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 .
Information Disclosure Statement
2. The information disclosure statement (IDS) submitted on 2/6/24 the information disclosure statement was considered by initialing the PTO Form 1449.
Drawings
The Examiner has approved drawings filed on 2/6/24.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-14 , are rejected under pre-AIA 35 U.S.C. 102(a)(1) as being anticipated by Lim Boyeong et al., (KR 2022004384 A).
As to claim 1, Lim disclose a facial recognition ( using edge device recognizing face image wearing masked) method based on masking (see abstract) comprising:
performing detection and normalization of a face area including five landmarks ( see para 50, full face image extraction unit can extract full image using coordinates of full-face area) see para 52, 89 determine landmark coordinates of eye, nose etc.) in an input image ( see para 61, normalization unit ( 510) , para 62 normalization entire facial input images, extraction unit 232 normalizing based on first and second feature maps are generated see para 69) ;
separating a face portion other than a portion covered by an obstacle in the detected face area ( see para 5, see fig 1 mask wearing system, see para 221, see fig 2, mask detection model, fig 8 mask area coordinates and partial face area coordinates, see para 88, 103);
generating a mask corresponding to the separated face portion when there is a portion covered by an obstacle in the separated face portion ( fig 7, mask detection model using (CNN) see par 105 ( feature are generating based on full face image 230, partial feature model 240 and mask detecting model (225), see para 127) to create an optimal face recognition model);
applying the mask to an image in a face image registration ( see para 121, 122) database ( see para 203 and extracting a feature of a masking region ( see para 128, ( see para 134, the second learning image may include a face image wearing a mask) see para 135 (see 173 to determine the presence or absence of a mask area and the location of the mask area) ; and
determining whether it is an identical ( see para 199, 205, person based on an extracted feature value ( see para 203, comparison mask image user etc., see para 200, 202 and 221, also note, authentication decision unit extracts a first user having the greatest partial similarity, extracts at least two second users in descending order of the overall similarity, and if there is an identical person to the first user among the at least two second users and the partial similarity of the first user is greater than or equal to a first threshold value, the mask wearing face recognition edge device is characterized in that it authenticates the mask wearing
target user as a legitimate user ).
As to claim 2, Lim discloses the facial recognition method of claim 1, wherein generating the mask corresponding to the separated face portion comprises: determining that there is a covered portion when the face landmark points are not present in the separated face portion or when a size ( see para 88 size, see para 177) of a detected face element is smaller ( see para 101, 185) than a preset size ( see para 135 ) .
As to claim 3, Lim discloses the facial recognition method of claim 2, wherein the face landmark points include center positions of both eyes ( see para 48) , a center position of nose ( see para 89 ) , and both corner positions of mouth ( see para 93), mask-wearing facial recognition system, characterized in that in the first paragraph, the first dimension is 256 dimensions and the second dimension is 512 dimensions see para 100 ), also see A mask-wearing face recognition system, characterized comprises a mask detection model that detects the presence or absence of a mask area and the location of the mask area from the input image, see para 173).
As to claim 4, Lim discloses the facial recognition method of claim 1, wherein determining whether it is an identical person based on the extracted feature value comprises: determining whether it is an identical person by using the feature value of the masking region and a feature value of an original registered image (see para 210, The array file update unit (1370) receives a new array file composed of multiple arrays including feature vectors extracted from the optimal reference image at each predetermined update cycle from the face recognition server (110) and changes the existing array file into the new array file ) .
As to claim 5, Lim discloses the facial recognition method of claim 4, wherein determining whether it is an identical person based on the extracted feature value comprises: calculating a weighted ( see para 71, see 185 weights are used with feature vector) sum of the feature value of the masking region and the feature value of the original registered image ( see para 96, fig 1, 218) based on a proportion ( see para 109) of the portion covered by the obstacle in a whole face ( see para 134, 135) .
As to claim 6, Lim discloses the facial recognition method of claim 1, wherein the face image registration database ( see para 212) stores a face image and a feature value corresponding to the face image (see para 21, 22, 24).
As to claim 7, Lim discloses the facial recognition method of claim 1, further comprising: determining whether it is an identical person by comparing a feature value ( see para 22, 24) extracted from an image in the face image ( see para 205) registration database with a feature value extracted from the input image when there is no portion covered by an obstacle ( see para 221) in the separated face portion ( see para 199, 205), note authentication decision unit extracts a first user having the greatest partial similarity, extracts at least two second users in descending order of the overall similarity, and if there is an identical person to the first user among the at least two second users and the partial similarity of the first user is greater than or equal to a first threshold value, the mask-wearing face recognition edge device is characterized in that it authenticates the mask-wearing target user as a legitimate user (see para 203, comparison mask image user etc., see para 200, 202 and 221).
Regarding claim 8, it is interpreted and thus rejected for the same reasons as applied above in the rejection of claim 1. However, Lim further discloses memory ( see para 167, 211) configured to store at least program ( see para 215 ) ; and a processor configured to execute the program ( see para 223, program is stored on it , so inherent the reference has a processor where programs are stored ) .
Regarding claim 9, it is interpreted and thus rejected for the same reasons as applied above in the rejection of claim 2.
Regarding claim 10, it is interpreted and thus rejected for the same reasons as applied above in the rejection of claim 3.
Regarding claim 11, it is interpreted and thus rejected for the same reasons as applied above in the rejection of claim 4.
Regarding claim 12, it is interpreted and thus rejected for the same reasons as applied above in the rejection of claim 5.
Regarding claim 13, it is interpreted and thus rejected for the same reasons as applied above in the rejection of claim 6.
Regarding claim 14, it is interpreted and thus rejected for the same reasons as applied above in the rejection of claim 7.
Other prior art cited
The prior art made of record and not relied upon is considered pertinent toapplicant's disclosure. US. Patent Number: 10,984,225 , 12,026,921, US PGPUB NO. 20230135400 A1, 20150165365, 20190332851, 20220044009, 20220180101, 20220100989, 20220300591, 20220327861.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHEELA C CHAWAN whose telephone number is (571)272-7446. The examiner can normally be reached M- F 8 am -5.00 pm Flex.
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, Park Chan can be reached at 571-272-7409. 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.
/SHEELA C CHAWAN/ Primary Examiner, Art Unit 2669