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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in parent Application No. 10-2024-0067677, filed on May 24, 2024, with Korean Patent Office.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12/06/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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.
Claims 1 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (CN 110969049 A) referred to as Chen hereinafter and further in view of Kim et al. (Incremental Face Recognition using Rehearsal and Recall Processes) referred to as Kim hereinafter.
Regarding claim 1, Chen teaches An apparatus for counting people based on face detection, comprising: one or more processors; (“The invention claims a method for people flow statistics, number counting method, device and electronic device, wherein, the people flow statistics method comprises monitoring image obtaining preset place; extracting the face image from the monitoring image” Chen, abstract)
and memory for storing at least one program executed by the one or more processors, (“a memory and a processor, the memory and the processor are in communication connection, the memory is stored with computer instructions, the processor executes the computer instructions to execute the first aspect or any embodiment of the first aspect the people flow statistics method” Chen, p. 4, para. 7)
wherein the at least one program detects a face of a person in a video input through a camera, (“the entrance of many places normally equipped with a monitoring camera, gradually realized based on the people flow statistics of the video.” Chen, p. 2, para. 1)
retrieves the detected face to check whether the detected face is a face registered in any one of short-term memory and long-term memory, counts the person of the detected face when the detected face is not retrieved from the short-term memory or the longer-term memory, registers the face of the counted person in the short-term memory, (“S242, counting the number of people flow by, calculating a preset location. in the electronic device counting the human face image number of the flow is the preset place, people flow therefore, using the number counting, it is possible to obtain the predetermined position.” Chen, p. 7, para. 12) and (“the electronic device may set history face image library, for storing in the preset time of the preset place appearing face image. after the electronic device extracting the face image from the monitoring image, firstly judging whether the human face image belongs to history face image library, if does not appear in a preset time period, then the face image stored in the historical face image library.” Chen, p. 7, para. 15)
and deletes a face previously registered in the long-term memory in a First-In-First-Out (FIFO) manner when a number of faces registered in the long-term memory exceeds a predefined number. (“S23, removing the human face image in the preset time period repeatedly appears. electronic device after extracting the face image, firstly determining whether the face image appeared repeatedly in a preset time period, if the repeated appears, then deleting the extracted face image, not involved in counting the people flow, if the face image and does not appear in a preset time period, then the statistics extracted face pattern involved in a flow of people.” Chen, p. 6, last para. p. 7, para. 1)
However, Chen does not teach transfers the face registered in the short-term memory to the long-term memory to be registered therein when the face registered in the short-term memory remains for a preset time or longer,
Kim teaches transfers the face registered in the short-term memory to the long-term memory to be registered therein when the face registered in the short-term memory remains for a preset time or longer, (“STM adapts faster to new incoming data and transfers the information to LTM for longer retention through rehearsal; whereas LTM provides the reconstructed data to STM through recall for accurate learning.” Kim, p. 2753, II. The Proposed Model), (“We compared the classification accuracy of STM with and without recall data in addition to the resized data. Five sampled images among the 13 images are used for training and the remaining eight faces are used for testing. The capacity of STM is limited by three. So three of five training images are used for initial batch modeling and the remaining two images are used for incremental learning.” Kim, p. 2755, III. Experimental Results) and fig. 2.
Chen and Kim are combinable because they are from the same field of endeavor, image processing in face detection.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Chen in light of Kim’s transferring the face registered in the short-term memory to the long-term memory. One would have been motivated to do so because it improves recognition performance by solving the insufficient data problem during incremental learning. (Kim, p. 2756, III. Experimental Results)
Regarding claim 10, refer to the explanation of claim 1.
Claim(s) 2, 3, 11, and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Chen and Kim as mentioned above and further in view of Kim Young et al. (KR 20230114650 A) referred to as Kim Young hereinafter.
Regarding claim 2, the combination of Chen and Kim does not teach when the detected face is not retrieved from the short-term memory or the long-term memory, the at least one program checks whether the face detected in a currently input video frame is identical to a face detected in a previously input video frame and counts the person of the face when the two faces are identical to each other.
