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 .
Response to Amendment
This action is responsive to applicant’s amendments and remarks received on 08/06/2026.
Response to Arguments
Applicant's arguments filed on 08/06/2026 have been fully considered but they are not persuasive.
Applicant argues:
Riley fails to disclose “wherein processing the design image indicating the geometric feature of the at least the part of the substrate includes adding a first image including an abnormality adding region to a second image including (i) a masked region that masks a region corresponding to the abnormality adding region of the first image and (ii) the geometric feature indicated by the design image” because Riley’s approach to generating training images is centered on user-created or user-modified synthetic defects in specimen images.
Examiner’s response:
Riley’s approach to generating training images is centered on user-created or user-modified synthetic defects in specimen images. However, the subject matter in claim 1 does not distinguish between generating training data automatically driven by a computer program, neural network, or user. “A generation method of generating, by an information processing apparatus, training data” can be understood as a user directing the generation of training data using a computer program or application. Furthermore, the subject matter in claim 1 does not distinguish between real or synthetic defects.
Claim Rejections - 35 USC § 101
The objections under this statue are hereby withdrawn in response to Applicant' s
amendments.
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 1-7, 9-16 are rejected under 35 U.S.C. 103 as being unpatentable over Riley et al. (US 20190294923 A1), hereinafter Riley, in view of Terao (US 20180022015 A1), hereinafter Terao.
Regarding claim 1, Riley teaches A generation method of generating, by an information processing apparatus, training data of a model (Abstract see "Methods and systems for training a machine learning model using synthetic defect images are provided. One system includes one or more components executed by one or more computer subsystems. The one or more components include a graphical user interface (GUI) configured for displaying one or more images for a specimen and image editing tools to a user and for receiving input from the user that includes one or more alterations to at least one of the images using one or more of the image editing tools. The component(s) also include an image processing module configured for applying the alteration(s) to the at least one image thereby generating at least one modified image and storing the at least one modified image in a training set. The computer subsystem(s) are configured for training a machine learning model with the training set in which the at least one modified image is stored."). generating a training image as the training data by processing a design image indicating a geometric feature of at least a part of the substrate. (Para. 22 see "The terms “design,” “design data,” and “design information” as used interchangeably herein generally refer to the physical design (layout) of an IC and data derived from the physical design through complex simulation or simple geometric and Boolean operations." Para. 66 see "The drawing tool may be used for freehand drawing of a polygon or irregular shape. The user may manually draw alterations on any available images to thereby insert or create painted synthetic defects therein. ... The reference images may be generated by imaging an actual specimen (as would be the case for die-to-die or cell-to-cell defect detection) or by simulating a reference image from a design for the specimen." Para. 69 see "the alteration(s) include creating a synthetic defect in the at least one of the one or more images based on one or more characteristics of a known DOI for the specimen. ... The image editing tools may be configured such that a user can drag a predetermined shape into a particular location in a specimen image and then modify the predetermined shape"). wherein processing the design image indicating the geometric feature of the at least the part of the substrate includes adding a first image including an abnormality adding region to a second image including (i) a masked region that masks a region corresponding to the abnormality adding region of the first image and (ii) the geometric feature indicated by the design image. (Para. 22 see "The terms “design,” “design data,” and “design information” as used interchangeably herein generally refer to the physical design (layout) of an IC and data derived from the physical design through complex simulation or simple geometric and Boolean operations. In addition, an image of a reticle acquired by a reticle inspection system and/or derivatives thereof can be used as a “proxy” or “proxies” for the design." Para. 67 see "the one or more alterations include pasting a portion of an image corresponding to a known DOI into the at least one of the one or more images. For example, the image editing tools may include a copy/paste tool that can be used to copy/paste an image patch from one image to another. In this manner, a defect image, which may be an image of an actual defect found on an actual specimen or a synthetic defect created by the user, may be copied and pasted from one image to another image to thereby add that defect to the other image." Para. 69 see "the alteration(s) include creating a synthetic defect in the at least one of the one or more images based on one or more characteristics of a known DOI... a user can select a region in an image and set the grey level (black-white) of that region... selecting a region using a rectangular selection tool or by drawing an arbitrary free-form boundary... a user can drag a predetermined shape into a particular location in a specimen image and then modify the predetermined shape... " Para. 75 see "if a user selects two images, a functionality may be made available for subtracting one of the images from the other." Examiner note: a first image with an abnormality adding region may be pasted onto a second image with an abnormality adding region, the adding regions corresponding to where the region is located in the first image and where the region is pasted in the second image. The region that is covered by the pasted region is considered masked. When two images are selected, regions in the first and second image may be subtracted and therefore the regions correspond.).
