DETAILED ACTIONS
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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 07/02/2026 has been entered.
Response to Amendment
This office action is in response to the amendments/arguments submitted by the Applicant(s) on 07/02/2026.
Status of the Claims
Claims 1-2, 5-6, 9-10, 12-13, 15-20 are pending.
Claims 1,9 and 13 are amended.
Claims 3-4, 7-8, 11, and 14 are cancelled
Claims 17-20 are new.
Response to Arguments
Rejections Under 35 U.S.C. 103
Applicant's arguments, see remarks pages 6-8, filed 07/02/2026 with respect to the rejection(s) of Claims under 35 U.S.C. 103 has been considered, and are moot because the amendment has necessitated a new ground of rejections. The new rejections are set forth below.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 5-6,12-13, 15-18 are rejected under 35 U.S.C. 103 as being unpatentable over OOTA et al. (US 2019/0325606 A1, hereinafter Oota, previously cited) and in of view of Suyama et al. (US 2017/0184514 A1, hereinafter Suyama).
Regarding Claim 1, Oota teaches,
An inspection device (Oota, Figure 1, Inspection apparatus, 1) comprising:
an image storage unit (Oota, Figure 1, 12,13,14, [0023]) that captures a plurality of images (Oota, Figure 1, [0027], “image data input from the imaging device 70”) having different input channels for an inspection object (Oota, Figure 2, Imaging unit 102) under a predetermined imaging condition corresponding to each input channel (Oota, Figure 2, Imaging condition 1, condition 2, and Image condition N), and
stores multiple inspection images obtained by the capturing and combining the plurality of images of the inspection object (Oota, Figure 1, [0027], “The nonvolatile memory 14 stores data input from the input/output device 60, image data input from the
imaging device 70 via the interface 19, and the like”); and
a determination unit (Oota, Figure 2, Determination Unit 103), that obtains a defective quality degree for the multiple inspection images stored in the image storage unit based on a learned model (Oota, Figure 2, 0033] (“The determination unit 103 includes a learning unit 1031 and a comprehensive determination unit 1032. The learning unit 1031 uses the image data output from the imaging unit 102 as an input and performs appearance inspection, that is, determination of quality by machine
learning”). created in advance by learning using an image having a same imaging condition as the multiple inspection images (Oota, Figure 3, [0041], [0041] The learning unit 1031 herein may input all of the plurality of image data to the same learning model or may input the image data to different learning models as illustrated in FIG. 3. For example, when a plurality of learning models optimized for a specific imaging condition are constructed, it is possible to perform the inspection using the learning model suited to the imaging condition of the image data to be input”), and
determines a quality state of the inspection object by comparison between the defective quality degree and a preset threshold (Oota, Figure1-3, [0042]” The comprehensive determination unit 1032 acquires a plurality of inspection results (for the same inspection target, but based on the plurality of image data with different imaging conditions) output from the learning unit 1031 and, based on the contents of the acquired results, determines a final inspection result”. For example, the comprehensive determination unit 1032 classifies, based on the
NG degree.”. For example, the comprehensive determination unit 1032 classifies, based on the NG degree, the inspection results into three cases in which
"not good" (NG degree is 81 to 100), NOTE: See [0039], threshold, and the range of NG Degrees 0 to 100),
wherein the learned model is associated with the imaging condition for the image used for learning (Oota, Figure 2, [0040] “The learning unit 1031 inputs the plurality of image data output from the imaging unit 102 with different imaging conditions into the learning model, and obtains the inspection result corresponding to each image data”), and wherein the learned model is learned for multiple different types of inspection objects with respect to the image having a same imaging condition as the multiple inspection images including at least images with a defective quality (“Oota, Figure 3,[0042], “Alternatively, it is also possible to estimate a comprehensive inspection result by using a learning model that can receive the plurality of inspection results output from the learning unit 1031 as an input and output the comprehensive inspection result. In this learning model, a correlation between the comprehensive inspection result determined by various methods so far and the plurality of inspection results output from the learning unit 1031 based on the comprehensive inspection result is learned in advance by a known machine learning method” NOTE: different defect quality images (good/not good) has been analyzed by the comprehensive inspection unit 1032).
