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 .
Status of the Claims
Claims 1-20 are currently pending.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-6, 12-17 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Miwa (US 20180239953 A1) in view of Rao et al. (US 20200057885 A1).
Concerning claim 1, Miwa teaches a method for person detection by a computer device, comprising:
retrieving, from a database of suspicious persons, a profile of a person detected in at least one image, wherein the profile lists crime incidents associated with the person (¶0064: DB 160; fig. 6: S22);
determining, using the profile, a scale of crimes committed by the person based on an average amount of monetary loss per criminal incident (¶0180: determining actual harm (e.g., economic loss)), wherein the certain type is one of theft at a particular store (¶0017: The basis of the invention is preventing shoplifting of habitual shoplifters by monitoring videos of cameras configured to surveil predetermined monitoring areas in a store; ¶0111: a history of shoplifting in a store of a company in question) or theft of a particular product type;
determining a rank of the person in the database of suspicious persons based on a frequency and the scale of crimes committed by the person compared to other suspicious persons (¶0180: prioritizing execution of the security system for a habitual shoplifter (i.e., a person who has a history of shoplifting in a store of a company in question (¶0111)) and applying a lower level of monitoring to a person classified as a suspicious behavior target (i.e., someone that is not a habitual shoplifter but repeatedly passes through each sales floor on each floor in the store or repeatedly looks at the monitor camera and is considered to bring less actual harm (economic loss))); and
transmitting, to a second computer device, the retrieved profile and a notification that indicates that the person is detected when the rank exceeds a threshold rank (¶0131; ¶0180: transmission of information of the habitual shoplifter and a notification is facilitated when the habitual shoplifter is in the environment, however, notification to headquarters/head office is not performed, and a waiting time for the answer-back signal is set to be longer for the person classified as a suspicious behavior target). Not explicitly taught is determining, using the profile, a scale of crimes committed by the person based on an amount of time between incidents of a certain type.
However, in analogous art, Rao et al. (hereinafter Rao) teaches determining, using the profile, a scale of crimes committed by the person based on an amount of time between incidents of a certain type (¶¶0119-0128: Prediction of loss prevention events based on machine learning models using features including time interval between two detections and graph of face recognized at various cameras (entrance, aisle, POS, exit) with weights as the time intervals). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Miwa in the manner taught by Rao to apply machine learning to collected theft information in an effort to prevent theft.
Concerning claim 2, Miwa further teaches the method of claim 1, wherein the at least one image is a video frame in a plurality of video frames captured by a camera in an environment (¶0040: cameras 11).
Concerning claim 3, Miwa further teaches the method of claim 1, wherein retrieving the profile of the person comprises:
identifying attributes of the person in the at least one image (fig. 6: S21-S23; ¶¶0122-0124);
comparing the attributes with attribute entries in the database of suspicious persons, wherein the database of suspicious persons includes attributes of a plurality of persons associated with an alert in an environment (fig. 6: S23-S24; ¶¶0124-0125); and
retrieving the profile in response to determining a match between the attributes of the person and an entry in the database corresponding to a suspicious person (fig. 6: S25-S27; ¶¶0126-0128).
Concerning claim 4, Miwa further teaches the method of claim 3, wherein the attributes include representations of one or more of: a facial image (¶0123: facial image), an attire, a gender, an approximate age, a gait, a dwell time, and movements uncommon with an activity performed in the environment.
Concerning claim 5, Miwa further teaches the method of claim 4, wherein the environment is a store and the activity is shopping (¶0010).
Concerning claim 6, Miwa teaches the method of claim 2, further comprising: transmitting a command to the camera to zoom and track the person in the environment (¶0076 & ¶0079).
Claim 12 is the corresponding system to the method of claim 1 and is rejected under the same rationale. Miwa further teaches a computing device comprising a memory and a processor to implement all functionality of the invention (fig. 1: image processing unit 170 & storage unit 130, ¶¶0192-0194).
Claim 13 is the corresponding system to the method of claim 2 and is rejected under the same rationale.
Claim 14 is the corresponding system to the method of claim 3 and is rejected under the same rationale.
Claim 15 is the corresponding system to the method of claim 4 and is rejected under the same rationale.
Claim 16 is the corresponding system to the method of claim 5 and is rejected under the same rationale.
Claim 17 is the corresponding system to the method of claim 6 and is rejected under the same rationale.
Claim 20 is the corresponding non-transitory compute readable medium to the method of claim 1 and is rejected under the same rationale. Miwa further teaches an embodiment of the invention realized by program on a storage medium to operate a computer (¶¶0192-0194).
Claims 7-9, 11 and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Miwa (US 20180239953 A1) in view of Rao et al. (US 20200057885 A1) and Rozner et al. (US 20210390287 A1).
Concerning claim 7, Miwa in view of Rao teaches the method of claim 3. Not explicitly taught is the method, wherein the at least one image is received at a second time, further comprising adding the entry in the database of suspicious persons by: detecting an alarm indicative of a crime in the environment at a first time prior to the second time, wherein the alarm is the alert; retrieving a set of video frames of the environment for a time period comprising the first time; identifying the person in the set of video frames; identifying a set of attributes of the person; and adding the set of attributes to the entry.
