DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . The Amendment filed 21 November 2025 has been entered and considered. Claims 1 and 5 have been amended. Claims 7-10 have been added. Claims 1-10 are all the claims pending in the application.
Response to Amendment
Prior Art Rejections
In view of the amendments to independent Claims 1 and 5, and their dependent claims by extension, the rejection under 35 USC 103 using previously cited art Kubo in view of a different embodiment of Kubo is withdrawn. However, a rejection under 35 USC 103 is presented using Bhowmik in view of previously cited art Kubo. Because of the new grounds of rejection necessitated by the Applicant’s amendments, previous arguments are now moot.
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.
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.
Claims 1-6 are rejected under 35 U.S.C. 103 as being unpatentable over Bhowmik et al. (NPL: On the Impact of Using X-Ray Energy Response Imagery for Object Detection Via Convolutional Neural Networks, hereafter referred as Bhowmik) in view of Kubo (U.S. Patent App. Pub No. 2021/0004994 A1, hereafter referred as Kubo).
Regarding Claim 1:
Bhowmik teaches an image storage unit that stores, as 3-channel pseudo RGB images, three inspection images having same imaging position with respect to an inspection object and different transmission characteristics (Bhowmik: Introduction and Fig. 1; a dual-energy X-ray scanner imagery consists of two intensity images acquired at two discrete energy levels (low and high), facilitating the recovery of material properties (effective atomic number, effective-z). The information is fused with the help of a colour transfer function into a single pseudo-colour X-ray image; The objective of using two energy levels (high and low) for object detection task is to obtain both the density and atomic number Z (effective-z) of the scanned materials; Fig. 1 showcases same imaging position of the inspection object) and obtained by capturing the inspection object (Bhowmik: Introduction and Fig. 1; to facilitate the interpretation of the baggage contents; Fig. 1 shows an inspection object being captured).
Bhowmik fails to further teach an inspection device comprising: and a determination unit that obtains a defective quality degree for the 3-channel pseudo RGB image stored in the image storage unit based on a learned model created in advance by learning using an image having a same format as the 3-channel pseudo RGB image, and determines a quality state of the inspection object by comparison between the defective quality degree and a preset threshold.
Kubo, like Bhowmik, is directed to dual-energy x-ray imaging. Kubo does teach an inspection device (Kubo: Par. [0002]; inspection apparatus (X-ray inspection apparatus)) comprising: and a determination unit that obtains a defective quality degree for the 3-channel pseudo RGB image stored in the image storage unit based on a learned model created in advance by learning using an image having a same format as the 3-channel pseudo RGB image (Kubo: Par. [0094]; detecting unit 104 acquires the foreign-matter likelihood (prediction result R1 output from the machine learned model 103) for the respective pixels by inputting the soft image P10 and the hard image P20 of an article G), and determines a quality state of the inspection object by comparison between the defective quality degree and a preset threshold (Kubo: Par. [0094]; detecting unit 104 can detect the foreign matter mixed in the article G by identifying pixels having a foreign-matter likelihood equal to or larger than the predetermined threshold).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Bhowmik to utilize the defective quality technique, as taught by Kubo, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. As taught by Kubo, the proposed modification makes it possible to generate suitable training data for performing machine learning of the machine learned model for determining whether a foreign matter is contained in an article on the basis of two types of transmission images obtained from the respective two line sensors of energy bands different from each other (Kubo: Par. [0020]).
In regards to Claim 2, Bhowmik as modified by Kubo further teaches the inspection device according to Claim 1, wherein the learned model is learned for each type of the inspection object with respect to the image having the same format as the 3-channel pseudo RGB image including at least images with a defective quality (Kubo: Par. [0090] and Fig. 7; learning unit 102 inputs the training data (from Bhowmik) thus obtained (the first virtual defective-product image P112, the second virtual defective-product image P122, and the correct data) to the machine learned model 103, thereby building a learned model including a (multilayer) neural network configured to input the soft image P10 and the hard image P20 and output a foreign-matter likelihood for each pixel).
In regards to Claim 3, Bhowmik as modified by Kubo further teaches the inspection device according to Claim 1, wherein the 3-channel pseudo RGB images are three inspection images obtained by spectroscopy of light transmitting through the inspection object (Bhowmik: Introduction and Fig. 1; a dual-energy X-ray scanner imagery consists of two intensity images acquired at two discrete energy levels (low and high), facilitating the recovery of material properties (effective atomic number, effective-z). The information is fused with the help of a colour transfer function into a single pseudo-colour X-ray image; The objective of using two energy levels (high and low) for object detection task is to obtain both the density and atomic number Z (effective-z) of the scanned materials).
