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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission, filed on 22 January 2026, has been entered.
Response to Arguments
Applicant’s arguments, filed 22 January 2026, with respect to the rejection under U.S.C. 103 of Claims 1-15 have been fully considered but are not persuasive.
In regard to the references Schumacher et al (US Publication 20180322778 A1), applicant states “Schumacher discloses classifying vehicles based primarily on visual similarity, using image-derived features such as edges, textures, and colors. Schumacher extracts visual features from vehicle images and matches them to a reference database. See the Abstract and paragraphs [0023]-[0026] of Schumacher. This image-based classification is inherently limited, because visually similar vehicles (e.g., same model and color) cannot be reliably distinguished, classification accuracy is sensitive to environmental conditions, such as lighting or occlusions, non-visible attributes (e.g., engine type or trim level) cannot be inferred from visual features.” However, this appears to be a rather superficial summary of Schumacher’s invention. By such measure, all inventions in this field would merely be “classifying vehicles based primarily on visual similarity, using image-derived features such as edges, textures, and colors”. There is instead much more nuance to what Schumacher discloses. Instead, Schumacher discloses capturing vehicle registration information such as the license plate of a vehicle (Reference “vehicle identifier 503”, See Specification paragraph 0039). Further, vehicle images are used for an automatic learning classification (Reference “vehicle images” and “automatic learning classification”, see Specification paragraph 0032) as well as the vehicle identifier used for querying the database (Reference “vehicle identifier”, see Specification paragraph 0033).
It appears in turn Schumacher would also disclose the newly introduced limitations “perform a learning process to learn the vehicle image using the classification key (Reference “automatic learning classification method “ See Specification paragraph 0032 where the vehicle images used for an automatic learning classification method and see Specification paragraph 0033 where the processor used in the automatic learning classification method uses the unique vehicle identifier to query the registration database which would read as a learning process using the classification key), wherein the learning process is performed using vehicle images that are stored in connection with corresponding classification keys (Reference “registration database”, see Specification paragraph 0025 which describes the registration database in detail where the visual images and futures. Further, note the specific mention the unique vehicle identifier and vehicle features extracted using vehicle image stored in the registration database), and wherein a same classification key is assigned to vehicle images that represents a same vehicle outer appearance (Reference “visual features”, See Specification paragraph 0032 where the visual features are used to determine if fit within the class in the database. Recalling the classes stored in the databased have the visual features and unique vehicle identifies stored associated with them), and different classification keys are assigned to vehicle images that represents different vehicle outer appearances (Reference “new class”, See Specification paragraph 0033 where the vehicle identifier is used to determine if a class exists for a vehicle with different outer appearance or vehicle that does not fit any other class’s visual features. Then see Specification paragraph 0034 where those different visual features are used to create a new class or see Specification paragraph 0025 describing the structure of this registration database in much greater detail: “A registration database is a database managed or controlled by a vehicle registration entity. One example of a registration database is the Driver and Vehicle Licensing Agency (DVLA). Another example is the local agency that issues vehicle registrations. The vehicle registration entity may be governmental or non-governmental. Registration database 130 may store vehicle registration information including unique vehicle identifiers, information about visual features, and associated vehicle class information”). Therefore, it appears Schumacher in view of Himana (see below) continues to disclose the limitations of Claim 1.
Claim Rejections - 35 USC § 103
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 1-2, 4-5, 7-8, and 11-15 are rejected under 35 U.S.C. 103 as being unpatentable over Schumacher et al (US Publication 20180322778 A1) in view of Himana et al (JP Publication No. 2005031880 A).
