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 .
Amendment
Applicant submitted amendments on 1/2/2026. The Examiner acknowledges the amendment and has reviewed the claims accordingly.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The IDS(s) dated 10/16/2023 that have been previously considered remain placed in the application file.
Overview
Claims 1 and 4-7 are pending in this application and have been considered below.
Claims 2-3 are canceled by the applicant.
Claims 1 and 6-7 are rejected.
Claims 4-5 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.
Applicant Arguments
In regards to Argument 1, Applicant states claims have been amended to tie with hardware components with specific structure for performing the claimed functions, therefore withdraw of the claim interpretation under 35 U.S.C. 112(f) is requested (See Remarks, page 6 under “Discussion of Claim Rejections under 35 U.S.C. 112(f)”).
In regards to Argument 2, Applicant states Claim 1 has been amended to incorporate language from dependent claims 2 and 3. Specifically, Porikli does not teach or suggest the claimed “function” or “distance from the function”. Porikli’s likelihood scores are frame-by-frame confidence measures, not a function derived from accumulated historical data representing a location-size relationship (See Remarks, page 7-8 under “Discussion of Claim Rejections under 35 U.S.C. 103”).
In regards to Argument 3, Applicant states Porikli’s “tracking update” is not equivalent to the claimed “target object determination”. Porikli’s purpose (tracking continuity) and the claimed invention’s purpose (false-detection elimination) are materially different (See Remarks, page 8-9 under “Discussion of Claim Rejections under 35 U.S.C. 103”).
In regards to Argument 4, Applicant states Yano does not disclose or suggest "creating a function indicating a relationship between the location of the detection object and the size of the detection object", or "determining a target object based on a distance from such a function". Yano merely addresses association logic for the detected object and the tracked object, not function derivation or distance evaluation (See Remarks, page 9 under “Discussion of Claim Rejections under 35 U.S.C. 103”).
In regards to Argument 5, Applicant states Oami does not teach deriving a function from that data that represents a location-size relationship, or using a distance between the function and current detection parameters as a determination criterion (See Remarks, page 9-10 under “Discussion of Claim Rejections under 35 U.S.C. 103”).
In regards to Argument 6, Applicant states the Examiners conclusion relies on hindsight reconstruction since none of the references recognize the problem of false detections caused by perspective-induced size variation without prior calibration, or suggest solving such a problem by automatically generating a location-size function from accumulated historical data (See Remarks, page 10 under “Discussion of Claim Rejections under 35 U.S.C. 103”).
Examiner’s Response
In response to Argument 1, with respect to Claim(s) 1-5 and 7, the Examiner has fully considered the Argument and has found it persuasive.
In response to Argument 2, the Examiner respectfully disagrees. The Applicant suggests the examiner misinterprets Porikli’s “likelihood scores” and “kernel update process” as the claimed “index” and “determination”, and Porikli’s distance is merely positional distance between kernel and prior location.
Applicant’s characterization of Porikli in isolation is noted, however, the rejection is based on the combination of references, with Oami providing the primary teaching of a history-derived function relating location and size. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Oami explicitly records historical detection and tracking results including position and size over time (¶54; See page 7 and 8 of the Non-Final Rejection), then derives a composite quality index that jointly considers location-dependent quality and size-dependent quality (¶81-82, 94-101; Fig. 17B-D). The total quality constitutes a function indicating a relationship between location and size under BRI, as higher quality requires both favorable location and sufficient size. Porikli supplements this with adaptive scale (size) modeling integrated with positional likelihood (¶50-60, 83--91).
The claim does not require a single fitted curve from a point cloud, like specified in claims 4-5, therefore a composite model derived from historical location/size data is sufficient under BRI.
The Examiner interprets the prior art to teach amended claim 1.
In response to Argument 3, the Examiner respectfully disagrees. The Applicant suggests Porikli assumes the tracked object is already the target and merely updates location, and does not perform binary determination for false detection suppression.
Examiner provided reason to combine (all three references operate in the analogous art of video surveillance and object detection/tracking, with a shared objective of improving reliability by distinguishing valid detections), please see the previous Office Action page 7 and 8. References do not need to share an identical purpose or solve the identical technical problem. See MPEP §2144; KSR International Co. v. Teleflex Inc., 82 USPQ2d 1385 (U.S. 2007)).
Oami explicitly suppresses low-quality detections (potential false positives) using history-based quality criteria incorporating location and size (¶54, 79-81), prioritizing high quality objects for extraction while low quality objects are not processed further. This achieves the claimed binary determination of “target object” status analogous to applicant’s stated goal of false detection suppression without manual calibration.