Kim Young teaches when the detected face is not retrieved from the short-term memory or the long-term memory, the at least one program checks whether the face detected in a currently input video frame is identical to a face detected in a previously input video frame and counts the person of the face when the two faces are identical to each other. (“The image recognition unit 140 recognizes a face when a person detected from the image approaches within a certain distance (S320). The image recognizing unit 140 detects a face region from the image, analyzes the face region, extracts features, and compares the image data and feature data of a previously registered person to determine whether a matching registrant exists (S330).” Kim Young, p. 10, para. 5) and (“the control unit 110 generates and outputs a warning about unauthorized access when the number of people entering and recognizing is different from that of the person in charge (S450), and sends a notification about unauthorized access to a previously registered person in charge (S460). In addition, the control unit 110 transmits a control command to the security system 200 for unauthorized access, restricts access, and sets security personnel to mobilize from adjacent facilities.” Kim Young, p. 11, para. para. 5)
Chen, Kim, and Kim Young are combinable because they are from the same field of endeavor, image processing in face detection.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Chen and Kim in light of Kim Young’s not retrieving the detected face from the memory. One would have been motivated to do so because it can increase accuracy of a security system.
Regarding claim 3, Chen teaches when a number of video frames of the face detected as the identical face in the input video is equal to or greater than a preset number, the at least one program counts the person of the detected face. (“the people counting method provided by the embodiment of the invention, through the inlet and the outlet for population statistics, performing deduplication processing to the human face image of inlet and outlet, namely removing the human face image in the preset time period repeatedly appears, so as to avoid the repeated collection of human face image in the preset place Lingering, or staying for a long time caused by increasing the accuracy of the people counting.” Chen, p. 8, para. 13)
Regarding claim 11, refer to the explanation of claim 2.
Regarding claim 12, refer to the explanation of claim 3.
Claim(s) 4, 5, 13, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Chen and Kim as mentioned above and further in view of Lee (KR 20050111519).
Regarding claim 4, the combination of Chen and Kim does not teach when the detected face is retrieved from the short-term memory, the at least one program records a matching rate for an ID of the registered face based on a number of times the registered face identical to the detected face is retrieved from the short-term memory.
Lee teaches when the detected face is retrieved from the short-term memory, the at least one program records a matching rate for an ID of the registered face based on a number of times the registered face identical to the detected face is retrieved from the short-term memory. (“Here, the reason why the memory 14 is embedded in the wireless camera door lock 10 to store a certain amount of image is stored in the wireless computer door lock 10. If the personal computer 32 does not operate or the wireless router 20 does not operate, the image is displayed. Since it cannot be confirmed, the present invention uses the memory 14 to store the minimum image information necessary for face verification, so that it can be used for identification later.” Lee, p. 3, para. 1) and (“Since the specified password is not inputted by someone illegally attempting to open the door, if another password is input two or more times in succession, it is regarded as a certain illegal intrusion and stores and transmits the image taken by the camera 13.” Lee, p. 2, para. 17)
Chen, Kim, and Lee are combinable because they are from the same field of endeavor, image processing in face detection.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Chen and Kim in light of Lee’s matching for an ID of the registered face. One would have been motivated to do so because it can confirm the real time of the intrusion.
Regarding claim 5, Chen does not teach wherein the at least one program transfers the face registered in the short-term memory to the long-term memory when the matching rate is equal to or less than a preset value.
Kim teaches wherein the at least one program transfers the face registered in the short-term memory to the long-term memory when the matching rate is equal to or less than a preset value. (“STM adapts faster to new incoming data and transfers the information to LTM for longer retention through rehearsal; whereas LTM provides the reconstructed data to STM through recall for accurate learning.” Kim, p. 2753, II. The Proposed Model) and fig. 2
Chen and Kim are combinable because they are from the same field of endeavor, image processing in face detection.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Chen in light of Kim’s transferring the face registered in the short-term memory to the long-term memory. One would have been motivated to do so because it improves recognition performance by solving the insufficient data problem during incremental learning. (Kim, p. 2756, III. Experimental Results)
Regarding claim 13, refer to the explanation of claim 4.
Regarding claim 14, refer to the explanation of claim 5.
Claim(s) 6, 7, 15, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Chen and Kim as mentioned above and further in view of Dreszer (US 6442661 B1).
