CTFR 18/536,895 CTFR 101428 Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Response to Arguments Objections to the Drawings Applicant’s argument and amendment [Sec I – Drawing Objection; pg. 7], filed 4/24/2026 with respect to objection to the drawings have been fully considered and are persuasive. Examiner acknowledges the amendment to the specification [¶0041] correct the previously missing reference to the process 400. The objection to the drawings has been withdrawn. Objections to the Claims Applicant’s arguments and amendments [Sec II – Claim Objections; pg. 7], filed 4/24/2026 with respect to objections to the claims have been fully considered and are persuasive. The amendments to claims 6 & 14 clarify that the background noise is removed using a second filtering algorithm. The amendments to claims 7 & 15 clarify that the registration is performed in response to the transforming process previously recited. The objections to the claims have been withdrawn. Rejections under 35 U.S.C. § 112(b) Applicant’s argument and amendment [Sec IIIA – Rejections under 35 U.S.C. § 112(b); pg. 8], filed 4/24/2026 with respect to the rejection made under 35 U.S.C. § 112(b) have been fully considered and are persuasive. Applicant has amended claim 16 to depend on claim 15 to correct the previously indicated lack of antecedent basis for the limitation of “the residual image”. The rejection made under 35 U.S.C. § 112(b) has been withdrawn. Rejections under 35 U.S.C. § 103 Applicant’s arguments and amendments [Sec IIIB – Rejections under 35 U.S.C. § 103; pg. 8-11], filed 4/24/2026 with respect to the rejections made under 35 U.S.C. § 103 have been fully considered but are not persuasive. The specific reasons are explained below: Argument 1 Applicant argues that Tan et al (“Seal Imprint Verification Using SVM Classifier and Unmatched Key Point Features”, 2021, IEEE), fails to teach, disclose, or otherwise suggest the amended limitation of claims 1, 9 & 17 “ authenticating the extracted seal in a scale invariant domain by at least using a comparison of the extracted seal and a model seal to determine a similarity score based on values of a residual matrix that is calculated for the extracted seal and the model seal ”. While not explicitly argued, applicant makes reference to the normalized Euclidian distance value taught by Tan and whether or not this can be construed as a similarity score. Applicant primarily argues that this Euclidian distance is based on histograms of left and right difference images, and does not disclose that this distance is based on values of a residual matrix calculated for the extracted seal and model seal, citing that Tan et al makes no reference to a residual matrix. The Examiner respectfully disagrees with this assertion. Pertaining to whether a normalized Euclidian distance value can be construed as a similarity score, it should be noted, that under the broadest reasonable interpretation to one of ordinary skill in the art, a similarity score, in the context of image processing, is simply a measure for how similar two or more images are to each other. A Euclidian distance, as disclosed by Tan et al, is used to indicate the difference between two images, particularly through matched key points, which by nature, function as a similarity score, with a smaller distance indicating a greater degree of similarity between two images. Furthermore, with regard to the argument that Tan et al fails to disclose a residual matrix, let alone using it as a basis for determining a similarity score of the extracted and model seal for the amended independent claims, the examiner would like to indicate the broadest reasonable interpretation of a “residual image” to one of ordinary skill in the art. A residual image, is interpreted to be a difference image, which is in line with how a residual image is defined in the specification of the instant application [¶0018, 38-39]. The histograms of the left and right difference images disclosed by Tan et al [Sec III C & D; Figs. 4 & 5], indicate just that, values based on the residual (left and right difference) images, calculated for a reference image (image -1 - – r ) and a query image (image -2 - – q ) [Sec III – C. Difference Images]. The examiner acknowledges that the amended claim language explicitly recites “values of a residual matrix” and not just values of a residual image. One of ordinary skill would recognize that an image is inherently a matrix of pixel values, so the interpretation of the previously indicated residual images (in the form of left and right difference images), inherently function as a residual matrix. Tan et al, further disclose the use of image patches [Sec III – D. Feature Extraction, with particular attention to subsections 2 & 3], for generating the left and right difference images. Here, it can be seen that 8 x 8 image patches (a type of matrix) are taken for each key point in a reference and query image. These patches are then used to generate the histograms (sorted values of features) for each of the left and right distance images. As argued above, Tan et al still teach the amended limitations of claims 1, 9 & 17. Therefore, the applicant’s argument is not persuasive. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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 prior art rejections set forth in this office actions have been revised in view of the aforementioned amendments to clarify the record. Particular attention is drawn to amended claims 1, 6, 7, 9, 14-17. 