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
The information disclosure statement (IDS) submitted on May 7, 2024 and August 14, 2024 are 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.
Claim(s) 1-5, 7-8, 11-15, 17-18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent No. 11,301,711 to Price et al. (hereinafter Price), and further in view of Jeon, Hae-Gon, et al. "Stereo matching with color and monochrome cameras in low-light conditions." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. (hereinafter Jeon).
Regarding independent claim 1, Price discloses A computer-implemented method for multi-model classification in a vehicle identification system (abstract, “Disclosed embodiments provide systems, methods, and computer-readable storage media for enhancing a vehicle identification with preprocessing. ”), the computer-implemented method comprising:
providing (column 4, line 65, “As used herein, the term “image” refers to any digital representation of a scene formed by one or more light beams. The image may comprise a plurality of pixels, each pixel having corresponding color and/or intensity data (e.g., RGB, CMYK, or grayscale data).”) (column 2, line 48, “The system may comprise memory and processor devices to execute instructions to perform operations including receiving an image depicting a vehicle.”);
processing the color image through a first machine learning model for first object classification of one or more features corresponding to the vehicle (column 3, line 65, “As used herein, the term “image” refers to any digital representation of a scene formed by one or more light beams. The image may comprise a plurality of pixels, each pixel having corresponding color and/or intensity data (e.g., RGB, CMYK, or grayscale data);” Figure 7, element 705, “receive image of object” and element 710; column 1, line 16, “More specifically, and without limitation, this disclosure relates to systems and methods for using machine learning processes to identify vehicles from images;” column 17, line 3, “At step 710, system 100 analyzes the received image with an identification model. That is, system 100 may determine an initial identification confidence value, by recognizing features in received image portraying an object, and utilizing statistical analysis to determine an initial identification of the object through assignment of confidence index values. System 100 determines the identity, that is, the predicted identity, of an object based on any of the considerations described herein;” the first processing is read as one machine learning network), wherein the first object classification is carried out without inputting any of:
image data from the monochrome image (as seen in Figure 7, only the initial color image is read as being input for processing); and
other data derived from the monochrome image (as seen in Figure 7, only the initial color image is read as being input for processing);
determining an accuracy confidence of the first object classification with respect to at least one of the one or more features (Figure 7, element 710, “analyze image with identification model and determine initial identification confidence); and
when the determined accuracy confidence is less than a predefined threshold (Figure 7, “N” in response to element 720; column 17, line 28, “At step 720, system 100 further determines whether the initial confidence of the predicted identity (i.e. first predicted identity) is within a predetermined quality threshold.”), processing a combination of the color image along with the monochrome image (column 10, line 35, “Image 401 may exhibit image attributes such as rotation angle 410, focus 420, brightness 430, contrast 440, black/white (saturation) 450, and color 460, as well as, other attribute data described herein;” column 11, line 15, “. Adjusting black/white 450 and color 460 may adjust every pixel data of image 401;” column 17, line 58, “At step 722, when the first identification confidence is below the quality threshold, outside the threshold range, or system 100 otherwise determines that a given identification is insufficiently strong (e.g., based on an analysis of one or more confidence index value distributions as described elsewhere herein, system 100 may modify an attribute of the image with a preprocessing augmentation tool, e.g., preprocessing augmentation tool 319. System 100 may modify an attribute of the received image by means discussed in FIG. 4. In some embodiments, system 100 may modify the received image numerous times, or alternatively, system 100 may modify several attributes once or numerous times by means discussed;” combination is read as the color image being transformed into the monochrome image via color adjustment), or along with a depth image derived at least in part from the monochrome image, through a second machine learning model for second object classification of the at least one of the one or more features (the second machine learning model is read as the second processing steps (i.e. these steps aren’t included in the first model if the quality is of the desired threshold); Figure 7, element 722-726; column 5, line 56, “The at least one processor may be further configured to run an augmented reality framework, such as Apple's ARKit or Android's ARCore, or a machine learning framework, such as Apple's CoreML or Android's Tensorflow.”),
wherein the processing through the second machine learning model is more computationally expensive than the processing through the first machine learning model (being that the second machine learning model requires image manipulation, the second model is read as more computationally expensive (i.e. involving more steps as opposed to just operating on raw image data)).
