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 .
Examiner’s Note
For applicant’s benefit, portions of the cited reference(s) have been cited to aid in the review of the rejection(s). While every attempt has been made to be thorough and consistent within the rejection it is noted that the PRIOR ART MUST BE CONSIDERED IN ITS ENTIRETY, including disclosures that teach away from the claims. See MPEP 2141.02 VI.
“The use of patents as references is not limited to what the patentees describe as their own inventions or to the problems with which they are concerned. They are part of the literature of the art, relevant for all they contain.” In re Heck, 699 F.2d 1331, 1332-33, 216 USPQ 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1009, 158 USPQ 275, 277 (CCPA 1968)). A reference may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art, including non-preferred embodiments. Merck & Co. v.Biocraft Laboratories, 874 F.2d 804, 10 USPQ2d 1843 (Fed. Cir.), cert. denied, 493 U.S. 975 (1989). See also Upsher-Smith Labs. v. Pamlab, LLC, 412 F.3d 1319, 1323, 75 USPQ2d 1213, 1215 (Fed. Cir. 2005) See MPEP 2123.
Claim Objections
Claim(s) 6 is/are objected to because of the following informalities:
Claim 6 recites “a multi-layer convolutional neural network” which is suggested to be amended to “[[a]]the multi-layer convolutional neural network”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim(s) 1-10 is/are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 1, claim 1 recites:
“performing forward simulation on the existing diseases data of different types” which renders the claim indefinite, such that the scope of the claim would not be reasonably ascertainable by one of ordinary skill in the art;
“for any type of disease data, performing forward simulation on different center frequencies of the transmitting antenna of the ground penetrating radar to obtain a simulated center frequency of the transmitting antenna” which renders the claim indefinite, such that the scope of the claim would not be reasonably ascertainable by one of ordinary skill in the art;
“the transmitting antenna of the ground penetrating radar” which lacks antecedent basis;
“carrying out coring verification to determine a ground penetrating radar test image” which renders the claim indefinite, such that the scope of the claim would not be reasonably ascertainable by one of ordinary skill in the art. It appears that the step is carried out in order to verify the ground penetrating radar test image, and not to determine;
“the measured image data” which lacks antecedent basis, such that the scope of the claim would not be reasonably ascertainable by one of ordinary skill in the art;
“the autonomous learning features” which lacks antecedent basis.
Claim 2 recites “the existing diseases data of different types” which renders the claim indefinite, such that the scope of the claim would not be reasonably ascertainable by one of ordinary skill in the art.
Claim 6 recites “summarizing it” which renders the claim indefinite, such that the scope of the claim would not be reasonably ascertainable by one of ordinary skill in the art.
Claim 8 recites “the recognition result” which lacks antecedent basis.
Claim 10 is rejected for similar reason(s) as claim 1.
Claim(s) 2-10 are additionally rejected by virtue of their dependence on claim 1.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 4, and 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (WO 2021/083394 A1 “ZHANG”), in view of Li et al. (US 2021/0396842 A1 “LI”), and in view of Troxler et al. (US 2011/0066398 A1 “TROXLER”), and further in view of Wang et al. (US 2010/0141810 A1 “WANG”).
Examiner’s note: For purpose of citation, the Examiner is using US 2022/0350015 A1 which is US equivalence of WO 2021/083394 A1 “ZHANG”.