07-21-aia AIA Claim s 1-3,9-11,15-19 are rejected under 35 U.S.C. 103 as being unpatentable over Rasheed et al (US 2024/0161463 A1) in view of Tan et al (“Seal Imprint Verification Using SVM Classifier and Unmatched Key Point Features”, 2021, IEEE) . Regarding claim 1 , Rasheed et al disclose a system and method for detecting and validating the similarity between two stamps or seals. More specifically, Rasheed et al teach A computer-implemented method, comprising: receiving, by a machine learning model, one more training documents (routine 100 outlines a method for detecting a seal or stamp, where in step 102 a document is received via a neural network [¶0101-104; Fig. 1], with routine 200 outlining the generation of training dataset by intaking a collection of digital stamp patterns at steps 202 & 204 [¶0105-0109; Fig. 2]) and one or more labels indicating whether the one or more training documents include a seal (pair labels showing whether documents contain the same stamp may be labeled one-way (e.g., with a “1”) and pairs showing different or no stamps may be labeled another (e.g., with a “0”) [0072]) ; training, using the one or more training documents and the one or more labels, the machine learning model to perform a task of detecting seals in one or more documents (routine 900 outlines a method of configuring a neural network for detecting a stamp, where images are labeled as positive or negative image pairs in accordance with their stamp labels [¶0138-0140; Fig. 9]) ; receiving, by the trained machine learning model, a document to be authenticated (routine 100 outlines a method for detecting a seal or stamp, where in step 102 a document is received via a neural network [¶0101-104; Fig. 1]) ; detecting, by the trained machine learning model, whether the document contains a seal (in step 104 the input page is configured to recognize a copy-guard digital stamp pattern [¶0102; Fig. 1]) ; in response to detecting the seal, providing the seal extracted by the trained machine learning model for authentication (routine 3300 outline the network training and validation processes for comparing pattern matches [¶0253-263; Fig. 33A]) ; and providing the similarity score as an indication of whether the extracted seal is authentic. (digital image comparator 2700 generates a similarity score 2748 from local feature maps of two stamps [¶0226; Fig. 27]) . Rasheed et al teaches authenticating the extracted stamp or seal and determining a similarity score, but do not teach extracting the seal in the scale invariant domain to do so. Tan et al, however, are analogous art in the same field of endeavor as the present application and also disclose a method for detecting and validating the authenticity of seal in a document. More specifically, Tan et al teach authenticating the extracted seal in a scale invariant domain (Tan et al: seals are authenticated and aligned using a scale-invariant feature transform (SIFT) [Sec. III-A & B; Figs. 1 & 4]) by at least using a comparison of the extracted seal and a model seal to determine a similarity score based on values of a residual matrix that is calculated for the extracted seal and the model seal ; (Tan et al: a normalized Euclidian distance (a similarity score) is calculated between for the values of left and right difference histogram functions from left and right difference images, with a shorter distance indicating a greater degree of similarity [Sec. III-C & D; Fig. 4 & 5]). A Euclidian distance, as disclosed by Tan et al, is used to indicate the difference between two images, particularly through matched key points, which by nature, function as a similarity score, with a smaller distance indicating a greater degree of similarity between two images. A residual image, is interpreted to be a difference image, which is in line with how a residual image is defined in the specification of the instant application [¶0018, 38-39]. The histograms of the left and right difference images disclosed by Tan et al [Sec III C & D; Figs. 4 & 5], indicate just that, values based on the residual (left and right difference) images, calculated for a reference image (image -1 - – r ) and a query image (image -2 - – q ) [Sec III – C. Difference Images]. The examiner acknowledges that the amended claim language explicitly recites “values of a residual matrix” and not just values of a residual image. One of ordinary skill would recognize that an image is inherently a matrix of pixel values, so the interpretation of the previously indicated residual images (in the form of left and right difference images), inherently function as a residual matrix. Tan et al, further disclose the use of image patches [Sec III – D. Feature Extraction, with particular attention to subsections 2 & 3], for generating the left and right difference images. Here, it can be seen that 8 x 8 image patches (a type of matrix) are taken for each key point in a reference and query image. These patches are then used to generate the histograms (sorted values of features) for each of the left and right distance images. Tan et al also disclose how their model, performs more accurately than that of 3 other models provided in the literature of the art [Tan et al: Sec. IV-D; Fig. 7], outperforming Ref[13] (Su et al, “Automatic Seal Imprint Verification Systems Using Edge Difference”, 2019, IEEE Access), which discloses a method for verifying a seal without the implementation of SIFT in feature matching. