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. Claim Status Claims 1-20 are currently pending in the application filed December 8, 2022. Priority Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55. Information Disclosure Statement The information disclosure statements (IDS) submitted on 11/02/2023 have been considered by the Examiner. Drawings The drawings are objected to under 37 CFR 1.83(a). The drawings must show every feature of the invention specified in the claims. Therefore, the claim 3 limitation “a total number of defects of each type, from among a plurality of defect types, is inserted in equal numbers in the plurality of generated images.” must be shown or the feature(s) canceled from the claim(s). No new matter should be entered. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance. Specification Applicant is reminded of the proper language and format for an abstract of the disclosure. The abstract should be in narrative form and generally limited to a single paragraph on a separate sheet within the range of 50 to 150 words in length. The abstract should describe the disclosure sufficiently to assist readers in deciding whether there is a need for consulting the full patent text for details. The language should be clear and concise and should not repeat information given in the title. It should avoid using phrases which can be implied, such as, “The disclosure concerns,” “The disclosure defined by this invention,” “The disclosure describes,” etc. In addition, the form and legal phraseology often used in patent claims, such as “means” and “said,” should be avoided. The abstract of the disclosure is objected to because it contains legal phraseology often used in patent claims such as " includes " and " comprising ". A corrected abstract of the disclosure is required and must be presented on a separate sheet, apart from any other text. See MPEP § 608.01(b). The disclosure is objected to because of the following informalities: FILLIN "Enter appropriate information" \* MERGEFORMAT In paragraph [ 0059], " themage " should read " the image " . Appropriate correction is required. Claim Rejections - 35 USC § 102 The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action: A person shall be entitled to a patent unless – (a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention. Claim(s) 1 -2, and 10- 12 are rejected under 35 U.S.C. 102 (a)(1) as being anticipated by Tiemeyer ( US 20040252879 A1 ) . Regarding Claim 1 , Tiemeyer teaches: A processor-implemented method with image generation, the method comprising ( Tiemeyer , [0036]; As shown in FIG. 6, the computer system includes at least a CPU or processor 100, a data storage or memory device 110, a display device or monitor 120, and one or more input devices 130 (e.g., a keyboard, a mouse, etc.). The computer is equipped with a graphical user interface (GUI) 140, as further described below. For illustration purposes, the GUI is shown as separate from the processor 100, but it will be understood that the GUI can be implemented in hardware and/or software of the processor.) receiving a plurality of input parameters for a plurality of images to be generated; ( Tiemeyer , [0010]; analyzing and classifying a population of data points each having associated with it at least three independent parameters, wherein the population of data points is graphically represented in three dimensions by plotting three parameters associated with each point in a selected coordinate system .) generating a plurality of defect profiles comprising a size and location of one or more defects to be formed in an image; ( Tiemeyer , [0011]; In this regard, another aspect of the invention relates to the creation of wafer "maps", i.e., graphical representations of scanned wafers having symbols displayed on the maps in locations corresponding to the locations of the defects they represent. The symbols may also have characteristics denoting attributes of the defects; for example, one symbol color, size, or shape may denote one defect type, another symbol color, size, or shape may denote another defect type, etc.) generating the plurality of images comprising defect information based on the plurality of defect profiles and the plurality of input parameters using an image rendering operation. ( Tiemeyer , [0011], The maps can be displayed side-by-side; alternatively, the maps can be overlaid to create a single composite map showing all defects for all wafers, or can be displayed in a "stacked" view with the maps spaced apart.) Regarding claim 2 , Tiemeyer teaches: wherein the plurality of input parameters comprises one or more of a plurality of defects to be formed in each image and a plurality of defect types. ( Tiemeyer , [0053], One or more defect types attributable to defects in the original boule can then be represented on the various wafer maps by a symbol that is distinguishable (e.g., in color, shape, and/or size) from other defects types). Regarding Claim 10 , Tiemeyer teaches: A non-transitory computer-readable storage medium storing instruction that, when executed by one or more processors, configure the one or more processors