Regarding claim 1, ZHANG discloses (Examiner’s note: What ZHANG does not disclose is ) a method for artificial intelligence recognition of ground penetrating radar images, comprising:
collecting data on different pavements using the during the on-site data collection, a sampling spacing is <15 cm, an antenna frequency is >1.6 GHz, and a sampling frequency is 10 to 20 times an antenna central frequency. The GPR image corresponding to these labels is used as a ground truth of the moisture damage to determine a feature of the moisture damage [0110-0111])
based on the ground penetrating radar field test data, selecting a typical disease image obtain an initial GPR image dataset of moisture damage: After preprocessing GPR data corresponding to the damage region, specify a plot scale of the GPR image, intercept the GPR image according to a length of 5 m to 6 m, construct initial GPR image datasets of the moisture damage, a bridge joint, and a normal asphalt pavement, and label respective features of the moisture damage, the bridge joint, and the normal asphalt pavement [0112])
establishing a ground penetrating radar graph library based on the the resolution of the initial GPR image dataset of the moisture damage is scaled directly to 224×224 to obtain the BD dataset [0127])
obtaining the measured image data of targets collected by the ground penetrating radar, and determining the autonomous learning features through a multi-layer convolutional neural network (inputting the BD dataset obtained in step 2 into the recognition model, performing operation by the recognition model [0129]); (the mixed deep learning model is composed of two parts: ResNet50 for feature extraction, and YOLO V2 framework for target detection [0131])
determining an initial type and initial location information of a target disease based on the manual features, the autonomous learning features, and the ground penetrating radar graph library (the mixed deep learning model divides image data obtained in step 2 into a training set and a test set with allocation ratios being 70% and 30% respectively. The designed mixed deep learning model is specifically trained by using a TL method. The model uses the MSE method as the loss function, and the quantity of anchor boxes is obtained by classifying heights/widths of a moisture damage and a bridge joint in a sample set according to the K-means method [0135]); (the output result is the image with the label name of the target and the position (x, y, w, h) of the candidate box BBox corresponding to the target [0059])
ZHANG further discloses to output a moisture damage result [0137].
In a same or similar field of endeavor, LI teaches simulating dielectric constant models of underground engineering targets of a plurality of background media, shapes, sizes, and distributions [0056]. The recognition method is mainly aimed at concealed abnormal bodies or defects, including concrete, reinforcing bar, and structural defects of underground engineering. Each type of target body is assigned with a unique type identification code, and can also be applied to geological abnormal bodies such as fractures, karst caves, and faults, pavement defects such as pavement cracks and subsidence, and various underground pipelines [0220]. Furthermore, LI teaches that the computer simulated data set is composed of ground penetrating radar data with a plurality of frequencies and a corresponding concealed target tag drawing, which are input into the deep learning model together for training the deep learning model [0231].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of LI, because doing so would improve detection of structural, internal, and surface defects, as recognized by LI. In addition, both of the prior art references, ZHANG and LI, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, ground penetrating radar signals.
ZHANG, as modified by LI, discloses the invention as set forth herein, but does not disclose carrying out coring verification to determine a ground penetrating radar test image; and identifying the initial type and the initial location information of the target disease using a committee discrimination method to determine the final type and final location information of the target disease.
In a same or similar field of endeavor, TROXLER teaches that the measuring device can be associated with a communications module operable to receive predetermined distances, positions or other suitable coordinate information for use in determining locations to obtain core samples from material 1500. Typically, the nondestructive measurement is made before the core is removed, and the core is drilled on or near the measurement spot [0127].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of TROXLER, because doing so would allow for acceptance or rejection of prior measurement data, as recognized by TROXLER. In addition, both of the prior art references, ZHANG and TROXLER, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, ground penetrating radar technique(s).
ZHANG, as modified by LI and TROXLER, discloses the invention as set forth above, but does not disclose identifying the initial type and the initial location information of the target disease using a committee discrimination method to determine the final type and final location information of the target disease.
In a same or similar field of endeavor, WANG teaches that N classification outcomes form a committee of classifiers to vote and determine whether this pixel (sensing element) is a bad pixel or not. Different voting schemes may be employed to allow determination of the pixel (sensing element) being defective by one or more individual classifiers be voted into determination of the pixel (sensing element) being a bad pixel. Said in other words, the bad pixel candidate is voted into the bad pixel according to the voting scheme [0026].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of WANG, because doing so would improve accuracy of the classification, as recognized by WANG. In addition, both of the prior art references, ZHANG and WANG, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, classification of sensor images.