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication disclosed by Rasheed et al implement SIFT feature matching provided by Tan et al for improved authentication accuracy to arrive at invention of the present application. Regarding claim 2, Rasheed et al in view of Tan et al teach The computer-implemented method of claim 1, (as described above). Rasheed et al also disclose the machine learning model of claim 1 comprising a convolution neural network. More specifically, Rasheed et al teach wherein the machine learning model comprises a convolutional neural network (Rasheed et al: digital image comparator 2700 comprises a first stage utilizing a faster regional proposal convolutional neural network (R-CNN 2704) that includes a region proposal network (RPN 3000) [¶0218; Fig. 27]) . Regarding claim 3, Rasheed et al in view of Tan et al teach The computer-implemented method of claim 1, (as previously described). Rasheed et al also disclose the machine learning model of claim 1 comprising a faster region proposal network. More specifically, Rasheed et al teach wherein the machine learning model comprises a faster regional proposal network (Rasheed et al: digital image comparator 2700 comprises a first stage utilizing a high-performance (i.e. faster) regional proposal convolutional neural network (R-CNN 2704) that includes a region proposal network (RPN 3000) [¶0218; Fig. 27]). Regarding claim 9 , Rasheed et al in view of Tan et al teach A system comprising at least one processor (Rasheed et al: processor(s) 612 [¶0117; Fig. 6]) and at least one memory including instructions, which when executed causes operations (Rasheed et al: volatile (616) and non-volatile (618) memory may store computer-executable instructions 620 to implement embodiments of the disclosed method [¶0118; Fig. 6]) comprising: receiving, by a machine learning model, one or more training documents (Rasheed et al: routine 100 outlines a method for detecting a seal or stamp, where in step 102 a document is received via a neural network [¶0101-104; Fig. 1], with routine 200 outlining the generation of training dataset by intaking a collection of digital stamp patterns at steps 202 & 204 [¶0105-0109; Fig. 2]) and one or more labels indicating whether the one or more training documents include a seal (Rasheed et al: pair labels showing whether documents contain the same stamp may be labeled one-way (e.g., with a “1”) and pairs showing different or no stamps may be labeled another (e.g., with a “0”) [¶0072]) ; training, using the one or more training documents and the one or more labels, the machine learning model to perform a task of detecting seals in one or more documents (Rasheed et al: routine 900 outlines a method of configuring a neural network for detecting a stamp, where images are labeled as positive or negative image pairs in accordance with their stamp labels [¶0138-0140; Fig. 9]) ; receiving, by the trained machine learning model, a document to be authenticated (Rasheed et al: routine 100 outlines a method for detecting a seal or stamp, where in step 102 a document is received via a neural network [¶0101-104; Fig. 1]) ; detecting, by the trained machine learning model, whether the document contains a seal (Rasheed et al: in step 104 the input page is configured to recognize a copy-guard digital stamp pattern [¶0102; Fig. 1]) ; and providing the similarity score as an indication of whether the extracted seal is authentic (Rasheed et al: digital image comparator 2700 generates a similarity score 2748 from local feature maps of two stamps [¶0226; Fig. 27]) . Rasheed et al teach authenticating the extracted stamp or seal and determining a similarity score, but do not teach extracting the seal in the scale invariant domain to do so. Tan et al, however, are analogous art in the same field of endeavor as the present application and also disclose a method for detecting and validating the authenticity of seal in a document. More specifically, Tan et al teach authenticating the extracted seal in a scale invariant domain (Tan et al: seals are authenticated and aligned using a scale-invariant feature transform (SIFT) [Sec. III-A & B; Figs. 1 & 4]) by at least using a comparison of the extracted seal and a model seal to determine a similarity score based on values of a residual matrix that is calculated for the extracted seal and the model seal ; (Tan et al: a normalized Euclidian distance (a similarity score) is calculated between for the values of left and right difference histogram functions from left and right difference images, with a shorter distance indicating a greater degree of similarity [Sec. III-C & D; Fig. 4 & 5]). A Euclidian distance, as disclosed by Tan et al, is used to indicate the difference between two images, particularly through matched key points, which by nature, function as a similarity score, with a smaller distance indicating a greater degree of similarity between two images. A residual image, is interpreted to be a difference image, which is in line with how a residual image is defined in the specification of the instant application [¶0018, 38-39]. The histograms of the left and right difference images disclosed by Tan et al [Sec III C & D; Figs. 4 & 5], indicate just that, values based on the residual (left and right difference) images, calculated for a reference image (image -1 - – r ) and a query image (image -2 - – q ) [Sec III – C. Difference Images]. The examiner acknowledges that the amended claim language explicitly recites “values of a residual matrix” and not just values of a residual image. One of ordinary skill would recognize that an image is inherently a matrix of pixel values, so the interpretation of the previously indicated residual images (in the form of left and right difference images), inherently function as a residual matrix. Tan et al, further disclose the use of image patches [Sec III – D. Feature Extraction, with particular attention to subsections 2 & 3], for generating the left and right difference images. Here, it can be seen that 8 x 8 image patches (a type of matrix) are taken for each key point in a reference and query image. These patches are then used to generate the histograms (sorted values of features) for each of the left and right distance images.Tan et al also disclose how their model, performs more accurately than that of 3 other models provided in the literature of the art [Tan et al: Sec. IV-D; Fig. 7], outperforming Ref[13] (Su et al, “Automatic Seal Imprint Verification Systems Using Edge Difference”, 2019, IEEE Access), which discloses a method for verifying a seal without the implementation of SIFT in feature matching. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication disclosed by Rasheed et al implement SIFT feature matching provided by Tan et al for improved authentication accuracy to arrive at invention of the present application. Regarding claim 10 , Rasheed et al in view of Tan et al teach The system of claim 9, (as described above). Rasheed et al also disclose the machine learning model of claim 9 comprising a convolution neural network. More specifically, Rasheed et al teach wherein the machine learning model comprises a convolutional neural network (Rasheed et al: digital image comparator 2700 comprises a first stage utilizing a faster regional proposal convolutional neural network (R-CNN 2704) that includes a region proposal network (RPN 3000) [¶0218; Fig. 27]) . Regarding claim 11, Rasheed et al in view of Tan et al teach The system of claim 9, (as previously described). Rasheed et al also disclose the machine learning model of claim 9 comprising a faster region proposal network. More specifically, Tan et al teach wherein the machine learning model comprises a faster regional proposal network (Rasheed et al: digital image comparator 2700 comprises a first stage utilizing a (high performance (i.e. faster) regional proposal convolutional neural network (R-CNN 2704) that includes a region proposal network (RPN 3000) [¶0218; Fig. 27]) . Regarding claim 15, Rasheed et al in view of Tan et al teach The system of claim 9 (as previously described). Tan et al also disclose transforming the extracted and model seal using one or more SIFT features and forming a residual image. More specifically, Tan et al teach the system further comprising: transforming the extracted seal and the model seal into the scale invariant domain using one or more scale invariant feature transform (SIFT) features of the extracted seal and the model seal (Tan et al: where seals are aligned using a scale-invariant feature transform (SIFT) [Sec. III-B; Fig. 4]) ; and in response to the transforming, registering, using the one or more scale invariant feature transform (SIFT) features, the transformed, extracted seal and the transformed model seal to form a residual image (Tan et al: left and right difference images indicating a value of similarity [Sec. III-D; Fig. 5]) . Tan et al also disclose how their model, performs more accurately than that of 3 other models provided in the literature of the art [Tan et al: Sec. IV-D; Fig. 7], outperforming Ref[13] (Su et al, “Automatic Seal Imprint Verification Systems Using Edge Difference”, 2019, IEEE Access), which discloses a method for verifying a seal without the implementation of SIFT in feature matching. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication disclosed by Rasheed et al implement SIFT feature matching provided by Tan et al for improved authentication accuracy to arrive at invention of the present application. Regarding claim 16, Rasheed et al in view of Tan et al teach The system of claim 15 (as previously described). Tan et al further disclose a system for authenticating a seal wherein a similarity score based on the residual image is determined. More specifically, Tan et al teach the system further comprising: determining the similarity score based on the residual image (Tan et al: with a normalized Euclidian distance value indicating the difference between left and right difference images indicating a value of similarity [Sec. III-D; Fig. 5]) . Tan et al also disclose that the normalized Euclidian distance was chosen as metric for computing the histogram distance metric (which functions as a similarity score) as it provides a stable support vector machine (SVM) classifier with good performance [Tan et al: Sec. IV-C]. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication disclosed by Rasheed et al in view of Tan et al and utilize the method of computing a similarity score proposed by Tan et al to arrive at the invention of the present application. Regarding claim 17, Rasheed et al teach A non-transitory computer-storage medium including instructions (Rasheed et al: volatile (616) and non-volatile (618) memory may store computer-executable instructions 620 to implement embodiments of the disclosed method [¶0118; Fig. 6]) , which when executed by at least one processor (Rasheed et al: processor(s) 612 [¶0117; Fig. 6]) , causes operations comprising: receiving, by a machine learning model, one or more training documents (Rasheed et al: routine 100 outlines a method for detecting a seal or stamp, where in step 102 a document is received via a neural network [¶0101-104; Fig. 1], with routine 200 outlining the generation of training dataset by intaking a collection of digital stamp patterns at steps 202 & 204 [¶0105-0109; Fig. 2]) and one or more labels indicating whether the one or more training documents include a seal (Rasheed et al: pair labels showing whether documents contain the same stamp may be labeled one-way (e.g., with a “1”) and pairs showing different or no stamps may be labeled another (e.g., with a “0”) [¶0072]) ; training, using the one or more training documents and the one or more labels, the machine learning model to perform a task of detecting seals in one or more documents (Rasheed et al: routine 900 outlines a method of configuring a neural network for detecting a stamp, where images are labeled as positive