Price fails to explicitly disclose as further recited. However, Jeon discloses
providing both a color image and a monochrome image, each in respect of at least a portion of a vehicle (Figure 1A, “(a) A pair of color and monochrome image”);
processing a combination of the color image along with the monochrome image (Figure 3; page 4088, left column, “we first decolorize the color input image”… “Given the grayscale input;” i.e. both the color input and grayscale (monochrome) image are input), or along with a depth image derived at least in part from the monochrome image (NOTE: “or” means the limitation is not required to be met)
Price is directed toward “disclosed embodiments provide systems, methods, and computer-readable storage media for enhancing a vehicle identification with preprocessing. The system may comprise memory and processor devices to execute instructions for receiving an image depicting a vehicle (abstract).” Jeon is directed toward “a new stereo matching method with a color and monochrome camera pair (abstract).” As can be easily seen by one of ordinary skill in the art before the effective filing date of the claimed invention, Price and Jeon are directed toward similar methods of endeavor of image analysis. Further, as evidenced in Jeon, there are drawbacks to stereo cameras as noted in the abstract, “Consumer devices with stereo cameras have become popular because of their low-cost depth sensing capability. However, those systems usually suffer from low imaging quality and inaccurate depth acquisition under low-light conditions.” One of ordinary skill in the art before the effective filing date of the claimed invention would be aware that there are multiple different imaging techniques that can be used to obtain an image of a vehicle. Further, when determining vehicle features, it is well known depth data may provide key information on vehicle type. Jeon discloses producing accurate depth maps and high-quality images, which again, would be incredibly useful when trying to determine a vehicle classification (i.e. low quality data can lead to inaccurate classifications). Thus, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Jeon in order to ensure depth data is accurately collected and images are of the best quality for downstream processing.
Regarding dependent claim 2, the rejection of claim 1 is incorporated herein. Additionally, Jeon in the combination further discloses wherein the combination of the color image along with one of: the monochrome image; and the depth image derived at least in part from the monochrome image is a combination of the color image and the monochrome image (abstract, “we present a new stereo matching method with a color and monochrome camera pair;” Figure 3, “Our method produces the accurate depth map (f) and the high-quality color image (g);” the inputs are the pair of the monochrome and color image).
It would be obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Jeon to ensure accurate depth maps are generated using the benefits of the color image and the monochrome image.
Regarding dependent claim 3, the rejection of claim 1 is incorporated herein. Additionally, Jeon in the combination further discloses wherein the combination of the color image along with one of: the monochrome image; and the depth image derived at least in part from the monochrome image is a combination of the color image and the depth image (Figure 3, “Our method produces the accurate depth map (f) and the high-quality color image (g);” the input color image is combined with the refined depth map (f) to generate a higher-quality color image).
It would be obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Jeon to ensure a high-quality data rich image is produced for processing.
Regarding dependent claim 4, the rejection of claim 3 is incorporated herein. Additionally, Price and Jeon in the combination fails to explicitly disclose wherein both the color image and the monochrome image are synchronously captured images, and the depth image is generated by combining the color image with the monochrome image. However, as seen in Figure 1, and throughout the paper, Jeon references the color image and monochrome images as “pairs.” Additionally, as seen in Figure 1A, the images are of the same scene and the abstract notes, “to address the problem, we present a new stereo matching method with a color and monochrome camera pair.” The examiner takes the official notice that the images being of the same scene is read that the images are taken at the time. Said differently, if the imaged scene was moving, and the images weren’t necessarily taken at the same time, then the images wouldn’t reflect the same objects/positioning. Thus, in order to have true image “pairs” where the difference is only in the coloring of the image, it would have been obvious to a person having ordinary skill int eh art before the effective filing date of the claimed invention to ensure the images were obtained simultaneously.