to perform the method of claim 1. ( Tiemeyer , [0025], The computer preferably is programmed, along with the graphical user interface, to allow the operator to create a defect classification algorithm that takes into account at least one defined boundary surface.) Regarding Claim 11 , Tiemeyer teaches: An apparatus with image generation, the apparatus comprising: one or more processors configured to: ( Tiemeyer , [0036]; As shown in FIG. 6, the computer system includes at least a CPU or processor 100, a data storage or memory device 110, a display device or monitor 120, and one or more input devices 130 (e.g., a keyboard, a mouse, etc.). The computer is equipped with a graphical user interface (GUI) 140, as further described below. For illustration purposes, the GUI is shown as separate from the processor 100, but it will be understood that the GUI can be implemented in hardware and/or software of the processor.) receive a plurality of input parameters for a plurality of images to be generated; ( Tiemeyer , [0010]; analyzing and classifying a population of data points each having associated with it at least three independent parameters, wherein the population of data points is graphically represented in three dimensions by plotting three parameters associated with each point in a selected coordinate system.) generate a plurality of defect profiles comprising a size and location of one or more defects to be formed in an image; and ( Tiemeyer , [0011]; In this regard, another aspect of the invention relates to the creation of wafer "maps", i.e., graphical representations of scanned wafers having symbols displayed on the maps in locations corresponding to the locations of the defects they represent. The symbols may also have characteristics denoting attributes of the defects; for example, one symbol color, size, or shape may denote one defect type, another symbol color, size, or shape may denote another defect type, etc.) generate the plurality of images comprising defect information based on the plurality of defect profiles and the plurality of input parameters using an image rendering operation. ( Tiemeyer , [0011], The maps can be displayed side-by-side; alternatively, the maps can be overlaid to create a single composite map showing all defects for all wafers, or can be displayed in a "stacked" view with the maps spaced apart.) Regarding claim 12 , Tiemeyer teaches: wherein the plurality of input parameters comprises one or more of a plurality of defects to be formed in each image and a plurality of defect types. ( Tiemeyer , [0053], One or more defect types attributable to defects in the original boule can then be represented on the various wafer maps by a symbol that is distinguishable (e.g., in color, shape, and/or size) from other defects types). 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. 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. This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. Claim s 3 and 13 is rejected under 35 U.S.C. 103 as being unpatentable over Tiemeyer ( US 20040252879 A1 ) as applied to claim 1 and further in view Honda ( US2004 0 234120A1 ) Regarding Claim 3 , Tiemeyer fails to teach: wherein the generating of the plurality of images comprises generating the plurality of images such that a total number of defects of each type, from among a plurality of defect types, is inserted in equal numbers in the plurality of generated images. Honda teaches: wherein the generating of the plurality of images comprises generating the plurality of images such that a total number of defects of each type, from among a plurality of defect types, is inserted in equal numbers in the plurality of generated images. (Honda, [0037] ; allocation may be so performed that each group includes each defect type in equal amount) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer and Honda is . The motivation to for the combination is to have the defect types inserted in equal numbers . ( Honda, [0058]; Here, such division is applied to equalize the defecting number included in each defect class in each group. ) Regarding claim 13 , Tiemeyer fails to teach: wherein the generating of the plurality of images comprises generating the plurality of images such that a total number of defects of each type, from among a plurality of defect types, is inserted in equal numbers in the plurality of generated images. Honda teaches: wherein the generating of the plurality of images comprises generating the plurality of images such that a total number of defects of each type, from among a plurality of defect types, is inserted in equal numbers in the plurality of generated images. (Honda, [0037]; allocation may be so performed that each group includes each defect type in equal amount) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer with Honda . The motivation to for the combination is to have the defect types inserted in equal numbers. (Honda, [0058]; Here, such division is applied to equalize the defecting number included in each defect class in each group.) Claim s 4 -5 and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Tiemeyer ( US 20040252879 A1 ) as