Oota is silent on
wherein the multiple inspection images comprise a low-energy X-ray image and a high- energy X-ray image that show different transmission characteristics and that are acquired simultaneously by irradiating the inspection object transported on a transportation belt at a transport speed with X-rays having a wavelength and intensity from an X-ray tube,
wherein the imaging condition includes the transport speed, a tube current and a tube voltage of the X-ray tube that are set by test imaging using each inspection object to generate the X-rays and obtain the multiple inspection images,
images with a defective quality due to containing foreign matter.
However, Suyama teaches wherein the multiple inspection images comprise a low-energy X-ray image and a high- energy X-ray image that show different transmission characteristics and, (Suyama, [0033], As shown in FIG. 1 and FIG. 2, the X-ray image acquiring system (radiation image acquiring system, radiation inspection system) 1 is an apparatus that irradiates X-rays (radiation) from an X-ray irradiator (radiation irradiator) 20 to a subject S, and detects, of the irradiated X-rays, transmitted X-rays having been transmitted through the subject S in a plurality of energy ranges. The X-ray image acquiring system 1 carries out, by using a transmission X-ray image, detection of a foreign substance contained in the subject S and a baggage inspection etc”) that are acquired simultaneously by irradiating the inspection object transported on a transportation belt at a transport speed with X-rays having a wavelength and intensity from an X-ray tube (Suyama, Figure 1, [0033], The X-ray image acquiring system 1 thus configured includes a belt conveyor ( conveying section) 10, an X-ray irradiator (radiation irradiator) 20, a low-energy image acquiring section 30, a high-energy image acquiring section 40, a timing control section 50, a timing calculating section 60, and an image processor ( composite image generating section, composite image output section) 70. The low-energy image acquiring section 30, the high-energy image acquiring section 40, and the timing control section 50 compose a dual image acquiring device (radiation detection device) 80”).
wherein the imaging condition includes the transport speed, (Suyama, [0034] The belt conveyor 10, as shown in FIG. 1, includes a belt portion 12 on which the subject S is placed. The belt conveyor 10 makes the belt portion 12 move in a conveying direction A (from an upstream side at the left-hand side of FIG. 1 to a downstream side at the right-hand side of FIG. 1) to thereby convey the subject Sin the conveying direction A at a predetermined conveying speed M. The conveying speed M of the subject S is, for example, 48 m/minute”) a tube current and a tube voltage of the X-ray tube that are set by test imaging using each inspection object to generate the X-rays and obtain the multiple inspection images, (Suyama [0044] In addition, as the low-energy detector 32 and the high-energy detector 42 to compose the dual energy sensor 86, for example, one with an energy discrimination function for which a low-energy cutting filter is arranged on a
high-energy sensor may be used. Alternatively, a scintillator for converting X-rays in a low-energy range to visible light and a scintillator for converting X-rays in a high-energy range to visible light may be used to provide both detectors 32, 42 with different wavelength sensitivities”)
images with a defective quality due to containing foreign matter The X-ray image acquiring system 1 carries out, by using a transmission X-ray image, detection of a foreign substance contained in the subject S and a baggage inspection etc”)
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Suyama’s X-ray inspection device with belt conveyer to inspect object with plurality of images with the benefit of detecting a foreign substance contained in the subject directly from processing the image data. (Suyama, [0050]).
Regarding Claim 2, combination of Oota and Suyama teaches the inspection device according to Claim 1,
Oota further teaches wherein the predetermined imaging condition includes at
least position information indicating an imaging position of the inspection object for
each input channel. (Oota, [0031] " The imaging condition decision unit 101 determines the imaging condition of the appearance of the inspection target. The imaging conditions include, for example, an angle of the light source or the camera with respect to the inspection target a positional relationship between the camera and the light source, a type (color, temperature, brightness, and the like) of the light source" NOTE: operator sets the imaging condition parameters and adjust as needed. (Oota, [0045], the imaging condition decision unit 101 can change a predetermined imaging condition according to a predetermined rule. For example, the imaging condition decision unit 101 determines to change relative positions of an inspection target”).