Regarding dependent claim 5, the rejection of claim 1 is incorporated herein. Additionally, Price discloses further comprising: comparing a second operand obtained from the second object classification of the at least one of the one or more features with a first stored operand that was obtained from the first object classification of the at least one of the one or more features (column 11, line 19, “By modifying one or more of each attribute 410-460, user 112 may modify image 401 and create a modified image for identification analysis.”… “The identification model application 400 may further compare resulting identification analyses, based on the resulting image;”). However, Price and Jeon in the combination as a whole fail to explicitly disclose as further recited.
However, the examiner takes official notice that one of ordinary skill in the art before the effective filing date of the claimed invention would easily implement overwriting incorrect values. The two operand data outputs not matching, means that one is inaccurate and one is accurate. One of ordinary skill in the art before the effective filing date of the claimed invention would understand that the first output could be inaccurate based on being processed on one image only, whereas the second output is based on additional data (i.e. a color image and the monochrome or depth map data). Further, in the field of computer processing, memory space is conserved as much as possible; retaining inaccurate or undesirable data takes up necessary memory space. Overwriting an inaccurate value saves memory of the system, as opposed to storing two pieces of data. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of Price and Jeon to include overwriting undesirable or inaccurate data, so that there is more storage room for necessary data.
Regarding dependent claim 7, the rejection of claim 1 is incorporated herein. Additionally, Price in the combination further discloses wherein the at least one of the one or more features corresponds to a color for the vehicle (column 4, line 24, “When the object is a vehicle, the object-attributes may be associated with a vehicle make, model, trim line, year, color, etc;” column 6, line 19, “System 100 may be used to identify a vehicle, and associated vehicle attributes (e.g., make, vehicle model, trim line, year, color, etc.) ”)
Regarding dependent claim 8, the rejection of claim 1 is incorporated herein. Additionally, Price in the combination further discloses wherein the first and second machine learning models are implemented on an at least one processor contained within a rechargeable battery-powered camera (column 8, line 9, “FIG. 3 illustrates an exemplary configuration of user device 110, consistent with disclosed embodiments. User device 110 may be implemented in system 100 as various devices, such as a cell phone, a tablet, a mobile computer, a desktop, etc. As shown, user device 110 includes a display 311, one or more input/output (“I/O”) components 312, one or more processors 313, and a memory 314 having stored therein one or more program applications 315, such as an identification model application, and data 316. User device 110 also includes an antenna 317 and one or more sensors 318;” the mobile phone is read as a rechargeable battery-powered camera under BRI).
Regarding dependent claim 11, the rejection of claim 1 is incorporated herein. Additionally, Price in the combination further discloses wherein the at least one of the one or more features corresponds to a make and model for the vehicle (column 4, line 24, “When the object is a vehicle, the object-attributes may be associated with a vehicle make, model, trim line, year, color, etc;” column 6, line 19, “System 100 may be used to identify a vehicle, and associated vehicle attributes (e.g., make, vehicle model, trim line, year, color, etc.) ”)
Regarding independent claim 12, the rejection of claim 1 applies directly. Additionally, Price discloses A vehicle identification system (abstract, “Disclosed embodiments provide systems, methods, and computer-readable storage media for enhancing a vehicle identification with preprocessing. ”) comprising:
at least one camera (column 13, line 46, “the device capturing the image”) configured to capture (abstract, “receiving an image depicting a vehicle;” column 4, line 65, “As used herein, the term “image” refers to any digital representation of a scene formed by one or more light beams. The image may comprise a plurality of pixels, each pixel having corresponding color and/or intensity data (e.g., RGB, CMYK, or grayscale data).”);
at least one processor in communication with the at least one camera (Figure 3, element 313, “processor” and the camera is read as the I/O 312; column 8, line 45, “ I/O components 312 may include components such as, for example, buttons, switches, speakers, microphones, cameras, styluses, or touchscreen panels.”); and
at least one electronic storage medium (Figure 3, element 314, “Memory”) storing program instructions that when executed by the at least one processor cause the at least one processor to perform (abstract, “The system may comprise memory and processor devices to execute instructions for receiving an image depicting a vehicle. ”):