The Examiner interprets the prior art to teach amended claim 1.
In response to Argument 4, the Examiner respectfully disagrees. The Applicant suggests Yano addresses association logic but does not teach creating a location-size function from history or distance evaluation.
In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Yano is a reference applied for its teaching of robust detection-tracking association using positional proximity and size-aware similarity thresholds in multi-scale environments (¶40-60, 85-95). Yano is not relied upon to teach the full function or distance limitations, which are addressed primarily by Oami.
The Examiner interprets the prior art to teach amended claim 1.
In response to Argument 5, the Examiner respectfully disagrees. The Applicant suggests Oami merely records historical data but does not derive a function modeling location-size correlations or use geometric distance for determination.
As outlined on page 7-10, Oami records historical detection/tracking results including time, position, and size (¶54-68), then derives a size-dependent resolution quality function (¶81-82; Expression 1) and a location-dependent environmental quality function (¶94-99; Expression 6). These are combined into total quality ‘Q’ (¶88-101). The resulting Q is a function indicating a relationship between location and size under BRI as quality depends jointly on both factors. Oami then determines target status by thresholding or ranking Q (¶79-80, 120-130), suppressing low quality detections. Deviation from expected quality reads on the claimed “distance”, which is not limited to geometric. Mere recording is not the mapping, it is the active derivation and combining of location/size factors from history for thresholded validation that directly addressed the limitation.
The Examiner interprets the prior art to teach amended claim 1.
In response to Argument 6, the Examiner respectfully disagrees. The Applicant suggests the combination of references relies on hindsight.
Examiner provided reason to combine (all three references operate in the analogous art of video surveillance and object detection/tracking, with a shared objective of improving reliability by distinguishing valid detections), please see the previous Office Action page 7 and 8. Pursuant to KSR, the Supreme Court has discouraged rigid use of the Teaching, Suggestion, Motivation (TSM) test, and has said that obviousness rejections must be based on an articulated reasoning with rational underpinning. (See KSR International Co. v. Teleflex Inc., 82 USPQ2d 1385 (U.S. 2007). Applicant has not provided persuasive evidence or argument that the rejection, as articulated, is not based upon a rational underpinning or how the provided rationales and item-to-item matching are insufficient articulation pursuant to In re Jung. Further, motivation was provided in all present and previous combinations of references. Although a specific motivation may not have been explicitly stated within one of the references, the motivation was not improper, and provided in accordance with the Teaching-Suggestion-Motivation Test (TSM). As such, Examiner's use of these facts as a motivation statement is in compliance with the requirements of the TSM test, since the Teaching-Suggestion-Motivation (TSM) test should be flexibly applied and the teaching, suggestion, or motivation need not be written within the reference. See KSR Int'l Co. v. Teleflex Inc., 82 USPQ2d 1385 (US 2007); Ortho-McNeil Pharm., Inc. v. Mylan Lab., Inc., 520 F.3d 1358, 86 U.S.P.Q.2d 1196 (Fed. Cir. 2008); Ex Parte Kubin, 83 USPQ2d 1410 (Bd. Pat. App. & Int. 2007).
The Examiner interprets the prior art to teach amended claim 1 and 6-7.
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.
Claim(s) 1 and 6-7 is/are rejected under 35 U.S.C. 103 as obvious over Porikli et al (US 20060222205 A1, hereafter referred to as Porikli) in view of Yano et al (US 20160260226 A1, hereafter referred to as Yano), further in view of Oami et al (US 20220180533 A1, hereafter referred to as Oami).
Claim 1
Regarding Claim 1, Porikli teaches An image recognition device, comprising:
a processor configured to:
acquire a captured image (Porikli in Abstract discloses "A method tracks a moving object in a video acquired of a scene with a camera.");
determine whether the detection object is the target object by comparing the location and the size of the detection object detected from the captured image with the index (Porikli in ¶88-89 discloses "there are several likelihood scores that we can assign to each of these estimated locations. We measure a distance likelihood score by measuring the distance between the estimated location of the kernel and the previous location … We integrate motion history of the object by determining and assigning a motion likelihood score based on the previous speed and direction of the object within the previous frames using a Kalman filter" – history-based index for target confirmation where a Kalman filter provides the mechanism described).