or negative image pairs in accordance with their stamp labels [¶0138-0140; Fig. 9]) ; receiving, by the trained machine learning model, a document to be authenticated (Rasheed et al: routine 100 outlines a method for detecting a seal or stamp, where in step 102 a document is received via a neural network [¶0101-104; Fig. 1]) ; detecting, by the trained machine learning model, whether the document contains a seal (Rasheed et al: in step 104 the input page is configured to recognize a copy-guard digital stamp pattern [¶0102; Fig. 1]) ; in response to detecting the seal, providing the seal extracted by the trained machine learning model for authentication (routine 3300 outline the network training and validation processes for comparing pattern matches [¶0253-263; Fig. 33A]) ; and providing the similarity score as an indication of whether the extracted seal is authentic (digital image comparator 2700 generates a similarity score 2748 from local feature maps of two stamps [¶0226; Fig. 27]) . Rasheed et al teach authenticating the extracted stamp or seal and determining a similarity score, but do not teach extracting the seal in the scale invariant domain to do so. Tan et al, however, are analogous art in the same field of endeavor as the present application and also disclose a method for detecting and validating the authenticity of seal in a document. More specifically, Tan et al teach authenticating the extracted seal in a scale invariant domain (Tan et al: seals are authenticated and aligned using a scale-invariant feature transform (SIFT) [Sec. III-A & B; Figs. 1 & 4]) by at least using a comparison of the extracted seal and a model seal to determine a similarity score based on values of a residual matrix that is calculated for the extracted seal and the model seal ; (Tan et al: a normalized Euclidian distance (a similarity score) is calculated between for the values of left and right difference histogram functions from left and right difference images, with a shorter distance indicating a greater degree of similarity [Sec. III-C & D; Fig. 4 & 5]). A Euclidian distance, as disclosed by Tan et al, is used to indicate the difference between two images, particularly through matched key points, which by nature, function as a similarity score, with a smaller distance indicating a greater degree of similarity between two images. A residual image, is interpreted to be a difference image, which is in line with how a residual image is defined in the specification of the instant application [¶0018, 38-39]. The histograms of the left and right difference images disclosed by Tan et al [Sec III C & D; Figs. 4 & 5], indicate just that, values based on the residual (left and right difference) images, calculated for a reference image (image -1 - – r ) and a query image (image -2 - – q ) [Sec III – C. Difference Images]. The examiner acknowledges that the amended claim language explicitly recites “values of a residual matrix” and not just values of a residual image. One of ordinary skill would recognize that an image is inherently a matrix of pixel values, so the interpretation of the previously indicated residual images (in the form of left and right difference images), inherently function as a residual matrix. Tan et al, further disclose the use of image patches [Sec III – D. Feature Extraction, with particular attention to subsections 2 & 3], for generating the left and right difference images. Here, it can be seen that 8 x 8 image patches (a type of matrix) are taken for each key point in a reference and query image. These patches are then used to generate the histograms (sorted values of features) for each of the left and right distance images. Tan et al also disclose how their model, performs more accurately than that of 3 other models provided in the literature of the art [Tan et al: Sec. IV-D; Fig. 7], outperforming Ref[13] (Su et al, “Automatic Seal Imprint Verification Systems Using Edge Difference”, 2019, IEEE Access), which discloses a method for verifying a seal without the implementation of SIFT in feature matching. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication disclosed by Rasheed et al implement SIFT feature matching provided by Tan et al for improved authentication accuracy to arrive at invention of the present application. Regarding claim 18, Rasheed et al in view of Tan et al teach The non-transitory computer-storage medium of claim 17, (as described above). Rasheed et al also disclose the machine learning model of claim 9 comprising a convolution neural network. More specifically, Rasheed et al teach wherein the machine learning model comprises a convolutional neural network (Rasheed et al: digital image comparator 2700 comprises a first stage utilizing a faster regional proposal convolutional neural network (R-CNN 2704) that includes a region proposal network (RPN 3000) [¶0218; Fig. 27]) . Regarding claim 19, Rasheed et al in view of Tan et al teach The non-transitory computer-storage medium of claim 17, (as previously described). Rasheed et al also disclose the machine learning model of claim 9 comprising a faster region proposal network. More specifically, Tan et al teach wherein the machine learning model comprises a faster regional proposal network (Rasheed et al: digital image comparator 2700 comprises a first stage utilizing a (faster regional proposal convolutional neural network (R-CNN 2704) that includes a region proposal network (RPN 3000) [¶0218; Fig. 27]) . 