While Riley teaches training a machine learning model using synthetic defect images to classify images of a specimen, Riley does not teach a model used to evaluate a film of a composition formed on a substrate using a mold.
However, Terao teaches evaluating a film of a composition formed on a substrate using a mold (Abstract see "The present invention an imprint apparatus which performs an imprint process of forming a pattern in an imprint material on a substrate using a mold, the apparatus including an image capturing unit configured to obtain an image by capturing the substrate, and a processing unit configured to perform detection processing of detecting a foreign particle present between the mold and the substrate, wherein the processing unit performs the detection processing by comparing, with a reference image, an image obtained by the image capturing unit" Para. 59 see "The manufacturing method includes a step of forming a pattern on a substrate (a wafer, a glass plate, a film-like substrate, or the like) using an imprint apparatus 100. The manufacturing method further includes a step of processing the substrate on which the pattern has been formed. The processing step can include a step of removing the residual film of the pattern. The processing step can also include another known step such as a step of etching the substrate using the pattern as a mask." Examiner Note: This discloses the relevant context in which a composition or imprint material is formed on a substrate using a mold, and the formed material on the substrate is then evaluated or processed based on acquired image information.).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Riley to incorporate the teachings of Terao to adapt the synthetic training image generation to evaluate films formed on a substrate using a mold. Doing so would predictably improve model accuracy by training on images from the mold and film process to identify defects.
Regarding claim 2, Riley in view of Terao teaches The method according to claim 1.
In addition, Riley teaches wherein the design image is processed, thereby generating the training image to which an abnormality that may occur is artificially added. (Para. 69 see "the alteration(s) include creating a synthetic defect in the at least one of the one or more images based on one or more characteristics of a known DOI for the specimen. ... The image editing tools may be configured such that a user can drag a predetermined shape into a particular location in a specimen image and then modify the predetermined shape").
While Riley teaches generating training data of images containing abnormalities of a specimen, Riley does not teach generating the training image to which an abnormality that may occur in the film.
However, Terao teaches evaluating images of a film-like substrate which can contain abnormalities (Abstract see "The present invention an imprint apparatus which performs an imprint process of forming a pattern in an imprint material on a substrate using a mold, the apparatus including an image capturing unit configured to obtain an image by capturing the substrate, and a processing unit configured to perform detection processing of detecting a foreign particle present between the mold and the substrate, wherein the processing unit performs the detection processing by comparing, with a reference image, an image obtained by the image capturing unit" Para. 59 see "The manufacturing method includes a step of forming a pattern on a substrate (a wafer, a glass plate, a film-like substrate, or the like) using an imprint apparatus 100. The manufacturing method further includes a step of processing the substrate on which the pattern has been formed. The processing step can include a step of removing the residual film of the pattern. The processing step can also include another known step such as a step of etching the substrate using the pattern as a mask." Examiner Note: This identifies the film formed on the substrate as the specific portion of the substrate that is evaluated and processed based on the acquired image information.).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Riley and Terao to incorporate the teachings of Terao to process the design image to artificially add abnormalities that occur in the film formed on the substrate. Doing so would predictably improve training accuracy by inserting defect examples of known film failures.
Regarding claim 3, Riley in view of Terao teaches The method according to claim 2.
In addition, Riley teaches wherein a region defining image for defining the abnormality adding region in a reference image indicating the at least the part of the substrate is created based on the design image, and generating the training image includes artificially adding the abnormality to the abnormality adding region of the reference image based on the region defining image. (Para. 66 see "The reference images may be generated by imaging an actual specimen (as would be the case for die-to-die or cell-to-cell defect detection) or by simulating a reference image from a design for the specimen." Para. 67 see "the one or more alterations include pasting a portion of an image corresponding to a known DOI into the at least one of the one or more images. For example, the image editing tools may include a copy/paste tool that can be used to copy/paste an image patch from one image to another. In this manner, a defect image, which may be an image of an actual defect found on an actual specimen or a synthetic defect created by the user, may be copied and pasted from one image to another image to thereby add that defect to the other image." Para. 68 see "After the image of a known DOI has been pasted into an image, the resulting image may also be altered by the user in any other manner described herein. For example, a user can copy a region of an image and paste it into another area of that image or another image. The user can then change one or more characteristics of the pasted region including, but not limited to, rotation, magnification, and intensity.").