In regards to Claim 4, Bhowmik as modified by Kubo further teaches the inspection device according to Claim 2, wherein the 3-channel pseudo RGB images are three inspection images obtained by spectroscopy of light transmitting through the inspection object (Bhowmik: Introduction and Fig. 1; a dual-energy X-ray scanner imagery consists of two intensity images acquired at two discrete energy levels (low and high), facilitating the recovery of material properties (effective atomic number, effective-z). The information is fused with the help of a colour transfer function into a single pseudo-colour X-ray image; The objective of using two energy levels (high and low) for object detection task is to obtain both the density and atomic number Z (effective-z) of the scanned materials).
Regarding Claim 5:
Bhowmik as modified by Kubo further teaches a learned model creation method (Kubo: Par. [0089]; learning unit 102 performs learning processing of the machine learned model 103) comprising: a learning image acquisition step of acquiring a non-defective image of an inspection object (Kubo: Par. [0050]; second image acquiring unit 51 acquires the first non-defective-product image P111, non-defective-product image means a transmission image of an article G containing no foreign matter; training data being used and referenced are the pseudo-colour X-ray images from Bhowmik) and an image with only defective quality of the inspection object as learning images (Kubo: Par. [0052]; first virtual defective-product image P112); a step of creating a learning defective quality synthesis image in which the image with only defective quality is synthesized with the non-defective image of the inspection object using the learning image (Kubo: Par. [0052]; first processing unit 52 changes pixel values of first target pixels PX1 that are at least one or more pixels forming the first non-defective-product image P111, thereby synthesis virtual foreign-matter images PF1 to generate a first virtual defective-product image P112 that is a virtual defective-product image) and a learning defective quality label showing a defective quality position in the learning defective quality synthesis image (Kubo: Par. [0048]; image is produced based on a non-defective-product image that can be acquired in large numbers, a virtual foreign matter can be generated by a computer, and thus the computer itself apparently knows the position of the foreign matter and can easily generate a label); and a step of creating a learned model by performing machine learning of the learning defective quality synthesis image (Kubo: Par. [0089]; learning unit 102 performs learning processing of the machine learned model 103 with training data including the first virtual defective-product image P112), wherein the learning image acquired in the learning image acquisition step is a 3-channel pseudo RGB image including three inspection images having same imaging position with respect to an inspection object and different transmission characteristics (Bhowmik: Introduction and Fig. 1; a dual-energy X-ray scanner imagery consists of two intensity images acquired at two discrete energy levels (low and high), facilitating the recovery of material properties (effective atomic number, effective-z). The information is fused with the help of a colour transfer function into a single pseudo-colour X-ray image; The objective of using two energy levels (high and low) for object detection task is to obtain both the density and atomic number Z (effective-z) of the scanned materials; Fig. 1 showcases same imaging position of the inspection object) and obtained by capturing the inspection object (Bhowmik: Introduction and Fig. 1; to facilitate the interpretation of the baggage contents; Fig. 1 shows an inspection object being captured).
In regards to Claim 6, Bhowmik as modified by Kubo further teaches an inspection method comprising: a step of obtaining a defective quality degree for 3-channel pseudo RGB images of an inspection object (Kubo: Par. [0094]; detecting unit 104 acquires the foreign-matter likelihood (prediction result R1 output from the machine learned model 103) for the respective pixels by inputting the soft image P10 and the hard image P20 of an article G; again referencing defective training data from Bhowmik) including three inspection images having different transmission characteristics ((Bhowmik: Introduction and Fig. 1; a dual-energy X-ray scanner imagery consists of two intensity images acquired at two discrete energy levels (low and high), facilitating the recovery of material properties (effective atomic number, effective-z). The information is fused with the help of a colour transfer function into a single pseudo-colour X-ray image; The objective of using two energy levels (high and low) for object detection task is to obtain both the density and atomic number Z (effective-z) of the scanned materials) and obtained by capturing the inspection object (Bhowmik: Introduction and Fig. 1; to facilitate the interpretation of the baggage contents; Fig. 1 shows an inspection object being captured) based on the learned model created by the learned model creation (Kubo: Par. [0089]; learning unit 102 performs learning processing of the machine learned model 103) method of Claim 5, and determining a quality state of the inspection object by comparison between the defective quality degree and a preset threshold (Kubo: Par. [0094]; detecting unit 104 can detect the foreign matter mixed in the article G by identifying pixels having a foreign-matter likelihood equal to or larger than the predetermined threshold).
