ [0355] “…IWB appliance 1710 acquires facial images of persons, such as meeting participants without the participation and/or knowledge of the persons. Facial images may be acquired using one or more cameras integrated into IWB appliance 1710, such as cameras 1746, or external sensors, as described in more detail hereinafter. IWB appliance 1710 then attempts to associate the acquired facial images with particular persons. For example, image recognition application 1752 may compare facial images acquired by IWB appliance 1710 to known facial images from databases, records, social media, etc. This may include using meeting participant information. For example, the participants of a meeting may be determined, and then the acquired facial images may be compared to facial images of meeting participants to associate the acquired facial images with a person.”; ¶ [0375] “…a determination is made to determine whether the identified person is a scheduled participant of the electronic meeting. For example, IWB appliance 1710 may consult the participant information for the electronic meeting from meeting information 1732 to determine whether the identified person is a scheduled participant of the electronic meeting.”);
Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Wu to incorporate the teachings of Nelson in order to improve recognition accuracy by limiting targeted facial recognition to persons expected to be encountered at the scheduled meeting.
Regarding claim 24: the claims limitations are similar to those of claim 12; therefore, rejected in the same manner as applied above.
Claim(s) 13 and 27 rejected under 35 U.S.C. 103 as being unpatentable over Wu (US 20160055371) in view of Li (US 20180120594) and Purwar (US 20180352150).
Regarding claim 13:
Wu in view of Li does not specifically teach: the instructions, when executed by the processor, further cause the mobile apparatus to: determine a scheduled meeting is within a threshold time period; select the first faceprint from the library of faceprints based on a scheduled meeting with a meeting attendee associated with the first faceprint, where providing the first faceprint is based on selecting the first faceprint.
However, in the same field of endeavor, Nelson teaches: Wu further teaches determining whether to add the second faceprint to the library of faceprints based on a quality-related condition of the detected face. Specifically, Wu teaches that, when profile information matching the facial features is not found, “the size of each of the recognized faces is calculated, and whether the size of the face is within a preset range is determined,” and, if the size is within the preset range, “the recognition step of the business card information is started and the face for which the size is within the preset range is associated with the recognized business card information.” Wu further explains that, if the face size is within the preset range, the face is associated with the recognized business-card information, and if not, “the association is not established.” See Wu (¶¶ [0013], [0019], and [0020]).
Wu in view of Li does not specifically teach: where the quality is based on at least one of clarity of facial features in the second faceprint, presence of obstructions of facial features in the second faceprint, and noise in the second faceprint.
However, in the same field of endeavor, Purwar teaches determining facial-image quality based on at least clarity/blur and obstruction/occlusion (Specifically, Purwar ¶ [0003] teaches that conventional alignment approaches do not address other quality factors that affect a selfie, including “occlusion” and “blur,” and further teaches analyzing the image to determine whether a face and at least one landmark facial feature are present. Purwar ¶ [0005] further teaches that, after the selfie is analyzed and normalized, “it undergoes further analysis to determine an image quality metric selected from occlusion, blur, distance-to-camera, facial expression, illumination, and combinations of these,” and that an SQI score is generated from the analyzed quality metrics and used to determine whether the selfie will undergo further analysis. Purwar ¶ [0044] further teaches that the image quality modules analyze qualitative metrics including “occlusion” and “blur,” and that the results are used to generate a selfie quality index score reflecting image quality. Purwar ¶ [0035] – ¶ [0036] and ¶ [0046] also teaches using a threshold to determine whether further processing occurs, including prompting a user to retake the image if the SQI score or an individual metric such as blur fails a threshold. Thus, Purwar teaches the claimed quality features because blur corresponds to clarity of facial features in the second faceprint, and occlusion corresponds to the presence of obstructions of facial features in the second faceprint. The claim recites “at least one of” clarity, obstructions, and noise; therefore, Purwar’s disclosure of blur/clarity and occlusion/obstruction is sufficient).
Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Wu in view of Li, and further in view of Purwar, by including: determining whether to add the second faceprint to the library of faceprints based on a quality of the second faceprint, where the quality is based on at least one of clarity of facial features in the second faceprint and presence of obstructions of facial features in the second faceprint, in order to prevent low-quality or obstructed faceprints from being added to the faceprint library and to improve the accuracy and reliability of subsequent facial recognition.