Porikli does not explicitly teach all of a detect a predetermined type of object as a detection object by image recognition from the captured image; perform control to record a history of a location and a size of the detection object detected from the captured image; create an index for determining whether the detection object is a target object to be detected based on the history, wherein the processor creates a function indicating a relationship between the location of the detection object and the size of the detection object as the index and determines that the detection object is the target object in response to a distance determined from the function and the location and the size of the detection object in the captured image being less than a predetermined threshold value.
However, Yano teaches a detect a predetermined type of object as a detection object by image recognition from the captured image (Yano in Abstract discloses “a detection unit configured to detect a detection target object from an interest image frame in the moving image, a tracking unit configured to obtain a tracked object in a neighborhood region of a detection position of the detection target object in an image frame preceding the interest image frame in the moving image, and a determination unit configured to determine whether or not the tracked object corresponds to the detection target object by integrating a position where the detection target object is detected by the detection unit and a position where the tracked object is obtained by the tracking unit");
determines that the detection object is the target object in response to a distance determined from the function and the location and the size of the detection object in the captured image being less than a predetermined threshold value (Yano in ¶49 discloses "The tracking object determination unit 700 determines whether or not the currently tracked object is the object set as the detection and tracking target on the basis of the likelihood of the object tracked by the first object tracking unit 400 which is output by the object discrimination unit 200 (step S420). It is determined. whether or not the likelihood of each of the tracking results obtained in step S400 output by the object discrimination unit 200 is higher than a predetermined threshold" – tracks object using a mean-shift process with kernels where the system determines a new location of the target object by calculating a fusion score; Kalman-derived motion model with a distance comparison to a maximum score.).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Porikli by incorporating a detection unit configured to detect a predetermined type of object that is taught by Yano, since both reference are analogous art in the field of video-based object and tracking; thus, one of ordinary skilled in the art would be motivated to combine the references since Porikli’s Kalman filter-based motion history with Yano’s image recognition detection unit yields the predictable result of enabling specific object type recognition while maintaining robust tracking confirmation, thereby improving overall detection accuracy and reducing false positives in dynamic image sequences.
Porikli in view of Yano does not explicitly teach all of a perform control to record a history of a location and a size of the detection object detected from the captured image; create an index for determining whether the detection object is a target object to be detected based on the history, wherein the processor creates a function indicating a relationship between the location of the detection object and the size of the detection object as the index.
However, Oami teaches perform control to record a history of a location and a size of the detection object detected from the captured image (Oami in ¶54 discloses "object detection result information includes time information about a frame in which detection is performed (or information for identifying the frame such as a frame number) and information about the detected object, and the information about the object includes the detection position and the size of the object.");
create an index for determining whether the detection object is a target object to be detected based on the history (Oami in ¶54 discloses "object detection result information includes time information about a frame in which detection is performed (or information for identifying the frame such as a frame number) and information about the detected object, and the information about the object includes the detection position and the size of the object."), wherein
the processor creates a function indicating a relationship between the location of the detection object and the size of the detection object as the index (Oami in ¶54 discloses "object detection result information includes time information about a frame in which detection is performed (or information for identifying the frame such as a frame number) and information about the detected object, and the information about the object includes the detection position and the size of the object.").
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Porikli in view of Yano by incorporating a recording control unit that records object detection result information, including time/frame identification, detection position, and object size, as well as an index that uses historical information to determine target objects that is taught by Oami, since both reference are analogous art in the field of object detection and tracking; thus, one of ordinary skilled in the art would be motivated to combine the references since Porikli in view of Yano’s Kalman filter-based motion prediction and type-specific detection system with Oami’s record of position, size, and time information for correspondence and correction yields the predictable result of enabling robust target verification and position correction across frames despite detection delays, thereby enhancing tracking accuracy in dynamic environments.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claim 6
Regarding Claim 6, Porikli teaches a method for an image recognition device, comprising:
an image acquisition step of acquiring a captured image (Porikli in Abstract discloses "A method tracks a moving object in a video acquired of a scene with a camera.");
a determining step of determining whether the detection object is the target object by comparing the location and the size of the detection object detected from the captured image with the index (Porikli in ¶88-89 discloses "there are several likelihood scores that we can assign to each of these estimated locations. We measure a distance likelihood score by measuring the distance between the estimated location of the kernel and the previous location … We integrate motion history of the object by determining and assigning a motion likelihood score based on the previous speed and direction of the object within the previous frames using a Kalman filter" – history-based index for target confirmation where a Kalman filter provides the mechanism described).