applied to claim 1 and further in view Dehaerne (A Comparative Study of Deep-Learning Object Detectors for Semiconductor Defect Detection) , presented in a conference from 24-26 October 2022. Regarding Claim 4 , Tiemeyer fails to teach: wherein each of the plurality of generated images comprises a line pattern corresponding to either one of an optical microscopy image and a scanning electron microscope image of a patterning process. Dehaerne teaches: wherein each of the plurality of generated images comprises a line pattern corresponding to either one of an optical microscopy image and a scanning electron microscope image of a patterning process. ( Dehaerne , pg 1 col 1 para 2; “Scanning electron microscopy (SEM) allows for higher resolution images than optical imaging tools and is therefore preferred for the inspection of nano-micro range components but automatic inspection remains a challenge. Deep-learning methods have been shown to be more robust than traditional, rule-based defect detectors for finding line pattern defects in SEM images”) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer with Dehaerne . The motivation to for the combination is to have line patterns be present for either optical microscopy and scanning electron microscopy. ( Dehaerne , pg 2 col 1 para 3 , This study compared eight different SOTA object detectors on the task of detecting semiconductor line space pattern defects) Regarding claim 5 , the combination of Tiemeyer and Dehaerne teaches: wherein one or more defects of the line pattern comprises any one or any combination of any two or more of a micro bridge, a bridge, a micro gap, an extended gap, and a line-collapse. ( Dehaerne , pg 1 col 1 para 3, “These defects are classified as belonging to one of five possible classes: line collapse, gap, probable gap, bridge, or microbridge”) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer with Dehaerne . The motivation to for the combination is to have the different classifications of the defect types . ( Dehaerne , Table II ) Regarding Claim 14 , Tiemeyer fails to teach: wherein each of the plurality of generated images comprises a line pattern corresponding to either one of an optical microscopy image and a scanning electron microscope image of a patterning process. Dehaerne teaches: wherein each of the plurality of generated images comprises a line pattern corresponding to either one of an optical microscopy image and a scanning electron microscope image of a patterning process. ( Dehaerne , pg 1 col 1 para 2; “Scanning electron microscopy (SEM) allows for higher resolution images than optical imaging tools and is therefore preferred for the inspection of nano-micro range components but automatic inspection remains a challenge. Deep-learning methods have been shown to be more robust than traditional, rule-based defect detectors for finding line pattern defects in SEM images”) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer with Dehaerne . The motivation to for the combination is to have line patterns be present for either optical microscopy and scanning electron microscopy. ( Dehaerne , pg 2 col 1 para 3, This study compared eight different SOTA object detectors on the task of detecting semiconductor line space pattern defects) Regarding Claim 15 , the combination of Tiemeyer and Dehaerne teaches : wherein one or more defects of the line pattern comprises any one or any combination of any two or more of a micro bridge, a bridge, a micro gap, an extended gap, and a line-collapse. ( Dehaerne , pg 1 col 1 para 3, “These defects are classified as belonging to one of five possible classes: line collapse, gap, probable gap, bridge, or microbridge”) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer with Dehaerne . The motivation to for the combination is to have the different classifications of the defect types. ( Dehaerne , Table II) Claim 6 and 16 is rejected under 35 U.S.C. 103 as being unpatentable over Tiemeyer ( US 20040252879 A1 ) as applied to claim 1 and further in view He (CN 112381794 A) Regarding Claim 6 , Tiemeyer fails to teach: wherein the generating of the plurality of defect profiles comprises determining th e location and size of the one or more defects to be formed in each image to be formed using a random distribution operation. He teaches: wherein the generating of the plurality of defect profiles comprises determining the location and size of the one or more defects to be formed in each image to be formed using a random distribution operation. ( He, [0008]; S 12, manufacturing the defect image: selecting a half picture, using the random number to determine the position and size of the defect) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer and He. The motivation to for the combination is to be able to detect size and location via the use of random distribution. (He, [0008]; S 12, manufacturing the defect image: selecting a half picture, using the random number to determine the position and size of the defect) Regarding Claim 1 6 , Tiemeyer fails to teach: wherein the generating of the plurality of defect profiles comprises determining th e location and size of