Regarding claim 4, ZHANG/ LI/ TROXLER/ WANG discloses the method for artificial intelligence recognition of ground penetrating radar images according to claim 1, wherein establishing a ground penetrating radar graph library based on the simulated ground penetrating radar image and the ground penetrating radar test image comprises: reconstructing and expanding the simulated ground penetrating radar image and the ground penetrating radar test image using data augmentation technology and transfer learning technology to establish the ground penetrating radar graph library (the mixed deep learning model divides an image obtained in step 2 into a training set and a test set with allocation ratios being 70% and 30% respectively. The designed mixed deep learning model is specifically trained by using a TL (transfer learning) method [ZHANG 0179]).
Regarding claim 10, ZHANG discloses an apparatus for artificial intelligence recognition of ground penetrating radar images for use in the method for artificial intelligence recognition of ground penetrating radar images according to claim 1, comprising:
a manual feature determination module configured to collect data on different pavements using the during the on-site data collection, a sampling spacing is <15 cm, an antenna frequency is >1.6 GHz, and a sampling frequency is 10 to 20 times an antenna central frequency. The GPR image corresponding to these labels is used as a ground truth of the moisture damage to determine a feature of the moisture damage [0110-0111])
a test image determination module configured to, based on the ground penetrating radar field test data, select a typical disease image obtain an initial GPR image dataset of moisture damage: After preprocessing GPR data corresponding to the damage region, specify a plot scale of the GPR image, intercept the GPR image according to a length of 5 m to 6 m, construct initial GPR image datasets of the moisture damage, a bridge joint, and a normal asphalt pavement, and label respective features of the moisture damage, the bridge joint, and the normal asphalt pavement [0112])
a graph library construction module configured to establish a ground penetrating radar graph library based on the the resolution of the initial GPR image dataset of the moisture damage is scaled directly to 224×224 to obtain the BD dataset [0127])
an autonomous learning feature determination module configured to obtain the measured image data of targets collected by the ground penetrating radar, and determine the autonomous learning features through a multi-layer convolutional neural network (inputting the BD dataset obtained in step 2 into the recognition model, performing operation by the recognition model [0129]); (the mixed deep learning model is composed of two parts: ResNet50 for feature extraction, and YOLO V2 framework for target detection [0131])
a target disease initial information determination module configured to determine an initial type and initial location information of a target disease based on the manual features, the autonomous learning features, and the ground penetrating radar graph library (the mixed deep learning model divides image data obtained in step 2 into a training set and a test set with allocation ratios being 70% and 30% respectively. The designed mixed deep learning model is specifically trained by using a TL method. The model uses the MSE method as the loss function, and the quantity of anchor boxes is obtained by classifying heights/widths of a moisture damage and a bridge joint in a sample set according to the K-means method [0135]); (the output result is the image with the label name of the target and the position (x, y, w, h) of the candidate box BBox corresponding to the target [0059])
ZHANG further discloses to output a moisture damage result [0137].
In a same or similar field of endeavor, LI teaches simulating dielectric constant models of underground engineering targets of a plurality of background media, shapes, sizes, and distributions [0056]. The recognition method is mainly aimed at concealed abnormal bodies or defects, including concrete, reinforcing bar, and structural defects of underground engineering. Each type of target body is assigned with a unique type identification code, and can also be applied to geological abnormal bodies such as fractures, karst caves, and faults, pavement defects such as pavement cracks and subsidence, and various underground pipelines [0220]. Furthermore, LI teaches that the computer simulated data set is composed of ground penetrating radar data with a plurality of frequencies and a corresponding concealed target tag drawing, which are input into the deep learning model together for training the deep learning model [0231].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of LI, because doing so would improve detection of structural, internal, and surface defects, as recognized by LI.