Regarding claim 4, Riley in view of Terao teaches The method according to claim 3.
In addition, Riley teaches wherein geometric transformation of the geometric feature in the design image is performed, and the region defining image is created based on a third image obtained by the geometric transformation. (Para. 68 see "The user can then change one or more characteristics of the pasted region including, but not limited to, rotation, magnification, and intensity. For example, a user can rotate the copied patch image. The user can also change the magnification of the copied image patch by shrinking or enlarging the copied image patch.").
Regarding claim 5, Riley in view of Terao teaches The method according to claim 4.
In addition, Riley teaches wherein an image in which a region where a difference is generated between the design image and the third image is set to the abnormality adding region is created as the region defining image. (Para. 69 see "creating a synthetic defect in the at least one of the one or more images based on one or more characteristics of a known DOI for the specimen. In one such example, the image editing tools may include a number of predetermined drawing shapes (not shown) that a user can add to a specimen image and manipulate one or more characteristics thereof such as dimensions, aspect ratio, gray level intensity" Para. 75 see "The GUI may also display options that can be used to modify one image with another image, e.g., if a user selects two images, a functionality may be made available for subtracting one of the images from the other. In this manner, a user may generate a difference image for a synthetic defect test image to see what the difference image would look like.").
Regarding claim 6, Riley in view of Terao teaches The method according to claim 3.
In addition, Riley teaches wherein the region defining image is created based on the design image and a fourth image including a noise component. (Para. 24 see "Nuisances that are not actually defects even though they are detected as such may be detected due to non-defect noise sources on a specimen (e.g., line edge roughness (LER), relatively small critical dimension (CD) variation in patterned features, thickness variations, etc.) and/or due to marginalitics in the inspection system itself or its configuration used for inspection." Para. 69 see "the image editing tools may include a rectangular clone selection (not shown). The image editing tools may be configured such that a user can drag a predetermined shape into a particular location in a specimen image and then modify the predetermined shape.").
Regarding claim 7, Riley in view of Terao teaches The method according to claim 3.
In addition, Riley teaches wherein based on the region defining image, a part of an image obtained by converting a luminance of the reference image is artificially added as the abnormality to the abnormality adding region of the reference image in the generating of the training image. (Para. 68 see "The user can also change the intensity of the copied image patch to darken or brighten it." Para. 69 see "To edit gray level, a user can select a region in an image and set the grey level (black-white) of that region.").
Regarding claim 9, Riley in view of Terao teaches The method according to claim 2.
In addition, Riley teaches wherein the abnormality includes at least one of a protrusion of the composition from a region on the substrate where the film should be formed, and an unfilling of the composition in the region. (Para. 64 see "Such as a defect class label may be a number such as that described above associated with a type of DOI but it also may be an actual name such as “bridges,” “opens,” “particles,” and the like describing the DOI type." Para. 69 see "if a user knows from experience that lines in a design for a specimen are prone to bridge defects, the user may choose to create a synthetic defect between those lines in an image using one or more of the image editing tools described herein and based on the expected characteristics of the bridge defect." Examiner Note: Riley is not limited to one defect label, it teaches synthesizing user selected expected defect types for a given process. Applied to the process using film and molds, the synthesized defect can be a protrusion (bridge) or unfilling (open).).
While Riley teaches generating training data of images containing abnormalities of a specimen including bridge defects, Riley does not teach wherein the abnormality includes at least one of a protrusion of the composition from a region on the substrate where the film should be formed.