07-21-aia AIA Claim s 4-8, 12-14 & 20 are rejected under 35 U.S.C. 103 as being unpatentable over Rasheed et al (US 2024/0161463 A1) in view of Tan et al (“Seal Imprint Verification Using SVM Classifier and Unmatched Key Point Features”, 2021, IEEE), further in view of Sundararam et al (WO 2022/035942 A1) . Regarding claim 4 , Rasheed et al in view of Tan et al teach The computer-implemented method of claim 1 (as previously described) , but does not disclose preprocessing to remove background noise from the extracted seal. Sundararam et al, however, are analogous art in the same field of endeavor as the present application and also disclose a method authenticating a seal by preprocessing to remove background noise from the extracted seal. More specifically, Sundararam et al teach wherein the authenticating further comprises: preprocessing the extracted seal to remove background noise from the extracted seal (Sundararam et al: image pre-processor 1214 in Fig. 12 can apply a Gaussian noise filter on candidate images to reduce noise [pg. 90; ln. 23-24 & pg. 91; ln. 1-11]) . Thus, in accordance with KSR rationales (see MPEP § 2143), the prior art includes all of the claimed elements in the present application, with the only difference being the lack of combination. Furthermore, one of ordinary skill in the art could have easily combined the elements by known methods and that each element would merely perform the same function as it does separately. For example, the inclusion of a Gaussian filter to remove background noise would provide for the extraction of a seal that would readily reduce noise and improve the overall accuracy. Finally, one of ordinary skill in the art would recognize that the result of the combination would be predictable, since the use of Gaussian filtering would merely reduce the background noise resulting in an improved process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication proposed by Rasheed et al in view of Tan et al and implement the reduction of background noise using a Gaussian filter proposed by Sundaram et al to arrive at the invention of the present application. Regarding claim 5 , Rasheed et al in view of Tan et al, further in view of Sundararam et al teach The computer-implemented method of claim 4, (as described above). Sundararam et al also disclose a method authenticating a seal by preprocessing to remove background noise from the extracted seal. More specifically, Sundararam et al teach wherein the background noise is removed using a first filtering algorithm if the extracted seal is in color (Sundararam et al: image pre-processor 1214 in Fig. 12 can convert the candidate image to grayscale and apply a Gaussian noise filter to reduce noise or smooth variations [pg. 90; ln. 23-24 & pg. 91; ln. 1-11]) . Thus, in accordance with KSR rationales (see MPEP § 2143), the prior art includes all of the claimed elements in the present application, with the only difference being the lack of combination. Furthermore, one of ordinary skill in the art could have easily combined the elements by known methods and that each element would merely perform the same function as it does separately. For example, the inclusion of a Gaussian filter to remove background noise would provide for the extraction of a seal that would readily reduce noise and improve the overall accuracy. The conversion of the image to grayscale prior to Gaussian filtering simply reduces image dimensionality and aids processing efficiency. Finally, one of ordinary skill in the art would recognize that the result of the combination would be predictable, since the conversion to grayscale and use of Gaussian filtering would merely reduce the background noise resulting in an improved process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication proposed by Rasheed et al in view of Tan et al and implement the conversion to grayscale and reduction of background noise using a Gaussian filter proposed by Sundaram et al to arrive at the invention of the present application. Regarding claim 6 , Rasheed et al in view of Tan et al, further in view of Sudararam et al teach The computer-implemented method of claim 4, (as previously described). Sundararam et al also disclose removing background noise via a second filtering algorithm if the extracted seal is in gray scale. More specifically, Sundararam et al teach wherein the background noise is removed using a second filtering algorithm if the extracted seal is in gray scale (Sundararam et al: image pre-processor 1214 in Fig. 12 can apply a Gaussian noise filter on candidate images to reduce noise [pg. 90; ln. 23-24 & pg. 91; ln. 1-11]) . Thus, in accordance with KSR rationales (see MPEP § 2143), the prior art includes all of the claimed elements in the present application, with the only difference being the lack of combination. Furthermore, one of ordinary skill in the art could have easily combined the elements by known methods and that each element would merely perform the same function as it does separately. For example, the inclusion of a Gaussian filter to remove background noise would provide for the extraction of a seal that would readily reduce noise and improve the overall accuracy. Finally, one of ordinary skill in the art would recognize that the result of the combination would be predictable, since the use of Gaussian filtering would merely reduce the background noise resulting in an improved process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication proposed by Rasheed et al in view of Tan et al and implement the reduction of background noise for a gray scale seal using a Gaussian filter proposed by Sundaram et al to arrive at the invention of the present application. Regarding claim 7 , Rasheed et al in view of Tan et al, further in view of Sudararam et al teach The computer-implemented method of claim 4 (as previously described). Tan et al also disclose transforming the extracted and model seal using one or more SIFT features and forming a residual image. More