Regarding claim 27: the claims limitations are similar to and/or border than claim 13; therefore, rejected in the same manner as applied above.
Claim(s) 14 and 31 are rejected under 35 U.S.C. 103 as being unpatentable over Wu (US 20160055371) in view of Kim (US 20220385617).
Regarding claim 14:
Wu does not specifically teach: where the determination is based on a salient event that is representative of a larger interaction.
However, in the same field of endeavor, Kim teaches: where the determination is based on a salient event that is representative of a larger interaction (¶ [0063] “…Face recognized Sensor data from camera If a face recognized as belong Output of facial to a database of faces recognition algorithm associated with the HMD user is in a defined region for longer than a threshold time, an In Conversation event is triggered.”; ¶ [0046] – ¶ [0066]: discuss other factor modules (location/movement, interaction logs, etc.) and combining them to detect whether a user is in a real-world conversation. Kim uses these conversation events as salient events to control another system behavior such as notification management).
Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Wu to incorporate the teachings of Kim by including: where the determination is based on a salient event that is representative of a larger interaction in order to provide effective, context-aware notification management at AR devices.
Regarding claim 31: the claims limitations are similar to those of claim 14; therefore, rejected in the same manner as applied above.
Claim(s) 25 is rejected under 35 U.S.C. 103 as being unpatentable over Wu (US 20160055371) in view of Lee (US 20190213773).
Regarding claim 25:
Wu further teaches: further cause the smart glasses device to: identify a face in an image (¶ [0017] “…smart glasses including an image capturing unit, a storage unit, a display unit, and a processing unit. In particular, the image capturing unit is configured to capture an image located in the field of view of the smart glasses…recognize at least one face appearing in the image captured by the image capturing unit”).
Wu does not specifically teach: and crop a region-of-interest including facial data from the image.
However, in the same field of endeavor, Lee teaches: and crop a region-of-interest including facial data from the image (¶ [0118] “…FIG. 10A depicts a full size high resolution image captured by the sensor 103, while FIG. 10B depicts a region of interest (ROI) (e.g., the person's face) that is cropped by the image processing module 106 to update the texture of the remote model—which is only a small portion of the overall image.”; ¶ [0052] “…Exemplary computing devices include, but are not limited to, a laptop computer, a desktop computer, a tablet computer, a smart phone, an internet of things (IoT) device, augmented reality (AR)/virtual reality (VR) devices (e.g., glasses, headset apparatuses, and so forth), or the like”)
Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Wu to incorporate the teachings of Lee by including: and crop a region-of-interest including facial data from the image in order reduce computational and bandwidth requirements when processing/transmitting the face images.
Claim(s) 26 is rejected under 35 U.S.C. 103 as being unpatentable over Wu (US 20160055371) in view of Lee (US 20190213773) and Petrou (US 20140172881).
Regarding claim 26:
Wu further teaches: further cause the smart glasses device to: identify a face in an image (¶ [0017] “…smart glasses including an image capturing unit, a storage unit, a display unit, and a processing unit. In particular, the image capturing unit is configured to capture an image located in the field of view of the smart glasses…recognize at least one face appearing in the image captured by the image capturing unit”).
Wu does not specifically teach: identify a face in a plurality of images; select a first image from the plurality of images; and crop a region-of-interest including facial data from the first image.
However, in the same field of endeavor, Petrou teaches: identify a face in a plurality of images (¶ [0042] “The visual query is an image… or a frame or a sequence of multiple frames of a video (206)”; ¶ [0043] “…A visual query can include an image of a person's face, whether taken by a camera embedded in the client system or a document scanned by or otherwise received by the client system.”; ¶ [0160] “…the visual query contains a plurality of faces, such as a picture of two or more friends, or a group photo of several people. In some cases where the visual query comprises a plurality of facial images… prior to identifying potential image matches, the system receives a selection of the respective facial image from the requester. For example, in some embodiments the system identifies each potential face and requests confirmation regarding which face(s) in the query the requester wishes to have identified.”));
select a first image from the plurality of images ¶ [0160] “…the visual query contains a plurality of faces, such as a picture of two or more friends, or a group photo of several people. In some cases where the visual query comprises a plurality of facial images… prior to identifying potential image matches, the system receives a selection of the respective facial image from the requester. For example, in some embodiments the system identifies each potential face and requests confirmation regarding which face(s) in the query the requester wishes to have identified.”):
Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Wu to incorporate the teachings of Petrou by including: a face in a plurality of images in order provide a variety of search results related to an identified person in the facial image query.