However, in analogous art, Rozner et al. (hereinafter Rozner) teaches a method, wherein the at least one image is received at a second time (¶¶0024-0027: receiving the video frames after a security event has been generated), further comprising adding the entry in the database of suspicious persons by: detecting an alarm indicative of a crime in the environment at a first time prior to the second time (¶0024), wherein the alarm is the alert (¶0024); retrieving a set of video frames of the environment for a time period comprising the first time (¶0025); identifying the person in the set of video frames (¶¶0026-0027); identifying a set of attributes of the person (¶¶0026-0027); and adding the set of attributes to the entry (¶0026: updating the database/watchlist if new information has been gathered).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Miwa and Rao in the manner taught by Rozner because it would allow the system to update the database when new suspicious persons have been detected.
Concerning claim 8, Rozner further teaches consolidating entries in the database of suspicious persons by:
searching for at least one other entry in the database of suspicious persons that includes attributes that match at least a threshold number of attributes in the set of attributes of the suspicious person (¶0027: searching for a confirmed POI facial feature, if there is no match comparing the unique facial feature set for the individual with one or more potential POI facial feature sets and check whether a POI threshold has been met in order to classify the unique facial feature set of the individual as a confirmed POI); and
combining the at least one other entry with the entry of the person in response to finding the at least one other entry (¶0027: If there is a match, then the comparator may determine whether a POI threshold has been met in order to classify the unique facial feature set of the individual as a confirmed POI and store the unique facial feature set of the individual as one of the confirmed POI facial feature sets).
Concerning claim 9, Rao further teaches wherein the alarm is for a theft committed by the person triggered by a tag that includes detail information about an item that is stolen, the detail information including at least one of an identifier of the item, a price of the item, or manufacturing information (¶0053, ¶0066).
Concerning claim 11, Miwa in view of Rao teaches the method of claim 3. Not explicitly taught is the method, wherein comparing the attributes with attribute entries in a database of suspicious persons comprises executing a machine learning algorithm configured to match an input attribute of any person to a known suspicious person.
However, in analogous art, Rozner teaches a method, wherein comparing the attributes with attribute entries in a database of suspicious persons comprises executing a machine learning algorithm configured to match an input attribute vector of any person to a known suspicious person (¶0016; ¶0035). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Miwa and Rao in the manner taught by Rozner because using a machine learning algorithm an extract faces from video frames and decide whether to store their features in a database without any human in the loop (Rozner, ¶0016).
Claim 18 is the corresponding system to the method of claim 7 and is rejected under the same rationale.
Claim 19 is the corresponding system to the method of claim 8 and is rejected under the same rationale.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Miwa (US 20180239953 A1) in view of Rao et al. (US 20200057885 A1) and Swift et al. (US 20040245330 A1).
Concerning claim 10, Miwa in view of Rao teaches the method of claim 1. Miwa further teaches sending a notification to a second computer device comprising information that may aid the store or security personnel in tracking the confirmed POI and/or in identifying previous types of stolen goods (¶0131; ¶0180). Not explicitly taught is the method, further comprising: determining a likelihood metric of the suspicious person committing a crime in the environment based on the profile of the suspicious person, wherein the profile of the suspicious person indicates types of items stolen by the suspicious person, prices of the items stolen by the suspicious person, an amount of times a crime is committed by the suspicious person compared to an amount of times the suspicious person is detected in any environment; and including the likelihood metric in the notification transmitted to the second computer device.
However, in analogous art, Swift et al. (hereinafter Swift) teaches a suspicious person database, further comprising:
determining a likelihood metric of the suspicious person committing a crime in the environment based on the profile of the suspicious person, wherein the profile of the suspicious person indicates types of items stolen by the suspicious person, prices of the items stolen by the suspicious person, an amount of times a crime is committed by the suspicious person compared to an amount of times the suspicious person is detected in any environment (fig. 2B: customer record 200; ¶0073 – Table comprising Reason Code Descriptions and SPD Points; ¶0032; ¶¶0034-0035); and
including a the likelihood metric into a customer record (fig. 2B: SPD Score).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the teachings of Miwa and Swift in the manner taught by Swift to determine a likelihood metric of the suspicious person committing a crime in the environment based on the profile of the suspicious person and include the customer record into the Miwa notification to the second computer device in order to determine if tracked individuals will repeat suspicious behavior and/or activities (Swift, ¶0034).
Response to Arguments
Applicant’s arguments, see page 7 of the remarks, filed 01/30/2026, with respect to double patenting rejection have been fully considered and are persuasive. With the approval of the terminal disclaimer, filed 01/30/2026, the rejection is withdrawn.
Applicant’s arguments, see section I on pages 7-8 of the remarks filed 01/30/2026, with respect to the rejection of claims 1, 12 and 20 under 35 U.S.C. §103 have been fully considered, but they are not persuasive.
Applicant alleges
“Whether taken alone or in combination, Miwa, Rao, Rozner, and Swift fail to show or render obvious "determining, using the profile, a scale of crimes committed by the person based on an amount of time between incidents of a certain type, wherein the certain type is one of theft at a particular store or theft of a particular product type," as recited in independent claims 1, 12, and 20.