Regarding Claim 5, combination of Oota and Suyama teaches the inspection device according to Claim 1,
Oota is silent on wherein the multiple inspection images include images obtained by spectroscopy of light transmitting through the inspection object.
However, Suyama teaches wherein the multiple inspection images include images obtained by spectroscopy of light transmitting through the inspection object. (Suyama, [0051] Here, a calculation method of the delay time Tin detection timing to be used by the timing control section 50 and actions will be described by taking an example of acquiring a transmission X-ray image of a subject S (refer to
FIG. 4) and detecting a foreign substance O contained in the subject S.”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Sumyas X-ray inspection device to inspect object with transmitted X-ray of different photon energy inspection apparatus and identify from the X-ray images the presence of a foreign subject matter. (Suyama, [0050]-[0051]).
Regarding Claim 6, combination of Oota and Suyama teaches the inspection device according to Claim 2,
Oota is silent wherein the multiple inspection images include images obtained by spectroscopy of light transmitting through the inspection object.
However, Suyama teaches wherein the multiple inspection images include images obtained by spectroscopy of light transmitting through the inspection object. (Suyama, [0051] Here, a calculation method of the delay time Tin detection timing to be used by the timing control section 50 and actions will be described by taking an example of acquiring a transmission X-ray image of a subject S (refer to
FIG. 4) and detecting a foreign substance O contained in the subject S.”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Sumyas X-ray inspection device to inspect object with transmitted X-ray of different photon energy inspection apparatus and identify from the X-ray images the presence of a foreign subject matter. (Suyama, [0050]-[0051]).
Regarding Claim 12, combination of Oota and Suyama teaches the inspection device according to Claim 1,
Oota teaches the learned model ( (Oota, Figure 3, [0041], The learning unit 1031 herein may input all of the plurality of image data to the same learning model or may input the image data to different learning models as illustrated in FIG. 3.”),
Oota is silent on the inspection device according to wherein the low-energy X-ray image and the high-energy X-ray image are acquired by a photon counting-type X-ray detector, and wherein the imaging condition includes an energy threshold for the photon counting-type X-ray detector and the energy threshold associated with the learned model.
However, Suyama teaches on the inspection device according to wherein the low-energy X-ray image and the high-energy X-ray image are acquired by a photon counting-type X-ray detector, and wherein the imaging condition includes an energy threshold for the photon counting-type X-ray detector and the energy threshold associated with the learned model (Suyama, [0044] In addition, as the low-energy detector 32 and the high-energy detector 42 to compose the dual energy sensor
86, for example, one with an energy discrimination function for which a low-energy cutting filter is arranged on a high-energy sensor may be used. Alternatively, a scintillator for converting X-rays in a low-energy range to visible light and a scintillator for converting X-rays in a high-energy range to visible light may be used to provide both detectors 32, 42 with different wavelength sensitivities, so as to allow detecting different energy ranges. In addition, filters may be arranged on scintillators having different wavelength sensitivities.
Further, there may be one with an energy discrimination function by a direct conversion method of CdTe (cadmium telluride) or the like”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Sumyas X-ray inspection device to inspect object with transmitted X-ray of different photon energy inspection apparatus and identify from the X-ray images the presence of a foreign subject matter. (Suyama, [0050]-[0051]).
Regarding Claim 13, combination of Oota and Suyama teaches the inspection device according to Claim 1,
Oota is silent on wherein the multiple inspection images comprise the low-energy X-ray image, the high-energy X-ray image and a difference image created from the low-energy X-ray image and the high-energy X-ray image.
However, Suyama teaches (Suyama, [0050] The image processor 70 is a device that performs an arithmetic processing for obtaining difference data
between the low-energy image data detected and generated by the low-energy detector 32 and the high-energy image data detected and generated by the high-energy detector 42, and generates an energy subtraction image, which is a
composite image. d. The image processor 70 outputs to display the energy subtraction image generated by the arithmetic processing on a display or the like. This output display allows visually confirming a foreign substance contained in
the subject S”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Sumyas X-ray inspection device to inspect object with transmitted X-ray of different photon energy inspection apparatus and identify from the X-ray images the presence of a foreign subject matter. (Suyama, [0050]-[0051]).