establishing a first machine learning model to process the color image for first object classification of one or more features corresponding to the vehicle (column 3, line 65, “As used herein, the term “image” refers to any digital representation of a scene formed by one or more light beams. The image may comprise a plurality of pixels, each pixel having corresponding color and/or intensity data (e.g., RGB, CMYK, or grayscale data);” Figure 7, element 705, “receive image of object” and element 710; column 1, line 16, “More specifically, and without limitation, this disclosure relates to systems and methods for using machine learning processes to identify vehicles from images;” column 17, line 3, “At step 710, system 100 analyzes the received image with an identification model. That is, system 100 may determine an initial identification confidence value, by recognizing features in received image portraying an object, and utilizing statistical analysis to determine an initial identification of the object through assignment of confidence index values. System 100 determines the identity, that is, the predicted identity, of an object based on any of the considerations described herein;” the first processing is read as one machine learning network), wherein the first object classification is carried out without inputting any of:
image data from the monochrome image (as seen in Figure 7, only the initial color image is read as being input for processing); and
other data derived from the monochrome image (as seen in Figure 7, only the initial color image is read as being input for processing);
determining an accuracy confidence of the first object classification with respect to at least one of the one or more features (Figure 7, element 710, “analyze image with identification model and determine initial identification confidence”); and
establishing a second machine learning model (the second machine learning model is read as the second processing steps (i.e. these steps aren’t included in the first model if the quality is of the desired threshold);) which, when the determined accuracy confidence is less than a predefined threshold (Figure 7, “N” in response to element 720; column 17, line 28, “At step 720, system 100 further determines whether the initial confidence of the predicted identity (i.e. first predicted identity) is within a predetermined quality threshold.”), processes a combination of the color image along with the monochrome image (column 10, line 35, “Image 401 may exhibit image attributes such as rotation angle 410, focus 420, brightness 430, contrast 440, black/white (saturation) 450, and color 460, as well as, other attribute data described herein;” column 11, line 15, “. Adjusting black/white 450 and color 460 may adjust every pixel data of image 401;” column 17, line 58, “At step 722, when the first identification confidence is below the quality threshold, outside the threshold range, or system 100 otherwise determines that a given identification is insufficiently strong (e.g., based on an analysis of one or more confidence index value distributions as described elsewhere herein, system 100 may modify an attribute of the image with a preprocessing augmentation tool, e.g., preprocessing augmentation tool 319. System 100 may modify an attribute of the received image by means discussed in FIG. 4. In some embodiments, system 100 may modify the received image numerous times, or alternatively, system 100 may modify several attributes once or numerous times by means discussed;” combination is read as the color image being transformed into the monochrome image via color adjustment), or along with a depth image derived at least in part from the monochrome image, for second object classification of the at least one of the one or more features (the second machine learning model is read as the second processing steps (i.e. these steps aren’t included in the first model if the quality is of the desired threshold); Figure 7, element 722-726; column 5, line 56, “The at least one processor may be further configured to run an augmented reality framework, such as Apple's ARKit or Android's ARCore, or a machine learning framework, such as Apple's CoreML or Android's Tensorflow.”),
wherein the processing through the second machine learning model is more computationally expensive than the processing through the first machine learning model (being that the second machine learning model requires image manipulation, the second model is read as more computationally expensive (i.e. involving more steps as opposed to just operating on raw image data)).
Price fails to explicitly disclose as further recited. However, Jeon discloses
at least one camera configured to capture both a color image and a monochrome image (abstract, “To address the problem, we present a new stereo matching method with a color and monochrome camera pair;” page 4086, right column, “In this paper, we present a stereo matching framework with a color and monochrome image pair (Fig. 1(a)). Our system is designed to estimate an accurate depth map under low-light conditions without additional light sources (Fig. 1(b)). In order to obtain reliable correspondence, we exploit the fundamental trade-off between color sensing capability and light efficiency of color cameras and monochrome cameras, respectively.”);
processes a combination of the color image along with the monochrome image (Figure 3; page 4088, left column, “we first decolorize the color input image”… “Given the grayscale input;” i.e. both the color input and grayscale (monochrome) image are input), or along with a depth image derived at least in part from the monochrome image (NOTE: “or” means the limitation is not required to be met).