specifically, Tan et al teach the method further comprising: transforming the extracted seal and the model seal into the scale invariant domain using one or more scale invariant feature transform (SIFT) features of the extracted seal and the model seal (Tan et al: where seals are aligned using a scale-invariant feature transform (SIFT) [Sec. III-B; Fig. 4]) ; and in response to the transforming, registering, using the one or more scale invariant feature transform (SIFT) features, the transformed, extracted seal and the transformed model seal to form a residual image (Tan et al: left and right difference images indicating a value of similarity [Sec. III-D; Fig. 5]) . Tan et al also disclose how their model, performs more accurately than that of 3 other models provided in the literature of the art [Tan et al: Sec. IV-D; Fig. 7], outperforming Ref[13] (Su et al, “Automatic Seal Imprint Verification Systems Using Edge Difference”, 2019, IEEE Access), which discloses a method for verifying a seal without the implementation of SIFT in feature matching. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication disclosed by Rasheed et al implement SIFT feature matching provided by Tan et al for improved authentication accuracy to arrive at invention of the present application. Regarding claim 8 , Rasheed et al in view of Tan et al, further in view of Sudararam et al teach The computer-implemented method of claim 7 (as previously described). Tan et al further disclose a method of authenticating a seal wherein a similarity score based on the residual image is determined. More specifically, Tan et al teach the method further comprising: determining the similarity score based on the residual image (Tan et al: with a normalized Euclidian distance value indicating the difference between left and right difference images indicating a value of similarity [Sec. III-D; Fig. 5]) . Tan et al also disclose that the normalized Euclidian distance was chosen as metric for computing the histogram distance metric (which functions as a similarity score) as it provides a stable support vector machine (SVM) classifier with good performance [Tan et al: Sec. IV-C]. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication disclosed by Rasheed et al in view of Tan et al, further in view of Sudararam et al and utilize the method of computing a similarity score proposed by Tan et al to arrive at the invention of the present application. Regarding claim 12, Rasheed et al in view of Tan et al teach The system of claim 9 (as previously described) , but does not disclose preprocessing to remove background noise from the extracted seal. Sundararam et al, however, are analogous art in the same field of endeavor as the present application and also disclose a method authenticating a seal by preprocessing to remove background noise from the extracted seal. More specifically, Sundararam et al teach wherein the authenticating further comprises: preprocessing the extracted seal to remove background noise from the extracted seal (Sundararam et al: image pre-processor 1214 in Fig. 12 can apply a Gaussian noise filter on candidate images to reduce noise [pg. 90; ln. 23-24 & pg. 91; ln. 1-11]) . Thus, in accordance with KSR rationales (see MPEP § 2143), the prior art includes all of the claimed elements in the present application, with the only difference being the lack of combination. Furthermore, one of ordinary skill in the art could have easily combined the elements by known methods and that each element would merely perform the same function as it does separately. For example, the inclusion of a Gaussian filter to remove background noise would provide for the extraction of a seal that would readily reduce noise and improve the overall accuracy. Finally, one of ordinary skill in the art would recognize that the result of the combination would be predictable, since the use of Gaussian filtering would merely reduce the background noise resulting in an improved process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication proposed by Rasheed et al in view of Tan et al and implement the reduction of background noise using a Gaussian filter proposed by Sundaram et al to arrive at the invention of the present application. Regarding claim 13, Rasheed et al in view of Tan et al, further in view of Sundararam et al teach The system of claim 12 (as described above). Sundararam et al also disclose a method authenticating a seal by preprocessing to remove background noise from the extracted seal. More specifically, Sundararam et al teach wherein the background noise is removed using a first filtering algorithm if the extracted seal is in color (Sundararam et al: image pre-processor 1214 in Fig. 12 can convert the candidate image to grayscale and apply a Gaussian noise filter to reduce noise or smooth variations [pg. 90; ln. 23-24 & pg. 91; ln. 1-11]) . Thus, in accordance with KSR rationales (see MPEP § 2143), the prior art includes all of the claimed elements in the present application, with the only difference being the lack of combination. Furthermore, one of ordinary skill in the art could have easily combined the elements by known methods and that each element would merely perform the same function as it does separately. For example, the inclusion of a Gaussian filter to remove background noise would provide for the extraction of a seal that would readily reduce noise and improve the overall accuracy. The conversion of the image to grayscale prior to Gaussian filtering simply reduces image dimensionality and aids processing efficiency. Finally, one of ordinary skill in the art would recognize that the result of the combination would be predictable, since the conversion to grayscale and use of Gaussian filtering