However, Terao teaches identifying where the film should be formed (Abstract see "The present invention an imprint apparatus which performs an imprint process of forming a pattern in an imprint material on a substrate using a mold, the apparatus including an image capturing unit configured to obtain an image by capturing the substrate, and a processing unit configured to perform detection processing of detecting a foreign particle present between the mold and the substrate, wherein the processing unit performs the detection processing by comparing, with a reference image, an image obtained by the image capturing unit" Para. 59 see "The manufacturing method includes a step of forming a pattern on a substrate (a wafer, a glass plate, a film-like substrate, or the like) using an imprint apparatus 100. The manufacturing method further includes a step of processing the substrate on which the pattern has been formed. The processing step can include a step of removing the residual film of the pattern." Examiner Note: This discloses forming a pattern on the substrate at an intended area. Therefore, synthetic defects can be added to areas in the image where the film should not be formed.).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Riley and Terao to incorporate the teachings of Terao to define the artificial abnormality as a protrusion or unfilling of the composition in a region where the film should be formed. Doing so would predictably improve the accuracy of the model by training on images of the specific expected failures when using mold and film.
Regarding claim 10, Riley in view of Terao teaches The method according to claim 1.
In addition, Riley teaches wherein the design image includes, as the geometric feature, information of a boundary of a region where a pattern should be formed on the substrate. (Para. 22 see "The terms “design,” “design data,” and “design information” as used interchangeably herein generally refer to the physical design (layout) of an IC and data derived from the physical design through complex simulation or simple geometric and Boolean operations." Para. 69 see "The options also include selecting a region using a rectangular selection tool or by drawing an arbitrary free-form boundary. The predetermined drawing shapes may include, for example, squares (or rectangles), circles (or ellipses), triangles, hexagons, and other polygons (including regular and irregular polygons)." Examiner Note: The cited design data is the physical layout of the integrated circuit, it inherently includes the edges and boundaries of the regions where a pattern should be formed.).
Regarding claim 11, Riley in view of Terao teaches The method according to claim 1.
In addition, Riley teaches wherein the design image includes, as the geometric feature, information of a mark that should be formed on the substrate. (Para. 22 see "The terms “design,” “design data,” and “design information” as used interchangeably herein generally refer to the physical design (layout) of an IC and data derived from the physical design through complex simulation or simple geometric and Boolean operations." Para. 69 see "The options also include selecting a region using a rectangular selection tool or by drawing an arbitrary free-form boundary. The predetermined drawing shapes may include, for example, squares (or rectangles), circles (or ellipses), triangles, hexagons, and other polygons (including regular and irregular polygons)." Examiner Note: Marks intentionally formed on a substrate are geometric features of the design data or layout.).
Regarding claim 12, Riley in view of Terao teaches The method according to claim 1.
In addition, Riley teaches wherein the design image is obtained from design information represented by a format of an image concerning the at least the part of the substrate. (Para. 22 see "In addition, an image of a reticle acquired by a reticle inspection system and/or derivatives thereof can be used as a “proxy” or “proxies” for the design. Such a reticle image or a derivative thereof can serve as a substitute for the design layout in any embodiments described herein that use a design." Examiner Note: The reticle image or image proxy is design information in image form.).
Regarding claim 13, Riley in view of Terao teaches The method according to claim 1.
In addition, Riley teaches wherein the design image is obtained from design information representing the at least the part of the substrate by vertices, a line segment, or a polygon. (Para. 69 see "The predetermined drawing shapes may include, for example, squares (or rectangles), circles (or ellipses), triangles, hexagons, and other polygons (including regular and irregular polygons).").
Regarding claim 14, Riley in view of Terao teaches The generation method according to claim 1.
In addition, Riley teaches A non-transitory computer-readable storage medium storing a program for causing a computer to execute the generation method according to claim 1. (Para. 43 see "The computer subsystems shown in FIG. 1 (as well as other computer subsystems described herein) may also be referred to herein as computer system(s). Each of the computer subsystem(s) or system(s) described herein may take various forms, including a personal computer system, image computer, mainframe computer system, workstation, network appliance, Internet appliance, or other device. In general, the term “computer system” may be broadly defined to encompass any device having one or more processors, which executes instructions from a memory medium. The computer subsystem(s) or system(s) may also include any suitable processor known in the art such as a parallel processor. In addition, the computer subsystem(s) or system(s) may include a computer platform with high speed processing and software, either as a standalone or a networked tool.").
Regarding claim 15, Riley in view of Terao teaches The generation method according to claim 1.