Price is directed toward “disclosed embodiments provide systems, methods, and computer-readable storage media for enhancing a vehicle identification with preprocessing. The system may comprise memory and processor devices to execute instructions for receiving an image depicting a vehicle (abstract).” Jeon is directed toward “a new stereo matching method with a color and monochrome camera pair (abstract).” As can be easily seen by one of ordinary skill in the art before the effective filing date of the claimed invention, Price and Jeon are directed toward similar methods of endeavor of image analysis. Further, as evidenced in Jeon, there are drawbacks to stereo cameras as noted in the abstract, “Consumer devices with stereo cameras have become popular because of their low-cost depth sensing capability. However, those systems usually suffer from low imaging quality and inaccurate depth acquisition under low-light conditions.” One of ordinary skill in the art before the effective filing date of the claimed invention would be aware that there are multiple different imaging techniques that can be used to obtain an image of a vehicle. Further, when determining vehicle features, it is well known depth data may provide key information on vehicle type. Jeon discloses producing accurate depth maps and high-quality images, which again, would be incredibly useful when trying to determine a vehicle classification (i.e. low quality data can lead to inaccurate classifications). Thus, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Jeon in order to ensure depth data is accurately collected and images are of the best quality for downstream processing.
Regarding dependent claim 13, the rejection of claim 12 is incorporated herein. Additionally, Jeon in the combination further discloses wherein the combination of the color image along with one of: the monochrome image; and the depth image derived at least in part from the monochrome image is a combination of the color image and the monochrome image (abstract, “we present a new stereo matching method with a color and monochrome camera pair;” Figure 3, “Our method produces the accurate depth map (f) and the high-quality color image (g);” the inputs are the pair of the monochrome and color image).
It would be obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Jeon to ensure accurate depth maps are generated using the benefits of the color image and the monochrome image.
Regarding dependent claim 14, the rejection of claim 12 is incorporated herein. Additionally, Jeon in the combination further discloses wherein the combination of the color image along with one of: the monochrome image; and the depth image derived at least in part from the monochrome image is a combination of the color image and the depth image (Figure 3, “Our method produces the accurate depth map (f) and the high-quality color image (g);” the input color image is combined with the refined depth map (f) to generate a higher-quality color image).
It would be obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Jeon to ensure a high-quality data rich image is produced for processing.
Regarding dependent claim 15, the rejection of claim 14 is incorporated herein.
Price in the combination further discloses the depth image is generated by combining the color image with the monochrome image (abstract, “we present a new stereo matching method with a color and monochrome camera pair;” Figure 3, “Our method produces the accurate depth map (f) and the high-quality color image (g);” the inputs are the pair of the monochrome and color image).
Additionally, Price and Jeon in the combination fails to explicitly disclose wherein capturing of both the color image and the monochrome image by the at least one camera is synchronized capturing. However, as seen in Figure 1, and throughout the paper, Jeon references the color image and monochrome images as “pairs.” Additionally, as seen in Figure 1A, the images are of the same scene and the abstract notes, “to address the problem, we present a new stereo matching method with a color and monochrome camera pair.” The examiner takes the official notice that the images being of the same scene is read that the images are taken at the time. Said differently, if the imaged scene was moving, and the images weren’t necessarily taken at the same time, then the images wouldn’t reflect the same objects/positioning. Thus, in order to have true image “pairs” where the difference is only in the coloring of the image, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to ensure the images were obtained simultaneously.