would merely reduce the background noise resulting in an improved process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication proposed by Rasheed et al in view of Tan et al and implement the conversion to grayscale and reduction of background noise using a Gaussian filter proposed by Sundaram et al to arrive at the invention of the present application. Regarding claim 14, Rasheed et al in view of Tan et al, further in view of Sudararam et al teach The system of claim 12, (as previously described). Sundararam et al also disclose removing background noise via a second filtering algorithm if the extracted seal is in gray scale. More specifically, Sundararam et al teach wherein the background noise is removed using a second filtering algorithm if the extracted seal is in gray scale (Sundararam et al: image pre-processor 1214 in Fig. 12 can apply a Gaussian noise filter on candidate images to reduce noise [pg. 90; ln. 23-24 & pg. 91; ln. 1-11]) . Thus, in accordance with KSR rationales (see MPEP § 2143), the prior art includes all of the claimed elements in the present application, with the only difference being the lack of combination. Furthermore, one of ordinary skill in the art could have easily combined the elements by known methods and that each element would merely perform the same function as it does separately. For example, the inclusion of a Gaussian filter to remove background noise would provide for the extraction of a seal that would readily reduce noise and improve the overall accuracy. Finally, one of ordinary skill in the art would recognize that the result of the combination would be predictable, since the use of Gaussian filtering would merely reduce the background noise resulting in an improved process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication proposed by Rasheed et al in view of Tan et al and implement the reduction of background noise for a gray scale seal using a Gaussian filter proposed by Sundaram et al to arrive at the invention of the present application. Regarding claim 20, Rasheed et al in view of Tan et al teach The non-transitory computer-storage medium of claim 17 (as previously described) , but does not disclose preprocessing to remove background noise from the extracted seal. Sundararam et al, however, are analogous art in the same field of endeavor as the present application and also disclose a method authenticating a seal by preprocessing to remove background noise from the extracted seal. More specifically, Sundararam et al teach wherein the authenticating further comprises: preprocessing the extracted seal to remove background noise from the extracted seal (Sundararam et al: image pre-processor 1214 in Fig. 12 can apply a Gaussian noise filter on candidate images to reduce noise [pg. 90; ln. 23-24 & pg. 91; ln. 1-11]) . Thus, the prior art includes all of the claimed elements in the present application, with the only difference being the lack of combination. Furthermore, one of ordinary skill in the art could have easily combined the elements by known methods and that each element would merely perform the same function as it does separately. For example, the inclusion of a Gaussian filter to remove background noise would provide for the extraction of a seal that would readily reduce noise and improve the overall accuracy. Finally, in accordance with KSR rationales (see MPEP § 2143), one of ordinary skill in the art would recognize that the result of the combination would be predictable, since the use of Gaussian filtering would merely reduce the background noise resulting in an improved process. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to take the method of seal authentication proposed by Rasheed et al in view of Tan et al and implement the reduction of background noise using a Gaussian filter proposed by Sundaram et al to arrive at the invention of the present application. Conclusion 07-39 AIA THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michael M. Sofroniou whose telephone number is (571)272-0287. The examiner can normally be reached M-F: 8:30 AM - 5:00 PM. 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 M. 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. /MICHAEL M SOFRONIOU/Examiner, Art Unit 2661 /JOHN VILLECCO/Supervisory Patent Examiner, Art Unit 2661 Application/Control Number: 18/536,895 Page 2 Art Unit: 2661 Application/Control Number: 18/536,895 Page 3 Art Unit: 2661 Application/Control Number: 18/536,895 Page 4 Art Unit: 2661 Application/Control Number: 18/536,895 Page 5 Art Unit: 2661 Application/Control Number: 18/536,895 Page 6 Art Unit: 2661 Application/Control Number: 18/536,895 Page 7 Art Unit: 2661 Application/Control Number: 18/536,895 Page 8 Art Unit: 2661 Application/Control Number: 18/536,895 Page 9 Art Unit: 2661 Application/Control Number: 18/536,895 Page 10 Art Unit: 2661 Application/Control Number: 18/536,895 Page 11 Art Unit: 2661 Application/Control Number: 18/536,895 Page 12 Art Unit: 2661 Application/Control Number: 18/536,895 Page 13 Art Unit: 2661 Application/Control Number: 18/536,895 Page 14 Art Unit: 2661 Application/Control Number: 18/536,895 Page 15 Art Unit: 2661 Application/Control Number: 18/536,895 Page 16 Art Unit: 2661 Application/Control Number: 18/536,895 Page 17 Art Unit: 2661 Application/Control Number: 18/536,895 Page 18 Art Unit: 2661 Application/Control Number: 18/536,895 Page 19 Art Unit: 2661 Application/Control Number: 18/536,895 Page 20 Art Unit: 2661 Application/Control Number: 18/536,895 Page 22 Art Unit: 2661 Application/Control Number: 18/536,895 Page 23 Art Unit: 2661 Application/Control Number: 18/536,895 Page 24 Art Unit: 2661 Application/Control Number: 18/536,895 Page 25 Art Unit: 2661
Prosecution Insights