Regarding Claim 1, Schumacher discloses A device for classifying vehicle images (Reference “automatic vehicle classification system”, see Specification paragraph 0023), the device comprising: a camera configured to (Reference “camera”, see Specification paragraph 0023) acquire a vehicle image containing a license plate of a vehicle (Reference “license plate”, see Specification paragraph 0023); a processor configured to extract vehicle identification information from the acquired vehicle image (Reference “Unique vehicle identifier”, see Specification paragraph 0024 which is extracted from the vehicle image); acquire vehicle registration information corresponding to the vehicle identification information (Reference “Unique vehicle identifier”, see Specification paragraph 0024 where the license plate characters are extracted which is registration information); selectively extract a portion of the vehicle registration information indicating outer appearance characteristics (Reference “visual characteristic”, see Specification paragraph 0025 where visual characteristics of the vehicle are extracted which include body, axel count, model, etc.) of the vehicle and allocate a classification key thereto (Reference “Vehicle class”, see Specification paragraph 0025 the vehicles are recognized by the processor and stored by a vehicle class. Note in the case of a new vehicle class the processor creates and stores a new vehicle class which reads as allocating); and classify the vehicle image based on the classification key (Reference “matching”, see Specification paragraph 0025 where the processor matches the characteristics gathered from the image with those present in a database to determine a match success to determine if the vehicle belongs in the vehicle class, specifically using the unique vehicle identifier as well in paragraph 0033); perform a learning process to learn the vehicle image using the classification key (Reference “automatic learning classification method“ See Specification paragraph 0032 where the vehicle images used for an automatic learning classification method and see Specification paragraph 0033 where the processor used in the automatic learning classification method uses the unique vehicle identifier to query the registration database which would read as a learning process using the classification key), wherein the learning process is performed using vehicle images that are stored in connection with corresponding classification keys (Reference “registration database”, see Specification paragraph 0025 which describes the registration database in detail where the visual images and futures. Further, note the specific mention the unique vehicle identifier and vehicle features extracted using vehicle image stored in the registration database), and wherein a same classification key is assigned to vehicle images that represents a same vehicle outer appearance (Reference “visual features”, See Specification paragraph 0032 where the visual features are used to determine if fit within the class in the database. Recalling the classes stored in the databased have the visual features and unique vehicle identifies stored associated with them), and different classification keys are assigned to vehicle images that represents different vehicle outer appearances (Reference “new class”, See Specification paragraph 0033 where the vehicle identifier is used to determine if a class exists for a vehicle with different outer appearance or vehicle that does not fit any other class’s visual features. Then see Specification paragraph 0034 where those different visual features are used to create a new class or see Specification paragraph 0025 describing the structure of this registration database in much greater detail: “A registration database is a database managed or controlled by a vehicle registration entity. One example of a registration database is the Driver and Vehicle Licensing Agency (DVLA). Another example is the local agency that issues vehicle registrations. The vehicle registration entity may be governmental or non-governmental. Registration database 130 may store vehicle registration information including unique vehicle identifiers, information about visual features, and associated vehicle class information.”).”
However, Schumacher fails to disclose vehicle registration information corresponding to the vehicle identification information, from an external database storing vehicle registration information included in vehicle registration certificates. Instead, Himana discloses vehicle identification information, from an external database storing vehicle registration information included in vehicle registration certificates (Reference “center server” and “registration database”, see Specification paragraph 0057 where a database is searched by the center server using the entrance data as a search key and the registration certificate is stored in the database. Further, see Specification paragraph 0046 which describes this entry data as a recognition result of an image taken when the vehicle enters the area and the recognition result attempts to recognize the vehicle registration information). Motivation for this modification is also given by Himana who notes its use in detection of counterfeiting and unauthorized activity in the monitored area (See Specification paragraph 0057). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify Schumacher with Himana’s vehicle registration database.
Regarding Claim 2, Schumacher discloses The device of claim 1, wherein the classification key is generated based on at least (Reference “class” and “unique vehicle identifier”, see Specification paragraph 0025 where the registration database stores this information and generates the class with the unique vehicle identifier and vehicle visual features such as), a vehicle type (Reference “visual characteristic” and “body type”, see Specification paragraph 0025 where visual characteristics such as body type is parsed such as SUV), a vehicle name (Note in the applicant Specification, this is called out to as a car model—the Sonata which is typically referred to as a “Kia make” and “Sonata model”. Schumacher nonetheless discloses both. Reference “make” or “model”, see Specification paragraph 0025), and a model type (Reference “model”, see Specification paragraph 0025 where the model of the vehicle is extracted, and see above where a make would read as a vehicle name) and year (Reference “manufacture date”, see Specification paragraph 0006 where a manufacture date which includes the model year is extracted from the visual features).
Regarding Claim 4, Schumacher discloses The device of claim 1, wherein the processor is further configured to acquire outer appearance information of the vehicle based on at least one of a vehicle type (Reference “body type”, see Specification paragraph 0025 where a body type is parsed such as SUV. Note this body type is specifically extracted from the visual characteristics), a vehicle name (Reference “make” or “model”, see Specification paragraph 0025), a model type and year (Reference “model”, see Specification paragraph 0025 where the model of the vehicle is extracted. Reference “manufacture date”, see Specification paragraph 0006 where a manufacture date which includes the model year is extracted from the visual features), and a vehicle identification number included in the vehicle registration information (Reference “unique vehicle identification”, see Specification paragraph 0025 where from the visual characteristics the unique vehicle identification is extracted).