Regarding claim 6, the combination of Chen and Kim does not teach wherein the at least one program manages the number of faces registered in the long-term memory based on a predefined length of a First-In-First-Out (FIFO) queue.
Dreszer teaches wherein the at least one program manages the number of faces registered in the long-term memory based on a predefined length of a First-In-First-Out (FIFO) queue. (“Referring to FIG. 3A, in one version, to effectively eliminate fragmentation of the memory 26, at file server startup/initialization the memory manager 30 segregates memory block allocations that are to remain allocated for long periods of time, long term (LT) memory blocks, to a first region LT memory 36 of the memory 26 from the heap 34 (preferably the low address end of the memory 26). Further, the memory manager 30 segregates memory block allocations that are to remain allocated for short periods of time, short term/transient (ST) memory blocks, to a second region ST memory 38 of the memory 26 from the heap 34 (preferably the high address end of the memory 26). Referring to FIG. 3B, the memory manager 30 then creates and maintains size queues 40 (SQ) including plurality of memory segments 42 of varying predetermined sizes, or separate memory pools, in a third region of the memory from the heap 34, to satisfy smaller short term efficient memory block allocation requests (e.g., requiring few/brief allocation steps).” Dreszer, col. 3, lines 61-67, col. 4, lines 1-12) and (“Referring to FIG. 3D, further, the memory manager 30 increases the number of segments 42 in the size queues 40 when depleted by borrowing one or more file system cache buffers 46 to create additional data segments 42, included in SQ growth 50, for one or more size queues 40.” Dreszer, col. 5, lines 42-46)
Chen, Kim, and Dreszer are combinable because they are from the same field of endeavor, allocation of memory blocks.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Chen and Kim in light of Dreszer’s managing the number of registered data. One would have been motivated to do so because it reduces memory fragmentation, increases available memory for the file server file system I/O buffers while optimizing the amount of memory available for other uses. (Dreszer, col. 1, lines 49-52)
Regarding claim 7, Dreszer teaches when the number of registered in the long-term memory exceeds the predefined length of the queue, the at least one program deletes the registered faces in an order in which the faces are registered. (“Thereafter, upon receiving memory allocation requests (step 196) the memory manager 30 treats requests for long term memory and short term memory allocations alike (step 198), wherein the memory manager 30 determines if a requested memory block size is larger than that available in the segments 42 of the size queues 40 (step 200); if not, allocation requests less than or equal to the largest segment 42 of the size queues 40 (e.g., 1024 bytes) are satisfied from the size queues 40 (step 204). Otherwise, the memory manager 30 then determines if there is sufficient memory in the ST memory 38 of the heap 34 to satisfy the memory allocation request (step 202), and if so, a requested memory block larger than the largest segment 42 of size queues 40 is satisfied from the ST memory 38 (step 206).” Dreszer, col. 11, lines 45-58)
Chen, Kim, and Dreszer are combinable because they are from the same field of endeavor, allocation of memory blocks.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Chen and Kim in light of Dreszer’s deleting previous data. One would have been motivated to do so because it reduces memory fragmentation, increases available memory for the file server file system I/O buffers while optimizing the amount of memory available for other uses. (Dreszer, col. 1, lines 49-52)
Regarding claim 15, refer to the explanation of claim 6.
Regarding claim 16, refer to the explanation of claim 7.
Allowable Subject Matter
Claims 8, 9, 17, and 18 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Regarding claims 8 and 17, the combination of the closest prior arts does not teach “wherein the long-term memory includes a first part in which faces transferred from the short-term memory are stored based on the length of the queue and a second part in which faces of preregistered residents are stored.”
Claims 9 and 18 is objected to as allowable by virtue of their dependency upon claim 8 and 17.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PARDIS SOHRABY whose telephone number is (571)270-0809. The examiner can normally be reached Monday - Friday 9 am till 6pm.
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, Jennifer Mehmood can be reached at (571) 272-2976. 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.
/PARDIS SOHRABY/ Examiner, Art Unit 2664
/JENNIFER MEHMOOD/ Supervisory Patent Examiner, Art Unit 2664
Prosecution Insights