the one or more defects to be formed in each image to be formed using a random distribution operation. He teaches: wherein the generating of the plurality of defect profiles comprises determining the location and size of the one or more defects to be formed in each image to be formed using a random distribution operation. (He, [0008]; S 12, manufacturing the defect image: selecting a half picture, using the random number to determine the position and size of the defect) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer and He. The motivation to for the combination is to be able to detect size and location via the use of random distribution. (He, [0008]; S 12, manufacturing the defect image: selecting a half picture, using the random number to determine the position and size of the defect) Claims 7-9 and 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Tiemeyer ( US 20040252879 A1 ) as applied to claim 1 above, and further in view of He ( CN-112381794-A ), C ho ( US7166856B2 ) , and Honda ( US20040234120A1 ). Regarding claim 7 , Tiemeyer fails to teach: providing the plurality of generated images and the plurality of generated defect profiles as a training data set to train a machine learning model; processing each image of the plurality of images into a grid comprising a plurality of cells; identifying an object by processing each cell in the grid using an object detection operation; and training the machine learning model by comparing coordinates of the identified object with coordinates stored in the plurality of generated defect profiles. He teaches: providing the plurality of generated images and the plurality of generated defect profiles as a training data set to train a machine learning model ( He, [0006]; S1, preparing training data set, comprising the following steps: S11, selecting image: selecting 50 printed images at different positions; S12, manufacturing the defect image: using the random number to determine the position and size of the defect, shape, generating random defect; ) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer and He . The motivation to for the combination is to be able prepare the training data set consisting of generated images and defect profiles. ( He, [ 000 3 ]; The deep learning method can deal with complex actual detection environment, but monitoring learning needs to use a large number of mark data set to perform model training, and the defect can be detected is only limited to the defect type in the training, for the defect of no training cannot be detected. using the unsupervised learning of the positive sample training; obtaining the defect-free image corresponding to the image to be detected; using the defect-free image and the to-be-detected image to obtain the result; and performing the optimization process to the result to realize the detection of any defect) Tiemeyer and He fail to teach: processing each image of the plurality of images into a grid comprising a plurality of cells; identifying an object by processing each cell in the grid using an object detection operation; and training the machine learning model by comparing coordinates of the identified object with coordinates stored in the plurality of generated defect profiles. Cho teaches: processing each image of the plurality of images into a grid comprising a plurality of cells; identifying an object by processing each cell in the grid using an object detection operation; ( Cho, [0048]; When a point of the defect can be identified from the image divided into a plurality of cells) identifying an object by processing each cell in the grid using an object detection operation; ( Cho, [0038]; the second controller 66 can determine whether a defect point is present in the second image) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer , and He with Cho . The motivation to for the combination is to be able arrange the images into plurality of cells and identify the defects in the images . (Cho, [0039], In this embodiment, it can be determined that a defect detected from a point X of each of the first and second images 41 and 42 does not indicate a defect of the LCD panel 15 itself. However, if the defect point of the second image 42 does not match that of the first image 41, a defect indicated in the second image 42 is determined to be a defect of the LCD panel 15 itself, at operation 86. Because a point of a defect can be detected from an image divided into a plurality of cells, a point (or pixel) of the defect incurred in the LCD panel 15 can be identified. Furthermore, in this embodiment, when a point Y indicating a defect point in the second image 42 is not displayed on the first image 41, the point Y can be determined to be a defect point of the LCD panel 15 itself.) Tiemeyer , He and Cho fail to teach: training the machine learning model by comparing coordinates of the identified object with coordinates stored in the plurality of generated defect profiles. Honda teaches: training the machine learning model by comparing coordinates of the identified object with coordinates stored in the plurality of generated defect profiles. (Honda, [0060], Here, as a method to see whether the classification performance is improved, there are a method for comparing the accuracy ratio among the classification classes, a method for comparison in terms of comprehensive performance, and a method of combination thereof. If the performance is improved as a result of both comparisons, the corresponding defects are regarded as the ones that have to be deleted. If the performance is reduced as a result of both comparisons, the defects are regarded as the ones essential for the teaching defects. And if the performance is improved as a result of either one comparison, the defects may be deleted or left as they are.) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer , He, and Cho with Honda . The motivation to for the combination is to be able train the machine learning model by comparing the defect profiles with the identified defects from the object identification technique. (Honda, Fig. 5) Regarding Claim 8 , The combination of Tiemeyer , He, Cho, and Honda teach es : providing a real image of a semiconductor wafer after a patterning process; (He, [0025], S51 to be-detected image generates non-defect image through generator; subtracting the defect image from the image to be detected by the S52 defect-free image to obtain a difference image; ) identifying the one or more defects in the real image using the trained machine learning model. ( He , [0027], using the threshold value division to remove the noise in the difference image, obtaining the final defect map.) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer , He, Cho, and Honda . The motivation to for the combination is to be able to identify the defect after using the trained machine learning model . (He, generating the subtraction between the image and the original image by the generator to obtain the difference image; fitting the noise distribution by the difference image of the defect-free image; removing noise by threshold value division, obtaining the final defect map.) Regarding Claim 9 , The combination of Tiemeyer , He, Cho, and Honda teaches: wherein the identifying of the one or more defects in the real image using the trained machine learning model comprises determining any one or any combination of any two or more of a defect type, a defect size, and a defect location in the real image. (He, [0008]; S 12, manufacturing the defect image: using the random number to determine the position and size of the defect, shape) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer , He, Cho, and Honda. The motivation to for the combination is to be able to identifying the defect after using the trained machine learning model and determining its physical characteristics. (He, [0008]; S 12, manufacturing the defect image: using the random number to determine the position and size of the defect, shape) Regarding Claim 17 , Tiemeyer fails to teach: receive the plurality of generated images and the plurality of generated defect profiles as a training data set to train a machine learning model; processing each image of the plurality of images into a grid comprising a plurality of cells; identifying an object by processing each cell in the grid using an object detection operation; and training the machine learning model by comparing coordinates of the identified object with coordinates stored in the plurality of generated defect profiles. He teaches: receive the plurality of generated images and the plurality of generated defect profiles as a training data set to train a machine learning model; ( He, [0006]; S1, preparing training data set, comprising the following steps: S11, selecting image: selecting 50 printed images at different positions; S12, manufacturing the defect image: using the random number to determine the position and size of the defect, shape, generating random defect; ) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer and He. The motivation to for the combination is to be able prepare the training data set consisting of generated images and defect profiles. (He, [0003]; The deep learning method can deal with complex actual detection environment, but monitoring learning needs to use a large number of mark data set to perform model training, and the defect can be detected is only limited to the defect type in the training, for the defect of no training cannot be detected. using the unsupervised learning of the positive sample training; obtaining the defect-free image corresponding to the image to be detected; using the defect-free image and the to-be-detected image to obtain the result; and performing the optimization process to the result to realize the detection of any defect) Tiemeyer and He fail to teach: processing each image of the plurality of images into a grid comprising a plurality of cells; identifying an object by processing each cell in the grid using an object detection operation; and training the machine learning model by comparing coordinates of the identified object with coordinates stored in the plurality of generated defect profiles. Cho teaches: processing each image of the plurality of images into a grid comprising a plurality of cells; identifying an