The Office Action submits that Miwa does not teach the subject matter at issue and relies on Rao. See Office Action, pg. 6. Applicant respectfully traverses.
Rao's teachings regarding a "time interval between two detections" are used as a feature for predicting loss-prevention events based on detections across cameras, rather than determining a scale of crimes committed based on time between crime incidents of a certain type (e.g., theft at a particular store or theft of a particular product type), as described by claims 1, 10, and 12. See Rao, paras. 119-123. Applicant's independent claims are directed to using the profile's crime- incident history and, specifically, the time spacing between incidents of a particular incident type to derive a "scale" metric, which is then used in ranking across suspicious persons and in threshold- based notification. In contrast, Rao's "time interval" is expressly listed as one of many machine- learning features tied to detection events and camera traversals, not a per-person crime-incident spacing metric keyed to, for example, a store or product-type incident categories. Accordingly, Rao does not teach the subject matter at issue.
Rozner and Swift are cited for allegedly teaching other claim features and fail to teach the subject matter at issue. For at least these reasons, any combination of Miwa, Rao, Rozner, and Swift fails to render the independent claims and the claims that depend thereon unpatentable.”
Applicant’s assertion that “Rao’s teachings regarding a time interval between two detections are used as a feature for predicting loss-prevention events based on detections across cameras” is not persuasive. Paragraphs [0119-0128] specifically disclose instances in which time of the day, day of the week, month a repeat offender is detected is considered. This is further evidenced in paragraph [0073] which shows associating a risk level to a person based on a number of occasions the person has triggered an alarm in the past. Therefore, this feature extends beyond simply detection across cameras. Furthermore, the previous rejection established that Miwa discloses determining, using the profile, a scale of crimes committed by a person based on monetary loss per criminal incident. Rao is used to show that using temporal features for criminal detection are known in art and would have been obvious. That is to say, one skilled in the art would understand that using a time interval between two detections as a metric for assessing risk to an offender, as taught by Rao, could be combined with the teachings of Miwa to arrive at the claimed invention.
Applicant’s arguments, see section II on page 8 of the remarks filed 01/30/2026, with respect to the rejection of claims 1, 12 and 20 under 35 U.S.C. §103 have been fully considered, but they are not persuasive.
Applicant alleges
“Whether taken alone or in combination, Miwa, Rao, Rozner, and Swift fail to show or render obvious "determining a rank of the person in the database of suspicious persons based on a frequency and the scale of crimes committed by the person compared to other suspicious persons," as recited in independent claims 1, 12, and 20.
The Office Action relies on Miwa for allegedly teaching the subject matter at issue. Applicant respectfully traverses. Miwa registers and identifies people as either a "habitual shoplifter" or a "suspicious behavior person," stores their facial images, and then transmits alerts preferentially to the closest employee once a match is found. See Miwa, paras. 111, 180. Miwa's discussion of determining "actual harm" and prioritizing actions for different classes of persons is not a determination of an ordered "rank of the person in the database of suspicious persons" based on frequency and scale compared to other suspicious persons, as recited. Miwa describes prioritizing execution and adjusting monitoring levels, which is qualitatively different from generating a rank within a database based on comparative frequency and scale metrics across multiple persons. Assigning individuals to two nominal categories is not an ordinal placement among individuals in the database. Ranking involves ordering persons relative to each other (e.g., first, second, third) using comparative cross-person measures; Miwa never performs such an ordering.
Rao, Rozner, and Swift are cited for allegedly teaching other claim features and fail to teach the subject matter at issue. For at least these reasons, any combination of Miwa, Rao, Rozner, and Swift fails to render the independent claims and the claims that depend thereon unpatentable.”
This is not persuasive. Miwa explicitly distinguishes between two types of persons. Habitual shoplifters and persons exhibiting suspicious behavior. The term “habitual” establishes this person as a one who repeatedly shoplifts. The person exhibiting suspicious behavior, as seen in paragraph [0180], is defined as one who is not a habitual shoplifter. That is to say, a clear difference in the frequency of criminal activity between the two types of persons is clearly defined. The scale of which (e.g., economic loss) is appropriately designated. It is established that priority is given to habitual shoplifters because they present more harm to the establishment than the persons exhibiting the suspicious behavior. Therefore, the priority given to the habitual shoplifter means they are more important to the system than the person exhibiting suspicious behavior. Paragraph [0185] shows that information concerning habitual shoplifters and suspicious behaving persons are both added to a database. Accordingly, at least the status assigned to the habitual shoplifter and the person exhibiting suspicious behavior is compared to determine the priority. The examiner maintains that the combination of Miwa and Rao teaches the inventions of claims 1, 12 and 20.
Conclusion
THIS ACTION IS MADE FINAL. 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 JAMES M ANDERSON II whose telephone number is (571)270-1444. The examiner can normally be reached Monday - Friday 10AM-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, BRIAN PENDLETON can be reached at 571-272-7527. 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.
/James M Anderson II/Primary Examiner, Art Unit 2425
Prosecution Insights