Regarding Claim 15, combination of Oota and Suyama teaches the inspection device according to Claim 12,
Oota is silent on wherein the multiple inspection images further comprise the difference image created from the low-energy X-ray image and the high-energy X-ray image.
However, Suyama teaches wherein the multiple inspection images further comprise the difference image created from the low-energy X-ray image and the high-energy X-ray image (Suyama, [0044] “In addition, as the low-energy detector 32 and the high-energy detector 42 to compose the dual energy sensor
86, for example, one with an energy discrimination function for which a low-energy cutting filter is arranged on a high-energy sensor may be used. Alternatively, a scintillator for converting X-rays in a low-energy range to visible light and a scintillator for converting X-rays in a high-energy range to visible light may be used to provide both detectors 32, 42 with different wavelength sensitivities, so as to allow detecting different energy ranges”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Sumyas X-ray inspection device to inspect object with transmitted X-ray of different photon energy inspection apparatus and identify from the X-ray images the presence of a foreign subject matter. (Suyama, [0050]-[0051]).
Regarding Claim 16, combination of Oota and Suyama teaches the inspection device according to Claim 1,
Oota further teaches wherein the learned model is learned for each type of the inspection object with respect to the image having a same imaging condition as the multiple inspection images. (Oota, Figure 3, [0042], “Alternatively, it is also possible to estimate a comprehensive inspection result by using a learning model that can receive the plurality of inspection results output from the learning unit 1031 as an input and output the comprehensive inspection result. In this learning model, a correlation between the comprehensive inspection result determined by various methods so far and the plurality of inspection results output from the learning unit 1031 based on the comprehensive inspection result is learned in advance by a known machine learning method” NOTE: different defect quality images (good/not good) has been analyzed by the comprehensive inspection unit 1032). including further images with a defective quality due to a shape defect (Oota, Figure 1, [0009] “An inspection apparatus according to an embodiment of the present invention is an inspection apparatus for performing an appearance inspection using a plurality of images obtained by imaging an inspection targe”).
Regarding Claim 17, combination of Oota and Suyama teaches the inspection device according to Claim 1,
Oota is silent on wherein the foreign matter is a piece of bone.
However, Suyama teaches wherein the foreign matter is a piece of bone (Suyama, [0008] “The present invention has therefore been made in
view of such problems, and an object thereof is to provide a radiation detection device, a radiation image acquiring system, a radiation detection system, and a radiation detection method capable of improving the detection accuracy of
a foreign substance etc., contained in a subject”. Foreign substance could be bone see, [0006]. “the composition of a foreign substance contained in the subject (for example, a difference of whether being bone or meat or whether being cartilage or a foreign substance in a meat inspection”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Sumyas X-ray inspection device to inspect object with transmitted X-ray of different photon energy inspection apparatus and identify from the X-ray images the presence of a foreign subject matter. (Suyama, [0050]-[0051]).
Regarding Claim 18, combination of Oota and Suyama teaches the inspection device according to Claim 2,
Oota is silent on wherein the foreign matter is a piece of bone.
However, Suyama teaches wherein the foreign matter is a piece of bone (Suyama, [0008] “The present invention has therefore been made in
view of such problems, and an object thereof is to provide a radiation detection device, a radiation image acquiring system, a radiation detection system, and a radiation detection method capable of improving the detection accuracy of
a foreign substance etc., contained in a subject”. Foreign substance could be bone see, [0006]. “the composition of a foreign substance contained in the subject (for example, a difference of whether being bone or meat or whether being cartilage or a foreign substance in a meat inspection”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Sumyas X-ray inspection device to inspect object with transmitted X-ray of different photon energy inspection apparatus and identify from the X-ray images the presence of a foreign subject matter. (Suyama, [0050]-[0051]).