ZHANG, as modified by LI, discloses the invention as set forth herein, but does not disclose to carry out coring verification to determine a ground penetrating radar test image; and a target disease final information determination module configured to identify the initial type and the initial location information of the target disease using a committee discrimination method to determine the final type and final location information of the target disease.
In a same or similar field of endeavor, TROXLER teaches that the measuring device can be associated with a communications module operable to receive predetermined distances, positions or other suitable coordinate information for use in determining locations to obtain core samples from material 1500. Typically, the nondestructive measurement is made before the core is removed, and the core is drilled on or near the measurement spot [0127].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of TROXLER, because doing so would allow for acceptance or rejection of prior measurement data, as recognized by TROXLER.
ZHANG, as modified by LI and TROXLER, discloses the invention as set forth above, but does not disclose a target disease final information determination module configured to identify the initial type and the initial location information of the target disease using a committee discrimination method to determine the final type and final location information of the target disease.
In a same or similar field of endeavor, WANG teaches that N classification outcomes form a committee of classifiers to vote and determine whether this pixel (sensing element) is a bad pixel or not. Different voting schemes may be employed to allow determination of the pixel (sensing element) being defective by one or more individual classifiers be voted into determination of the pixel (sensing element) being a bad pixel. Said in other words, the bad pixel candidate is voted into the bad pixel according to the voting scheme [0026].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of WANG, because doing so would improve accuracy of the classification, as recognized by WANG.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over ZHANG, in view of LI, and TROXLER, and WANG, and further in view of Tsokos et al. (US 10,677,914 B1 “TSOKOS”).
Regarding claim 2, ZHANG/ LI/ TROXLER/ WANG discloses the method for artificial intelligence recognition of ground penetrating radar images according to claim 1,
In a same or similar field of endeavor, TSOKOS teaches that two-dimensional synthetic models were created using the FDTD gprMax code [col. 4, lines 31-32].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of TSOKOS, because doing so would improve generation of GPR signals and simulations, as recognized by TSOKOS. In addition, both of the prior art references, ZHANG and TSOKOS, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, ground penetrating radar signals.
Claim(s) 3 and 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over ZHANG, in view of LI, and TROXLER, and WANG, and further in view of LaBarca et al. (US 2017/0323480 A1 “LABARCA”).
Regarding claim 3, ZHANG/ LI/ TROXLER/ WANG discloses the method for artificial intelligence recognition of ground penetrating radar images according to claim 1,
In a same or similar field of endeavor, LABARCA teaches that GPR systems are often used to examine things such walls, ceilings, etc., and structures such as bridges, tunnels, trees, poles, beams and other structures made of wood, concrete, masonry, natural or artificial materials, etc. A GPR system is used to detect something hidden behind a surface, even if the something is not necessarily a physical object, as GPR systems are also used to detect, for example and without limitation, voids, or defects, or texture changes in a variety of materials and situations [0056].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of LABARCA, because doing so would provide an effective and easy technique to allow for inspection of hidden surroundings and remodeling of existing structures, as recognized by LABARCA. In addition, both of the prior art references, ZHANG and LABARCA, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, ground penetrating radar.
Regarding claim 5, ZHANG/ LI/ TROXLER/ WANG discloses the method for artificial intelligence recognition of ground penetrating radar images according to claim 1, wherein the ground penetrating radar graph library includes images of non-diseases (obtain an initial GPR image dataset of moisture damage: After preprocessing GPR data corresponding to the damage region, specify a plot scale of the GPR image, intercept the GPR image according to a length of 5 m to 6 m, construct initial GPR image datasets of the moisture damage, a bridge joint, and a normal asphalt pavement, and label respective features of the moisture damage, the bridge joint, and the normal asphalt pavement [ZHANG 0112]),
In a same or similar field of endeavor, LABARCA teaches that GPR systems are often used to examine things such walls, ceilings, etc., and structures such as bridges, tunnels, trees, poles, beams and other structures made of wood, concrete, masonry, natural or artificial materials, etc. A GPR system is used to detect something hidden behind a surface, even if the something is not necessarily a physical object, as GPR systems are also used to detect, for example and without limitation, voids, or defects, or texture changes in a variety of materials and situations [0056].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of LABARCA, because doing so would provide an effective and easy technique to allow for inspection of hidden surroundings and remodeling of existing structures, as recognized by LABARCA.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over ZHANG, in view of LI, and TROXLER, and WANG, and further in view of Toth et al. (US 2020/0394784 A1 “TOTH”).