Regarding dependent claim 17, the rejection of claim 12 is incorporated herein. Additionally, Price in the combination further discloses wherein the at least one of the one or more features corresponds to a color for the vehicle (column 4, line 24, “When the object is a vehicle, the object-attributes may be associated with a vehicle make, model, trim line, year, color, etc;” column 6, line 19, “System 100 may be used to identify a vehicle, and associated vehicle attributes (e.g., make, vehicle model, trim line, year, color, etc.) ”)
Regarding dependent claim 18, the rejection of claim 12 is incorporated herein. Additionally, Price in the combination further discloses wherein the at least one processor is contained within the at least one camera, and the at least one camera is a rechargeable battery-powered camera (column 8, line 9, “FIG. 3 illustrates an exemplary configuration of user device 110, consistent with disclosed embodiments. User device 110 may be implemented in system 100 as various devices, such as a cell phone, a tablet, a mobile computer, a desktop, etc. As shown, user device 110 includes a display 311, one or more input/output (“I/O”) components 312, one or more processors 313, and a memory 314 having stored therein one or more program applications 315, such as an identification model application, and data 316. User device 110 also includes an antenna 317 and one or more sensors 318;” the mobile phone is read as a rechargeable battery-powered camera under BRI).
Regarding dependent claim 20, the rejection of claim 12 is incorporated herein. Additionally, Price in the combination further discloses wherein the at least one of the one or more features corresponds to a make and model for the vehicle (column 4, line 24, “When the object is a vehicle, the object-attributes may be associated with a vehicle make, model, trim line, year, color, etc;” column 6, line 19, “System 100 may be used to identify a vehicle, and associated vehicle attributes (e.g., make, vehicle model, trim line, year, color, etc.) ”)
Claim(s) 6, 10 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Price further in view of Jeon as applied to claims 1 and 12 respectively above, and further in view of U.S. Patent No. 9,911,055 to Kozitsky et al. (hereinafter Kozitsky).
Regarding dependent claim 6, the rejection of claim 1 is incorporated herein. Additionally, Price and Jeon in the combination fail to explicitly disclose wherein the at least one of the one or more features corresponds to a license plate number for the vehicle.
However, Kozitsky discloses wherein the at least one of the one or more features corresponds to a license plate number for the vehicle (abstract, “Methods, systems, and processor-readable media for the detection and classification of license plates. In an example embodiment, an image of a vehicle can be captured with an image-capturing unit. A license plate region can then be located in the captured image of the vehicle by extracting a set of candidate regions from the image utilizing a weak classifier.”).
As noted above, Price and Jeon are directed toward accurate and high-quality image analysis. Further, Kozitsky is directed toward “Methods, systems, and processor-readable media for the detection and classification of license plates. In an example embodiment, an image of a vehicle can be captured with an image-capturing unit (abstract).” As can be easily seen by one of ordinary skill in the art before the effective filing date of the claimed invention, Price, Jeon and Kozitsky are directed toward similar methods of endeavor of image analysis. Further, one of ordinary skill in the art before the effective filing date of the claimed invention would be well aware there are multiple different uses of vehicle detection, and different features of a vehicle one may be interested in. For example, one may be interested in determining a type of car they like, charging a car tolls by plate, or ensuring registration is accurate in relation to make/model of the car and the registration. Thus, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Kozitsky to allow for additional processing beyond general car feature classification, and instead allow specific tracking of a unique vehicle by license plate.
Regarding dependent claim 10, the rejection of claim 1 is incorporated herein. Additionally, Price and Jeon in the combination fail to explicitly disclose wherein:
the at least a portion of a vehicle is a license plate displaying a license plate number, and
the license plate appears as a partly occluded object in the color image.
However, Kozitsky discloses wherein:
the at least a portion of a vehicle is a license plate displaying a license plate number (abstract, “Methods, systems, and processor-readable media for the detection and classification of license plates. In an example embodiment, an image of a vehicle can be captured with an image-capturing unit. A license plate region can then be located in the captured image of the vehicle by extracting a set of candidate regions from the image utilizing a weak classifier.”), and
the license plate appears as a partly occluded object in the color image (column 1, line 19, “challenging noise sources present in license plate images captured under realistic conditions (i.e., field deployed solutions). These include: heavy shadows, non-uniform illumination, challenging optical geometries, partial occlusion, varying contrast, and general imaging noise;” column 6, line 3, “cases where the license plate is not present, is partially occluded, is too dark, too bright, or mangled, etc;” column 4, line 50, “The image capture operation shown at block 32 involves the capture/acquisition of images from, for example, highways or express-ways using, for example, RGB cameras which are directed towards the license plate of an incoming vehicle.”).