Porikli does not explicitly teach all of a detect a predetermined type of object as a detection object by image recognition from the captured image; perform control to record a history of a location and a size of the detection object detected from the captured image; create an index for determining whether the detection object is a target object to be detected based on the history, wherein the processor creates a function indicating a relationship between the location of the detection object and the size of the detection object as the index and determines that the detection object is the target object in response to a distance determined from the function and the location and the size of the detection object in the captured image being less than a predetermined threshold value.
However, Yano teaches a detect a predetermined type of object as a detection object by image recognition from the captured image (Yano in Abstract discloses “a detection unit configured to detect a detection target object from an interest image frame in the moving image, a tracking unit configured to obtain a tracked object in a neighborhood region of a detection position of the detection target object in an image frame preceding the interest image frame in the moving image, and a determination unit configured to determine whether or not the tracked object corresponds to the detection target object by integrating a position where the detection target object is detected by the detection unit and a position where the tracked object is obtained by the tracking unit");
determines that the detection object is the target object in response to a distance determined from the function and the location and the size of the detection object in the captured image being less than a predetermined threshold value (Yano in ¶49 discloses "The tracking object determination unit 700 determines whether or not the currently tracked object is the object set as the detection and tracking target on the basis of the likelihood of the object tracked by the first object tracking unit 400 which is output by the object discrimination unit 200 (step S420). It is determined. whether or not the likelihood of each of the tracking results obtained in step S400 output by the object discrimination unit 200 is higher than a predetermined threshold" – tracks object using a mean-shift process with kernels where the system determines a new location of the target object by calculating a fusion score; Kalman-derived motion model with a distance comparison to a maximum score.).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Porikli by incorporating a detection unit configured to detect a predetermined type of object that is taught by Yano, since both reference are analogous art in the field of video-based object and tracking; thus, one of ordinary skilled in the art would be motivated to combine the references since Porikli’s Kalman filter-based motion history with Yano’s image recognition detection unit yields the predictable result of enabling specific object type recognition while maintaining robust tracking confirmation, thereby improving overall detection accuracy and reducing false positives in dynamic image sequences.
Porikli in view of Yano does not explicitly teach all of a perform control to record a history of a location and a size of the detection object detected from the captured image; create an index for determining whether the detection object is a target object to be detected based on the history, wherein the processor creates a function indicating a relationship between the location of the detection object and the size of the detection object as the index.
However, Oami teaches perform control to record a history of a location and a size of the detection object detected from the captured image (Oami in ¶54 discloses "object detection result information includes time information about a frame in which detection is performed (or information for identifying the frame such as a frame number) and information about the detected object, and the information about the object includes the detection position and the size of the object.");
create an index for determining whether the detection object is a target object to be detected based on the history (Oami in ¶54 discloses "object detection result information includes time information about a frame in which detection is performed (or information for identifying the frame such as a frame number) and information about the detected object, and the information about the object includes the detection position and the size of the object."), wherein
the processor creates a function indicating a relationship between the location of the detection object and the size of the detection object as the index (Oami in ¶54 discloses "object detection result information includes time information about a frame in which detection is performed (or information for identifying the frame such as a frame number) and information about the detected object, and the information about the object includes the detection position and the size of the object.").
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Porikli in view of Yano by incorporating a recording control unit that records object detection result information, including time/frame identification, detection position, and object size, as well as an index that uses historical information to determine target objects that is taught by Oami, since both reference are analogous art in the field of object detection and tracking; thus, one of ordinary skilled in the art would be motivated to combine the references since Porikli in view of Yano’s Kalman filter-based motion prediction and type-specific detection system with Oami’s record of position, size, and time information for correspondence and correction yields the predictable result of enabling robust target verification and position correction across frames despite detection delays, thereby enhancing tracking accuracy in dynamic environments.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claim 7
Regarding Claim 7, Porikli in view of Yano, further in view of Oami teaches A non-transient computer-readable recording medium, recording a program for an image recognition device, being an image recognition program for causing a computer to function as the image recognition device according to claim 1, and the program being configured to cause a computer to function as the processor (Porikli in view of Yano, further in view of Oami discloses a computer to function as the image recognition device according to claim 1. See rejection for Claim 1.).
Allowable Subject Matter
Claims 4-5 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.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JUSTIN P CASCAIS whose telephone number is (703)756-5576. The examiner can normally be reached Monday-Friday 8:00-4:00.
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, Mr. O’Neal Mistry can be reached on (313) 446-4912. 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.
/J.P.C./Examiner, Art Unit 2674
/ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674
Date: 1/13/2026