Claims 7-10 are rejected under 35 U.S.C. 103 as being unpatentable over Bhowmik et al. (NPL: On the Impact of Using X-Ray Energy Response Imagery for Object Detection Via Convolutional Neural Networks, hereafter referred as Bhowmik) in view of Kubo (U.S. Patent App. Pub No. 2021/0004994 A1, hereafter referred as Kubo) and Tao (NPL: Multi-energy CT imaging for large patients using dual-source photon-counting detector CT, hereafter referred as Tao)
In regards to Claim 7, Bhowmik as modified by Kubo further teaches the inspection device according to Claim 1, wherein the 3-channel pseudo RGB images consist of a low-energy X-ray image, a high- energy X-ray image, and a difference X-ray image indicating the difference between the low- energy X-ray image and the high-energy X-ray image (Bhowmik: Introduction and Fig. 1; a dual-energy X-ray scanner imagery consists of two intensity images acquired at two discrete energy levels (low and high), facilitating the recovery of material properties (effective atomic number, effective-z). The information is fused with the help of a colour transfer function into a single pseudo-colour X-ray image; The objective of using two energy levels (high and low) for object detection task is to obtain both the density and atomic number Z (effective-z) of the scanned materials).
Bhowmik fails to further teach wherein the low-energy X-ray image and the high-energy X-ray image are obtained by a photon counting-type X-ray detector.
Tao, like Bhowmik, is directed to dual-energy x-ray imaging. Tao does teach wherein the low-energy X-ray image and the high-energy X-ray image are obtained by a photon counting-type X-ray detector (Tao: Introduction; photon-counting detectors (PCD)).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Bhowmik to the photon counting-type x-ray detector, as taught by Tao, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. As taught by Tao, the proposed modification can resolve the energy of incident photons and are therefore capable of multi-energy imaging with a single kV scan (Tao: Introduction).
In regards to Claim 8, Bhowmik as modified by Kubo and Tao further teaches the inspection device according to Claim 2, wherein the 3-channel pseudo RGB images consist of a low-energy X-ray image, a high- energy X-ray image, and a difference X-ray image indicating the difference between the low- energy X-ray image and the high-energy X-ray image (Bhowmik: Introduction and Fig. 1; a dual-energy X-ray scanner imagery consists of two intensity images acquired at two discrete energy levels (low and high), facilitating the recovery of material properties (effective atomic number, effective-z). The information is fused with the help of a colour transfer function into a single pseudo-colour X-ray image; The objective of using two energy levels (high and low) for object detection task is to obtain both the density and atomic number Z (effective-z) of the scanned materials), wherein the low-energy X-ray image and the high-energy X-ray image are obtained by a photon counting-type X-ray detector (Tao: Introduction; photon-counting detectors (PCD)).
In regards to Claim 9, Bhowmik as modified by Kubo and Tao further teaches the learned model creation method according to Claim 5, wherein the 3-channel pseudo RGB image consist of a low-energy X-ray image, a high- energy X-ray image, and a difference X-ray image indicating the difference between the low- energy X-ray image and the high-energy X-ray image (Bhowmik: Introduction and Fig. 1; a dual-energy X-ray scanner imagery consists of two intensity images acquired at two discrete energy levels (low and high), facilitating the recovery of material properties (effective atomic number, effective-z). The information is fused with the help of a colour transfer function into a single pseudo-colour X-ray image; The objective of using two energy levels (high and low) for object detection task is to obtain both the density and atomic number Z (effective-z) of the scanned materials), wherein the low-energy X-ray image and the high-energy X-ray image are obtained by a photon counting-type X-ray detector (Tao: Introduction; photon-counting detectors (PCD)).
In regards to Claim 10, Bhowmik as modified by Kubo and Tao further teaches the learned model creation method according to Claim 6, wherein the 3-channel pseudo RGB image consist of a low-energy X-ray image, a high- energy X-ray image, and a difference X-ray image indicating the difference between the low- energy X-ray image and the high-energy X-ray image (Bhowmik: Introduction and Fig. 1; a dual-energy X-ray scanner imagery consists of two intensity images acquired at two discrete energy levels (low and high), facilitating the recovery of material properties (effective atomic number, effective-z). The information is fused with the help of a colour transfer function into a single pseudo-colour X-ray image; The objective of using two energy levels (high and low) for object detection task is to obtain both the density and atomic number Z (effective-z) of the scanned materials), wherein the low-energy X-ray image and the high-energy X-ray image are obtained by a photon counting-type X-ray detector (Tao: Introduction; photon-counting detectors (PCD)).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RENAE BITOR whose telephone number is (703)756-5563. The examiner can normally be reached Monday to Friday: 8:00 - 5:30 but off the 1st Friday of the biweek.
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, GREG MORSE can be reached on (571)272-3838. 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.
/RENAE A BITOR/Examiner, Art Unit 2663
/GREGORY A MORSE/Supervisory Patent Examiner, Art Unit 2698
Prosecution Insights