As noted above, Price and Jeon are directed toward accurate and high-quality image analysis. Further, Kozitsky is directed toward “Methods, systems, and processor-readable media for the detection and classification of license plates. In an example embodiment, an image of a vehicle can be captured with an image-capturing unit (abstract).” As can be easily seen by one of ordinary skill in the art before the effective filing date of the claimed invention, Price, Jeon and Kozitsky are directed toward similar methods of endeavor of image analysis. Further, one of ordinary skill in the art before the effective filing date of the claimed invention would be well aware there are multiple different uses of vehicle detection, and different features of a vehicle one may be interested in. For example, one may be interested in determining a type of car they like, charging a car tolls by plate, or ensuring registration is accurate in relation to make/model of the car and the registration. Thus, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Kozitsky to allow for additional processing beyond general car feature classification, and instead allow specific tracking of a unique vehicle by license plate.
Regarding dependent claim 16, the rejection of claim 12 is incorporated herein. Additionally, Price and Jeon in the combination fail to explicitly disclose wherein the at least one of the one or more features corresponds to a license plate number for the vehicle.
However, Kozitsky discloses wherein the at least one of the one or more features corresponds to a license plate number for the vehicle (abstract, “Methods, systems, and processor-readable media for the detection and classification of license plates. In an example embodiment, an image of a vehicle can be captured with an image-capturing unit. A license plate region can then be located in the captured image of the vehicle by extracting a set of candidate regions from the image utilizing a weak classifier.”).
As noted above, Price and Jeon are directed toward accurate and high-quality image analysis. Further, Kozitsky is directed toward “Methods, systems, and processor-readable media for the detection and classification of license plates. In an example embodiment, an image of a vehicle can be captured with an image-capturing unit (abstract).” As can be easily seen by one of ordinary skill in the art before the effective filing date of the claimed invention, Price, Jeon and Kozitsky are directed toward similar methods of endeavor of image analysis. Further, one of ordinary skill in the art before the effective filing date of the claimed invention would be well aware there are multiple different uses of vehicle detection, and different features of a vehicle one may be interested in. For example, one may be interested in determining a type of car they like, charging a car tolls by plate, or ensuring registration is accurate in relation to make/model of the car and the registration. Thus, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Kozitsky to allow for additional processing beyond general car feature classification, and instead allow specific tracking of a unique vehicle by license plate.
Allowable Subject Matter
Claims 9 and 19 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.
The following is a statement of reasons for the indication of allowable subject matter: the closest prior arts of record teach methods of processing multiple images as needed for classification of objects using machine learning methods. However, none of them alone or in any combination teaches determining if an accuracy confidence of an object classification is less than a threshold, where the threshold itself is determined based on a target power consumption level for a rechargeable battery-powered camera.
The closest prior art being Price discloses utilizing a threshold to determine if the calculated confidence of the identification of an object satisfies the threshold (Figure 7, element 710-720). Further, Price discloses the threshold that is used as the comparative value is a predetermined value; column 17, line 39, “The predetermined quality threshold (or threshold range) may be set by user 112, by a third-party developer, and/or by system 100. User 112, the third-party developer, or system 100 may set the predetermined quality threshold based on analysis of the model prediction performance and historical confidence distribution data stored in a database such as database 120 or memory 314.” The pre-determined value is not based on a target power consumption.
However, Price fails to disclose determining if an accuracy confidence of an object classification is less than a threshold, where the threshold itself is determined based on a target power consumption level for a rechargeable battery-powered camera.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
U.S. Publication No. 2015/0110358 to Han et al. discloses “n apparatus and method for detecting a vehicle number plate that may determine whether an input image includes a number plate, based on an optimal feature to be used to determine whether the input image includes a number plate (abstract).”
U.S. Publication No. 2024/0395027 to Shen et al. discloses, “In various examples, multilabel hierarchical classification of objects for autonomous systems and applications is described herein (abstract).”
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Courtney J. Nelson whose telephone number is (571)272-3956. 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, John Villecco can be reached at 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.
/COURTNEY JOAN NELSON/Primary Examiner, Art Unit 2661