Wu in view of Petrou does not specifically teach and crop a region-of-interest including facial data from the first image.
However, in the same field of endeavor, Lee teaches: and crop a region-of-interest including facial data from the first image (¶ [0118] “…FIG. 10A depicts a full size high resolution image captured by the sensor 103, while FIG. 10B depicts a region of interest (ROI) (e.g., the person's face) that is cropped by the image processing module 106 to update the texture of the remote model—which is only a small portion of the overall image.”; ¶ [0052] “…Exemplary computing devices include, but are not limited to, a laptop computer, a desktop computer, a tablet computer, a smart phone, an internet of things (IoT) device, augmented reality (AR)/virtual reality (VR) devices (e.g., glasses, headset apparatuses, and so forth), or the like”)
Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Wu and Petrou to incorporate the teachings of Lee by including: and crop a region-of-interest including facial data from the image in order reduce computational and bandwidth requirements when processing/transmitting the face images.
Claim(s) 33-34 are rejected under 35 U.S.C. 103 as being unpatentable over Wu (US 20160055371) in view of Kaehler (US 20170351909).
Regarding claim 33:
Wu further discloses: , further cause the mobile apparatus to identify a matching faceprint based on the region-of-interest (¶ [0017] “…The storage unit is configured to store a database, and the database records a plurality of profile information and business card information corresponding to each of the profile information. The processing unit is coupled to the image capturing unit, the storage unit, and the display unit, and is configured to recognize at least one face appearing in the image captured by the image capturing unit, and compare the facial features of each of the recognized faces with those of the profile information in the database to find the profile information matching the facial features.”; ¶ [0042] “…In particular, the database stored in the storage unit 12 records information related to people that the user met in the past and for whom face recognition and business card recognition are completed, wherein the information includes features such as the outline of the face, positions and shapes of facial features, hairstyle, and skin color.”)
Wu does not specifically teach: further comprising a neural network trained to perform facial recognition from the library of faceprints, where the instructions, when executed by the processor.
However, in the same field of endeavor, Kaehler teaches: further comprising a neural network trained to perform facial recognition from the library of faceprints (¶ [0080] “The object recognitions may be performed using a variety of computer vision techniques… facial recognition (e.g., from a person in the environment or an image on a document),… One or more computer vision algorithms may be used to perform these tasks. Non-limiting examples of computer vision algorithms include:… various machine learning algorithms (such as e.g., support vector machine, k-nearest neighbors algorithm, Naive Bayes, neural network (including convolutional or deep neural networks), or other supervised/unsupervised models, etc.), and so forth”; ¶ [0106] “Feature vectors of the two faces within the image 1200a may be used to compare similarities and dissimilarities between the two faces. For example, the ARD can calculate the distance (such as a Euclidean distance) between the two feature vectors in a corresponding feature vector space. When the distance exceeds a threshold, the ARD may determine the two faces are sufficiently dissimilar. On the other hand, when the distance is below the threshold, the ARD may determine the two faces are similar.”; ¶ [0111] “…The ARD can further look up the identified features in a database to determine whether there are one or more persons matching the identified features.”))
Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the claimed invention to have modified Wu to incorporate the teachings of Kaehler by including: a neural network trained to perform facial recognition from the library of faceprints in order improve performance and reduce power consumption compared to conventional facial recognition techniques.
Regarding claim 34:
Wu further discloses: where the metadata comprises corresponding contact information associated with the matching faceprint (¶ [0043] “If the profile information matching the facial features is found, the processing unit 14 provides the business card information corresponding to the profile information to display on the display unit 13 to prompt the user (step S210), and the display method includes, for instance, directly displaying the image of the business card or displaying the business card information obtained from the business card, and the invention is not limited thereto. Accordingly, the user can see relevant information of people met in the display unit 13 and therefore recognize the person.”).
Response to Arguments
Applicant’s arguments with respect to claim(s) 9, 21, and 28 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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.
/WASSIM MAHROUKA/Primary Examiner, Art Unit 2665
Prosecution Insights