In addition, Riley teaches A method of learning a model that receives an image of a film of a composition formed on a substrate using a mold as an input, thereby outputting an evaluation result of the film, comprising: performing learning of the model using, as training data, a training image generated by the generation method defined in claim 1. (Para. 12 see "The method further includes training a machine learning model with the training set in which the at least one modified image is stored." Para. 85 see "the computer subsystem(s) may input the user-drawn defects to a machine learning training algorithm that trains a model to thereby improve detection and/or classifier performance.").
While Riley teaches generating training data of images containing abnormalities of a specimen, Riley does not teach an image of a film of a composition formed on a substrate using a mold.
However, Terao teaches an image of a film of a composition formed on a substrate using a mold (Abstract see "The present invention an imprint apparatus which performs an imprint process of forming a pattern in an imprint material on a substrate using a mold, the apparatus including an image capturing unit configured to obtain an image by capturing the substrate, and a processing unit configured to perform detection processing of detecting a foreign particle present between the mold and the substrate, wherein the processing unit performs the detection processing by comparing, with a reference image, an image obtained by the image capturing unit" Para. 59 see "The manufacturing method includes a step of forming a pattern on a substrate (a wafer, a glass plate, a film-like substrate, or the like) using an imprint apparatus 100 . The manufacturing method further includes a step of processing the substrate on which the pattern has been formed. The processing step can include a step of removing the residual film of the pattern. The processing step can also include another known step such as a step of etching the substrate using the pattern as a mask." Examiner Note: This discloses the relevant context in which a composition or imprint material is formed on a substrate using a mold, and the formed material on the substrate is then evaluated or processed based on acquired image information.).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Riley and Terao to incorporate the teachings of Terao to train the model using images of a film of a composition formed on a substrate using a mold as the model input. Doing so would predictably improve evaluation performance by teaching the model with images from the same process which uses molds and film.
Regarding claim 16, Riley in view of Terao teaches The learning method according to claim 15.
In addition, Riley teaches A non-transitory computer-readable storage medium storing a program for causing a computer to execute the learning method according to claim 15. (Para. 43 see "The computer subsystems shown in FIG. 1 (as well as other computer subsystems described herein) may also be referred to herein as computer system(s). Each of the computer subsystem(s) or system(s) described herein may take various forms, including a personal computer system, image computer, mainframe computer system, workstation, network appliance, Internet appliance, or other device. In general, the term “computer system” may be broadly defined to encompass any device having one or more processors, which executes instructions from a memory medium. The computer subsystem(s) or system(s) may also include any suitable processor known in the art such as a parallel processor. In addition, the computer subsystem(s) or system(s) may include a computer platform with high speed processing and software, either as a standalone or a networked tool." Para. 44 see "computer subsystem 36 may be coupled to computer subsystem(s) 102 as shown by the dashed line in FIG. 1 by any suitable transmission media, which may include any suitable wired and/or wireless transmission media known in the art. Two or more of such computer subsystems may also be effectively coupled by a shared computer-readable storage medium (not shown).").
Allowable Subject Matter
Claim 8 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Regarding claim 8, Riley teaches wherein based on the region defining image, a part of an image is artificially added as the abnormality to the abnormality adding region of the reference image in the generating of the training image. (Para. 66 see "The reference images may be generated by imaging an actual specimen (as would be the case for die-to-die or cell-to-cell defect detection) or by simulating a reference image from a design for the specimen. The defect-free images may also be any images generated by imaging the specimen on which defect detection has been performed and in which no defect has been found." Para. 69 see "the image editing tools may include a rectangular clone selection (not shown). The image editing tools may be configured such that a user can drag a predetermined shape into a particular location in a specimen image and then modify the predetermined shape." Examiner Note: An existing image region from an image may be copied to the synthesized image.)
Neither Riley nor Terao teaches identifying a part of an image of the substrate before the film is formed.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Jeong et al. (WO 2023085479 A1) discloses an artificial intelligence-based material defect image generation method and defect detection system.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEXANDER VAUGHN whose telephone number is (571) 272-5253. The examiner can normally be reached M-F 11am-7pm.
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, JENNIFER MEHMOOD can be reached on (571) 272-2976. 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.
/ALEXANDER VAUGHN/Examiner, Art Unit 2675
/JENNIFER MEHMOOD/Supervisory Patent Examiner, Art Unit 2664
Prosecution Insights