Regarding claim 7, ZHANG/ LI/ TROXLER/ WANG discloses the method for artificial intelligence recognition of ground penetrating radar images according to claim 1,
In a same or similar field of endeavor, TOTH teaches that the data management component 120 manages pre-assessed image data 155 used for training or validation purposes. Pre-assessed image data 155 comprises images and associated data thereof, including metadata and annotations. The images in pre-assessed image data 155 may include, for example, client-provided historical data, proprietary data, and/or publicly available data. The metadata and annotations may be supplied by human inspectors or generated automatically (e.g. time and location where the image was captured), and may include information regarding the identity of one or more infrastructure features depicted in the image, and location data indicating the geographical location of each infrastructure feature. The associated data also includes the classification of the type, severity and/or other characteristics of one or more defects in the feature(s) shown in the image, and/or a remediation recommendation in regards to the defect(s) [0040].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of TOTH, because doing so would improve detection accuracy and classification automation, as recognized by TOTH. In addition, both of the prior art references, ZHANG and TOTH, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, artificial intelligence (AI) based system for detecting defects in infrastructure.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over ZHANG, in view of LI, and TROXLER, and WANG, and further in view of Krishnan et al. (US 2021/0326660 A1 “KRISHNAN”).
Regarding claim 8, ZHANG/ LI/ TROXLER/ WANG discloses the method for artificial intelligence recognition of ground penetrating radar images according to claim 1, wherein identifying the initial type and the initial location information of the target disease using a committee discrimination method to determine the final type and final location information of the target disease comprises: N classification outcomes form a committee of classifiers to vote and determine whether this pixel (sensing element) is a bad pixel or not. Different voting schemes may be employed to allow determination of the pixel (sensing element) being defective by one or more individual classifiers be voted into determination of the pixel (sensing element) being a bad pixel. Said in other words, the bad pixel candidate is voted into the bad pixel according to the voting scheme [WANG 0026], cited and incorporated in the rejection of claim 1).
In a same or similar field of endeavor, KRISHNAN teaches cross entropy, self-supervised contrastive loss, and supervised contrastive loss. In particular, the cross entropy loss (shown generally at FIG. 2A) uses labels and a softmax loss to train a model while the self-supervised contrastive loss (shown generally at FIG. 2B) uses a contrastive loss and data augmentations to learn representations about classes [0028]. Furthermore, KRISHNAN teaches that the cross-entropy loss is likely the most widely used loss function for supervised learning. It is naturally defined as the KL-divergence between two discrete distributions [0003].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of KRISHNAN, because doing so would enable contrastive learning to occur simultaneously across multiple training examples, as recognized by KRISHNAN. In addition, both of the prior art references, ZHANG and KRISHNAN, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, deep learning for classification.
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over ZHANG, in view of LI, and TROXLER, and WANG, and KRISHNAN, and further in view of Savvides et al. (US 2019/0279091 A1 “SAVVIDES”).
Regarding claim 9, ZHANG/ LI/ TROXLER/ WANG discloses the method for artificial intelligence recognition of ground penetrating radar images according to claim 8, wherein the plurality of discrimination methods includes Softmax discrimination method, cross entropy, self-supervised contrastive loss, and supervised contrastive loss. In particular, the cross entropy loss (shown generally at FIG. 2A) uses labels and a softmax loss to train a model while the self-supervised contrastive loss (shown generally at FIG. 2B) uses a contrastive loss and data augmentations to learn representations about classes [KRISHNAN 0028], cited and incorporated in the rejection of claim 8. The cross-entropy loss is likely the most widely used loss function for supervised learning. It is naturally defined as the KL-divergence between two discrete distributions [KRISHNAN 0003], cited and incorporated in the rejection of claim 8).