Claims 9-10 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over OOTA and in view of Suyama and in further view of Sachihiro Nakagawa (US 2022/0318985 A1, hereinafter Nakagawa, previously cited)
Regarding Claim 9, Oota teaches
Oota teaches a learned model creation method ((Oota, Figure 2, [0040] “The learning unit 1031 inputs the plurality of image data output from the imaging unit 102 with different imaging conditions into the learning model, and obtains the inspection result corresponding to each image data”),) comprising:
a step of acquiring a non-defective image of an inspection object and an image with only defective quality (Oota, Figure 3,[0042], “Alternatively, it is also possible to estimate a comprehensive inspection result by using a learning model that can receive the plurality of inspection results output from the learning unit 1031 as an input and output the comprehensive inspection result. In this learning model, a correlation between the comprehensive inspection result determined by various methods so far and the plurality of inspection results output from the learning unit 1031 based on the comprehensive inspection result is learned in advance by a known machine learning method” NOTE: different defect quality images (good/not good) has been analyzed by the comprehensive inspection unit 1032).
a step of creating a learned model by performing machine learning of the learning defective quality synthesis image and associating the learned model with the imaging condition (Oota, Figure 3, [0041], [0041] The learning unit 1031 herein may input all of the plurality of image data to the same learning model or may input the image data to different learning models as illustrated in FIG. 3. For example, when a plurality of learning models optimized for a specific imaging condition are constructed, it is possible to perform the inspection using the learning model suited to the imaging condition of the image data to be input”),
Oota is silent on learning images that comprise a low-energy X-ray image and a high-energy X-ray image that show different transmission characteristics acquired and that are acquired simultaneously by irradiating the inspection object with X-rays from an X-ray tube;
However, Suyama teaches learning images that comprise a low-energy X-ray image and a high-energy X-ray image that show different transmission characteristics acquired and (Suyama, [0033], As shown in FIG. 1 and FIG. 2, the X-ray image acquiring system (radiation image acquiring system, radiation inspection system) 1 is an apparatus that irradiates X-rays (radiation) from an X-ray irradiator (radiation irradiator) 20 to a subject S, and detects, of the irradiated X-rays, transmitted X-rays having been transmitted through the subject S in a plurality of energy ranges. The X-ray image acquiring system 1 carries out, by using a transmission X-ray image, detection of a foreign substance contained in the subject S and a baggage inspection etc”); that are acquired simultaneously by irradiating the inspection object with X-rays from an X-ray tube(Suyama, Figure 1, [0033], The X-ray image acquiring system 1 thus configured includes a belt conveyor ( conveying section) 10, an X-ray irradiator (radiation irradiator) 20, a low-energy image acquiring section 30, a high-energy image acquiring section 40, a timing control section 50, a timing calculating section 60, and an image processor ( composite image generating section, composite image output section) 70. The low-energy image acquiring section 30, the high-energy image acquiring section 40, and the timing control section 50 compose a dual image acquiring device (radiation detection device) 80”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Suyama’s X-ray inspection device with belt conveyer to inspect object with plurality of images with the benefit of detecting a foreign substance contained in the subject directly from processing the image data. (Suyama, [0050]).
Oota and Suyama are silent on
a step of creating a learned model by performing machine learning of the learning defective quality synthesis image and associating the learned model with the imaging condition that includes a transport speed of the object on a transportation belt a tube current and a tube voltage of the X- ray tube that are set by test imaging using the inspection object.
a step of creating a learning defective quality synthesis image in which the image with only defective quality due to containing foreign matter is synthesized with the non-defective image of the inspection object using the learning image and a learning defective quality label showing a position of foreign matter in the learning defective quality synthesis image having a same imaging condition as the non-defective image of an inspection object
However, Nakagawa teaches a step of creating a learned model by performing machine learning of the learning defective quality synthesis image and associating the learned model with the imaging condition that includes a transport speed of the object on a transportation belt a tube current and a tube voltage of the X- ray tube that are set by test imaging using the inspection object (Nakagawa, 0101] First, the inspection device 1 receives an operation by the user for setting the inspection conditions (step S200). The inspection conditions include selection of a learned model to be used in the determination of an object to be removed, in addition to conditions for a general inspection device, such as an irradiation intensity of X-rays, visible
light, etc. at the time of image capturing, time of exposure, a feeding speed, etc”).