Regarding Claim 5, Schumacher discloses The device of claim 1, wherein the processor includes a storage for storing (Reference “storage”, see Specification paragraph 0046 where non-volatile computer storages are described) the vehicle image using a predetermined classification key or vehicle registration number as an index (Reference “vehicle class”, see Specification paragraph 0037 where for example an outlier vehicle image is stored and these are stored within their vehicle class. This is used to confirm new or outlier vehicles which might not belong to one of already established classes, and therefore reads as a classification key).
Regarding Claim 7, Schumacher discloses The device of claim 1, wherein the vehicle image contains a vehicle region extracted from the vehicle image using coordinates of the vehicle license plate (Reference “license plate” and “image”, see Specification paragraph 0023-0024 describing capture of the license plate region and further use of edge detection. Specification paragraph 0041 for example shows further use of this license plate region when the edge detection occurring near the license plate area helps identify visual characteristics such as curvature of the vehicle bumper).
Claim 8 is rejected for containing similar limitations described above in Claim 1.
Claim 11, as a method embodiment of the devices and systems disclosed above in Claim 1, is also disclosed by Schumacher (Reference “method”, See Specification paragraphs 0032 and 0039)
Claim 12 is rejected for containing similar limitations described above in Claim 4.
Claim 13 is rejected for containing similar limitations described above in Claim 5.
Regarding Claim 14, Schumacher discloses The method of claim 11, wherein the learning process includes extracting learning information by analyzing vehicle images corresponding to the same classification key (Reference “vehicle class”, see Specification paragraph 0037 This is used to confirm new or outlier vehicles which might not belong to one of already established classes and see previous uses of the classification key in rejection above. Further note Specification paragraph 0038 further describing the comparison of the visual features to those in the same vehicle class or sharing the same classification key).
Claim 15 is rejected for containing similar limitations described above in Claim 7.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Schumacher et al (US Publication 20180322778 A1) in view of Himana et al (JP Publication No. 2005031880 A) further in view of Petrey et al (US Publication No. 20200410251 A1).
Regarding Claim 3, Schumacher fails to disclose The device of claim 1, wherein the vehicle identification information includes an identifier or a media access control (MAC) address of communication unit installed in the vehicle.
Instead, Petrey discloses The device of claim 1, wherein the vehicle identification information includes an identifier or a media access control (MAC) address of communication unit installed in the vehicle (Reference “MAC”, see Specification paragraph 0021 where the vehicle identifiers extracted by the system include MAC addresses of various communication units which might be present in the vehicles monitored such as WIFI or Bluetooth). Motivation for such a modification is given when attempting to identify suspicious vehicles, as conventional systems are unable to do so (See Specification paragraph 0020). The electronic identifiers such as MAC addresses of devices present within the car help to distinguish these suspicious vehicles and can also help with accuracy and speed of decisions made (See Specification paragraph 0020). Therefore, it would have been obvious before the effective filing date to modify Schumacher with Petrey to utilize the identifiers of electronic devices in the vehicles being monitored.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Schumacher et al (US Publication 20180322778 A1) in view of Himana et al (JP Publication No. 2005031880 A) further in view of Guo (“A Method of Recognition for Fake Plate Vehicles”).
Regarding Claim 10, Schumacher fails to disclose The system of claim 8, wherein one or more processors are further configured to determine whether there is a duplicated vehicle registration number among previously stored vehicle images and classification keys. Instead, Guo discloses The system of claim 8, wherein the operation unit is configured to determine whether there is a duplicated vehicle registration number among previously stored vehicle images and classification keys (Reference “duplicate”, see Section “Recognition of Fake Plate Vehicles between Same Vehicle Types”, “Recognition of Fake Plate Vehicles between Different Vehicle Types”, and Figures 3 and 4. Specifically, in paragraph 3 of “Recognition of Fake Plate Vehicles between Same Vehicle Types”, the comparison of vehicle images is used to determine if a duplicate number is present). Motivation for such a modification is found in the Abstract, where verification of such processes must be done by enforcement personnel and public information. This conventional approach “is inefficient and produces very little effect”. Instead, this automatic approach taught by Guo is efficient and has 84% precision. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify Schumacher in view of Guo.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEXANDER JOHN RODGERS whose telephone number is (703)756-1993. The examiner can normally be reached 5:30AM to 2:30PM ET.
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, John Villecco can be reached on (571) 272-7319. 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.
/ALEXANDER JOHN RODGERS/Examiner, Art Unit 2661
/JOHN VILLECCO/Supervisory Patent Examiner, Art Unit 2661