object by processing each cell in the grid using an object detection operation; (Cho, [0048]; When a point of the defect can be identified from the image divided into a plurality of cells) identifying an object by processing each cell in the grid using an object detection operation; (Cho, [0038]; the second controller 66 can determine whether a defect point is present in the second image) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer , and He with Cho . The motivation to for the combination is to be able arrange the images into plurality of cells and identify the defects in the images. (Cho, [0039], In this embodiment, it can be determined that a defect detected from a point X of each of the first and second images 41 and 42 does not indicate a defect of the LCD panel 15 itself. However, if the defect point of the second image 42 does not match that of the first image 41, a defect indicated in the second image 42 is determined to be a defect of the LCD panel 15 itself, at operation 86. Because a point of a defect can be detected from an image divided into a plurality of cells, a point (or pixel) of the defect incurred in the LCD panel 15 can be identified. Furthermore, in this embodiment, when a point Y indicating a defect point in the second image 42 is not displayed on the first image 41, the point Y can be determined to be a defect point of the LCD panel 15 itself.) Tiemeyer , He and Cho fail to teach: training the machine learning model by comparing coordinates of the identified object with coordinates stored in the plurality of generated defect profiles. Honda teaches: training the machine learning model by comparing coordinates of the identified object with coordinates stored in the plurality of generated defect profiles. (Honda, [0060], Here, as a method to see whether the classification performance is improved, there are a method for comparing the accuracy ratio among the classification classes, a method for comparison in terms of comprehensive performance, and a method of combination thereof. If the performance is improved as a result of both comparisons, the corresponding defects are regarded as the ones that have to be deleted. If the performance is reduced as a result of both comparisons, the defects are regarded as the ones essential for the teaching defects. And if the performance is improved as a result of either one comparison, the defects may be deleted or left as they are.) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer , He, and Cho with Honda. The motivation to for the combination is to be able train the machine learning model by comparing the defect profiles with the identified defects from the object identification technique. (Honda, Fig. 5) Regarding claim 18 , The combination of Tiemeyer , He, Cho, and Honda teaches: receive a real image of a semiconductor wafer after a patterning process; (He, [0025], S51 to-be detected image generates non-defect image through generator; subtracting the defect image from the image to be detected by the S52 defect-free image to obtain a difference image; ) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer , He, Cho, and Honda. The motivation to for the combination is to be able provide a real image of the wafer to the model so it can identify the defects. (He, the machine vision is mainly used for detecting the defect by matching the template. subtracting the to-be-detected picture and the template image to obtain the defect mode) Tiemeyer , He, Cho, and Honda teaches: identifying the one or more defects in the real image using the trained machine learning model. ( He, [0027], using the threshold value division to remove the noise in the difference image, obtaining the final defect map.) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer , He, Cho, and Honda. The motivation to for the combination is to be able to identify the defect after using the trained machine learning model. (He, generating the subtraction between the image and the original image by the generator to obtain the difference image; fitting the noise distribution by the difference image of the defect-free image; removing noise by threshold value division, obtaining the final defect map.) Regarding Claim 19 , The combination of Tiemeyer , He, Cho, and Honda teaches: wherein the identifying of the one or more defects in the real image using the trained machine learning model comprises determining any one or any combination of any two or more of a defect type, a defect size, and a defect location in the real image. (He, [0008]; S12, manufacturing the defect image: using the random number to determine the position and size of the defect, shape) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer , He, Cho, and Honda . The motivation to for the combination is to be able to identifying the defect after using the trained machine learning model and determining its physical characteristics. (He, [0008]; S12, manufacturing the defect image: using the random number to determine the position and size of the defect, shape) Regarding Claim 20 , Tiemeyer teaches: A processor-implemented method with image generation, the method comprising ( Tiemeyer , [0036]; As shown in FIG. 6, the computer system includes at least a CPU or processor 100, a data storage or memory device 110, a display device or monitor 120, and one or more input devices 130 (e.g., a keyboard, a mouse, etc.). The computer is equipped with a graphical user interface (GUI) 140, as further described below. For illustration purposes, the GUI is shown as separate from the processor 100, but it will be understood that the GUI can be implemented in hardware and/or software of the processor.) receiving a plurality of input parameters for a plurality of images to be generated; ( Tiemeyer , [0010]; analyzing and classifying a population of data points each having associated with it at least three independent parameters, wherein the population of data points is graphically represented in three dimensions by plotting three parameters associated with each point in a selected coordinate system.) generating a plurality of defect profiles comprising a size and location of one or more defects to be formed in an image; ( Tiemeyer , [0011]; In this regard, another aspect of the invention relates to the creation of wafer "maps", i.e., graphical representations of scanned wafers having symbols displayed on the maps in locations corresponding to the locations of the defects they represent. The symbols may also have characteristics denoting attributes of the defects; for example, one symbol color, size, or shape may denote one defect type, another symbol color, size, or shape may denote another defect type, etc.) generating the plurality of images comprising defect information based on the plurality of defect profiles and the plurality of input parameters using an image rendering operation. ( Tiemeyer , [0011], The maps can be displayed side-by-side; alternatively, the maps can be overlaid to create a single composite map showing all defects for all wafers, or can be displayed in a "stacked" view with the maps spaced apart.) Tiemeyer fails to teach: identifying an object by processing each cell in the grid using an object detection operation; Cho teaches: identifying an object by processing each cell in the grid using an object detection operation; (Cho, [0038]; the second controller 66 can determine whether a defect point is present in the second image) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer with Cho . The motivation to for the combination is to be identify the defects in the images. (Cho, [0039], In this embodiment, it can be determined that a defect detected from a point X of each of the first and second images 41 and 42 does not indicate a defect of the LCD panel 15 itself. However, if the defect point of the second image 42 does not match that of the first image 41, a defect indicated in the second image 42 is determined to be a defect of the LCD panel 15 itself, at operation 86. Because a point of a defect can be detected from an image divided into a plurality of cells, a point (or pixel) of the defect incurred in the LCD panel 15 can be identified. Furthermore, in this embodiment, when a point Y indicating a defect point in the second image 42 is not displayed on the first image 41, the point Y can be determined to be a defect point of the LCD panel 15 itself.) Tiemeyer , and Cho fail to teach: training the machine learning model by comparing coordinates of the identified object with coordinates stored in the plurality of generated defect profiles. Honda teaches: training the machine learning model by comparing coordinates of the identified object with coordinates stored in the plurality of generated defect profiles. (Honda, [0060], Here, as a method to see whether the classification performance is improved, there are a method for comparing the accuracy ratio among the classification classes, a method for comparison in terms of comprehensive performance, and a method of combination thereof. If the performance is improved as a result of both comparisons, the corresponding defects are regarded as the ones that have to be deleted. If the performance is reduced as a result of both comparisons, the defects are regarded as the ones essential for the teaching defects. And if the performance is improved as a result of either one comparison, the defects may be deleted or left as they are.) Before the time of filing, it would have been obvious to one of ordinary skill in the art to combine Tiemeyer , He, and Cho with Honda . The motivation to for the combination is to be able train the machine learning model by comparing the defect profiles with the identified defects from the object identification technique. (Honda, Fig. 5). Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to FILLIN "Examiner name" \* MERGEFORMAT SHIVANGI SARKAR whose telephone number is FILLIN "Phone number" \* MERGEFORMAT (571)272-7262 . The examiner can normally be reached FILLIN "Work Schedule?" \* MERGEFORMAT M-F: 7:30-5:00 . 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, Emily Terrel l can be reached at (571) 270-3717 . 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. /SHIVANGI SARKAR/ Examiner, Art Unit 2666 /EMILY C TERRELL/ Supervisory Patent Examiner, Art Unit 2666