a step of creating a learning defective quality synthesis image in which the image with only defective quality due to containing foreign matter is synthesized with the non-defective image of the inspection object using the learning image (Nakagawa, Figures 3, 7A-7B, and 10-11, [0062] After the position(s) where the seal section(s) is/are present has/have been specified, blob F indicating the section where foreign matter is present may further be detected as shown in FIG. 7A by binarizing the image of the inspection target 2 by using, as a threshold, the darkness of the image corresponding to the section where the foreign matter is present in the seal section(s) 2s, and a predetermined area including this blob F may be specified as inspection area A as shown in FIG. 7B. FIGS. 7A and 7B illustrate the case with a single blob F, but it is possible to specify a plurality of inspection areas A in a similar manner in the case where there is a plurality of blobs F.” [0064] The cut-out means 121 cuts out the image of the inspection area(s) specified as described above from the image of the inspection target 2 and outputs the same as a learning-target image to the sorting means 124.).
a learning defective quality label showing position of foreign matter in the learning defective quality synthesis image having a same imaging condition as the non-defective image of an inspection object; Nakagawa, Figure 11, step 200, set inspection condition, [0066] The extraction means 122 outputs the thus extracted sub-images to the sorting means 124 as learning target images. [0067] In this way, by using the sub-images obtained by subdividing the inspection area A as the learning-target”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s and Suyamas X-ray image processing method to incorporate an analysis of the identifying foreign object as taught by Nakagawa image analysis method with a X-ray inspection apparatus and identify from image analysis the presence of the presence of foreign matters. (Nakagawa [0002]-[0004]).
Regarding Claim 10, combination of Oota, Suyama and Nakagawa teaches the learned model creation of claim 9,
An inspection method (Oota, Figure 4) comprising:
a step of determining a quality state of an inspection object by capturing a plurality of images (Oota, Figure 1, [0027], “image data input from the imaging device 70”) having different input channels for the inspection object under an imaging condition corresponding to each input channel, (Oota, Figure1-3, [0042]” The comprehensive determination unit 1032 acquires a plurality of inspection results (for the same inspection target, but based on the plurality of image data with different imaging conditions) output from the learning unit 1031 and, based on the contents of the acquired results, determines a final inspection result”. For example, the comprehensive determination unit 1032 classifies, based on the
NG degree.”. For example, the comprehensive determination unit 1032 classifies, based on the NG degree, the inspection results into three cases in which
"not good" (NG degree is 81 to 100), NOTE: See [0039],
Oota is silent on obtaining a degree of containing foreign matter for multiple inspection images obtained by the capturing and combining the plurality of images of the inspection object, based on a learned model created using an image having a same imaging condition as the multiple inspection images by the learned model creation method of claim 9, and comparing degree of containing the foreign matter and a preset threshold.
However, Nakagawa teaches obtaining a degree of containing foreign matter for; multiple inspection images obtained by the (Nakagawa Figures 3, 7A-7B, and 10-11, [0062] After the position(s) where the seal section(s) is/are present has/have been specified, blob F indicating the section where foreign matter is present may further be detected as shown in FIG. 7A by binarizing the image of the inspection target 2 by using, as a threshold, the darkness of the image corresponding to the section where the foreign matter is present in the seal section(s) 2s, and a predetermined area including this blob F may be specified as inspection area A as shown in FIG. 7B. [0064] The cut-out means 121 cuts out the image of the inspection area(s) specified as described above from the image of the inspection target 2 and outputs the same as a learning-target image to the sorting means 124.”). capturing and combining the plurality of images of the inspection object based on a learned model created using an image having a same imaging condition as the multiple inspection images by the learned model creation method of claim 9 [0070] In the case where the cut-out means 121 cuts out a learning-target image when performing additional learning on the learned model, which is generated on the basis of the image of the inspection area, the cut-out conditions for the cut-out means 121 are set so that the image of the inspection area of the size and shape used to generate such learned model is cut out”)
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s and Suyama’s X-ray image processing method to incorporate an analysis of the identifying foreign object as taught by Nakagawa image analysis method with a X-ray inspection apparatus and identify from image analysis the presence of the presence of foreign matters. (Nakagawa [0002]-[0004]).