In a same or similar field of endeavor, SAVVIDES teaches that constrastive loss and the Triplet loss replace the Softmax loss with losses which focus on learning a discriminative embedding while trying to minimize intra-class variation in the learned features. This is accomplished by sampling training pairs or triplet sets which leads to expensive hard-sample mining in large-scale applications [0004].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of ZHANG to include the teachings of SAVVIDES, because doing so would allow for simultaneous optimization of discrimination and improve data processing, as recognized by SAVVIDES. In addition, both of the prior art references, ZHANG and SAVVIDES, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, training of deep neural networks for classification.
Allowable Subject Matter
Claim(s) 6 would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
The closest reference ZHANG discloses a method for detecting a moisture damage on an asphalt pavement based on adaptive selection of a penetrating radar (GPR) image grayscale, which includes obtaining a moisture damage GPR image dataset through asphalt pavement investigation by using a ground GPR, where a GPR image with an appropriate plot scale is selected according to an adaptive GPR image selection method; adjusting image resolution, specifically, scaling a resolution of an initial GPR image dataset of a damage directly to 224×224 to obtain a BD dataset; inputting the dataset into a recognition model, specifically, inputting the BD dataset obtained into the recognition model, performing operation by the recognition model, and outputting a moisture damage result.
Furthermore, WANG discloses a method for bad pixel classification for an image sensor having a plurality of sensing elements. The method includes capturing a plurality of images using the image sensor, determining based on a pre-determined criterion, using an image of the plurality of images and a threshold value selected from one or more pre-determined threshold values, whether a sensing element in the image sensor is defective to generate a vote, wherein a threshold parameter associated with the pre-determined criterion is set to the threshold value, tallying the vote to generate a voting count by performing iterations of the determining step using different images of the plurality of images and different threshold values of the one or more pre-determined threshold values, and classifying the sensing element as a bad pixel if the voting count exceeds a pre-determined classification threshold.
However, Applicant’s claim also encompasses an invention that the prior art does not disclose, teach, or otherwise render obvious. Neither ZHANG nor WANG anticipates or renders fairly obvious, alone, or in combination, to teach all the additional limitations as cited in claim 6, within the context of Applicant' s claimed invention as a whole, that is, “wherein obtaining the measured image data of targets collected by the ground penetrating radar, and determining the autonomous learning features through a multi-layer convolutional neural network comprises: determining a feature layer and generating a candidate region box by subjecting the measured image data of the target to a pre-constructed region proposal network (RPN) structure based on multi-layer feature fusion in the multi-layer convolutional neural network; and performing a non-negative maximum suppression operation on the candidate region box and summarizing it to determine the autonomous learning feature” as recited in claim 6.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Jazayeri et al. (US 2020/0003892 A1) is considered pertinent art for the disclosure overall, and in particular the details of targeting the dimensions and infilling material of buried objects. The method is useful in situations where clear isolated diffraction hyperbolas indicate the presence of an underground object, but the object's dimensions and filling may be unknown. The present invention acquires GPR data and applies advanced numerical methods to get the depth and size of the underground object in a very accurate manner. An embodiment of the invention includes five main steps: GPR data processing, ray-based analysis to set a good initial model, 3D to 2D transformation of data, effective SW estimation, and FWI.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HAILEY R LE whose telephone number is (571)272-4910. The examiner can normally be reached 9:00 AM - 5:00 PM EST.
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, WILLIAM J KELLEHER can be reached at (571) 272-7753. 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.
/Hailey R Le/Examiner, Art Unit 3648 May 27, 2026
Prosecution Insights