Regarding Claim 19, combination of Oota, Suyama and Nakagawa teaches the learned model creation of claim 9,
Oota is silent on wherein the foreign matter is a piece of bone.
However, Suyama teaches wherein the foreign matter is a piece of bone (Suyama, [0008] “The present invention has therefore been made in
view of such problems, and an object thereof is to provide a radiation detection device, a radiation image acquiring system, a radiation detection system, and a radiation detection method capable of improving the detection accuracy of
a foreign substance etc., contained in a subject”. Foreign substance could be bone see, [0006]. “the composition of a foreign substance contained in the subject (for example, a difference of whether being bone or meat or whether being cartilage or a foreign substance in a meat inspection”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Sumyas X-ray inspection device to inspect object with transmitted X-ray of different photon energy inspection apparatus and identify from the X-ray images the presence of a foreign subject matter. (Suyama, [0050]-[0051]).
Regarding Claim 20, combination of Oota, Suyama and Nakagawa teaches the learned model creation of claim 10,
Oota is silent on wherein the foreign matter is a piece of bone.
However, Suyama teaches wherein the foreign matter is a piece of bone (Suyama, [0008] “The present invention has therefore been made in
view of such problems, and an object thereof is to provide a radiation detection device, a radiation image acquiring system, a radiation detection system, and a radiation detection method capable of improving the detection accuracy of
a foreign substance etc., contained in a subject”. Foreign substance could be bone see, [0006]. “the composition of a foreign substance contained in the subject (for example, a difference of whether being bone or meat or whether being cartilage or a foreign substance in a meat inspection”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Oota’s inspection device with Sumyas X-ray inspection device to inspect object with transmitted X-ray of different photon energy inspection apparatus and identify from the X-ray images the presence of a foreign subject matter. (Suyama, [0050]-[0051]).
Conclusion
Citation of Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
OHASHI TADASHI (JP 2021156636 A) recites “To provide an article inspection device and an article inspection method capable of suppressing restrictions on delay times used in the calculation of
time delay integration and improving inspection accuracy. [Solution] An X-ray inspection device 1 as an article inspection device includes an X-ray irradiation
unit 11 that irradiates an inspection object W made of a moving fluid with X-rays as electromagnetic waves spreading radially, and an X-ray line sensor 15 that
detects X-rays influenced by the inspection object W by a plurality of detection elements 15a arranged in a main scanning direction (Y direction) perpendicular
to the movement direction (X direction) of the inspection object W and in the movement direction. The X-ray inspection device 1 includes a control circuit 36 as a delay time setting unit and a TDI image generating unit. The control circuit 36 sets a plurality of delay times based on a predetermined reference delay time t,and performs a time delay integration process in which detection data detected by the X-ray line sensor 15 is added using the plurality of delay times, thereby
generating a plurality of TDI images corresponding to the plurality of delay times”(Abstract.
HIROSE OSAMU (JP2020003387A) discloses “To provide an inspection device, an inspection system, an inspection method, an inspection program and a recording medium capable of improving processing capacity. An X-ray inspection apparatus 10 detects an X-ray irradiation unit 15 that irradiates an article A with X-rays, an X ray detection unit 16 that detects X-rays that have passed through the article A, and an X-ray detection unit 16. The transparent image G1 created from the result is subjected to the reduction processing of the number of pixels to create the reduced image G2, and the reduced image G2 created by the processing unit 21 is generated by machine learning. The acquisition unit 22 for acquiring the processing result obtained by the processing by the learned model, and the inspection unit 23 for inspecting the article A based on the processing result acquired by the acquisition unit 22 are provided(Abstract).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DILARA SULTANA whose telephone number is (571)272-3861. The examiner can normally be reached Mon-Fri, 9 AM-5:30 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, EMAN ALKAFAWI can be reached on (571) 272-4448. 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.
/DILARA SULTANA/Examiner, Art Unit 2858
08/06/2026
/SON T LE/Primary Examiner, Art Unit 2858
Prosecution Insights