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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 11/05/2024 is being considered by the examiner.
Drawings
The drawings are objected to because Fig. 5, element 506 recites “Re-modify the modified first image set based on the least one third image enhancement profile.” Applicant is advised to amend the element to “Re-modify the modified first image set based on the at least one third image enhancement profile.” Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claims 2, 3, and 17 are objected to because of the following informalities:
Claim 2 recites “extracting a first image parameters” in line 2; Applicant is advised to amend the line to “extracting a first image parameter”
Claim 2 recites “wherein the generating, by using the second AI-based model, at least one first image enhancement profile for the first image set comprises the generating, by using the second AI-based model, at least one first image enhancement profile for the first image set based on a determination that the first image set can be enhanced based on the extracted first image parameters.” The underlined portions appear to repeat the same limitation and impede understanding of the claim. Applicant is advised to amend the claim to improve clarity.
Claim 3 recites “extracting a predefined image parameters” in line 3; Applicant is advised to amend the line to “extracting a predefined image parameter”
Claim 17 recites “for which the detect detection process detected any defects" in line 5; Applicant is advised to amend the line to "for which the defect detection process detected any defects"
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 17 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 17 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being incomplete for omitting essential steps, such omission amounting to a gap between the steps. See MPEP § 2172.01. The omitted steps are: a step connecting the step of “generating a new first image-enhancement profile for the thus-reduced enhanced first image set” and “applying the defect detection process thereto” in the final limitation. Fig. 3 of the Drawings, and Specification paragraphs [0079]-[0081] disclose “Generate at least one first image enhancement profile for the modified first image set,” then “Modify the modified first image set based on the least one first image enhancement profile,” then “Re-performing the defect detection process on the re-modified first image set.” Claim 17 lacks the step of modifying or enhancing the thus-reduced enhanced first image set before applying the defect detection process, as recites in the specification. Applicant is advised to amend the final limitation to recite the method recited in the Specification, as the Specification does not disclose directly applying a defect detection process to an image-enhancement profile.
Allowable Subject Matter
Claims 1-16 are allowed.
Claim 17, which has been rejected above under 35 U.S.C. 112(b), is not rejected over prior art references, are objected to as being dependent upon a rejected base claim, but would be allowable if the above-described rejection of these claims under 35 U.S.C. 112(b) is overcome.
The following is an examiner’s statement of reasons for allowance:
Regarding Claim 1, Sherman et al. (US 2024/0428396 A1) in view of Yang et al. (US 12,707,940 B2) teaches “A method for detecting defects in semiconductor wafers, the method comprising:
receiving, from a user device or an imaging device, input images of the semiconductor wafers” (Sherman, [0080] discloses “A plurality of images of a semiconductor specimen acquired by an examination tool can be obtained (202)”);
“performing, by using a first Artificial Intelligence (AI)-based model, a first defect detection process on the input images to detect defects in the respective input images” (Sherman, [0080] discloses “The plurality of images can be processed (204) using a first ML model (e.g., the ML model 104) for defect detection, thereby obtaining, from the plurality of images, a set of images labeled with detected defects”; where a first ML model is a first artificial intelligence-based model);
“collecting, based on a result of the first defect detection process, (Sherman, [0080] discloses “The plurality of images can be processed (204) using a first ML model (e.g., the ML model 104) for defect detection, thereby obtaining, from the plurality of images, a set of images labeled with detected defects”);
modifying, by using a third AI-based model, the first image (Yang, column 4, lines 29-32 and lines 34-36 discloses “In step 504, an image enhancing model is used to enhance the low resolution images of the regions of the semiconductor wafer captured by the camera to produce enhanced images of the semiconductor wafer” and “The image enhancing model may include a machine learning model, e.g., a generative adversarial network (GAN)”; where an image enhancing model is a third AI-based model); “and
performing a second defect detection process on the modified first image set to detect previously undetected defects in the input images in the modified first image set” (Yang, column 4, lines 54-58 discloses “In step 506, a defect detection model is used to analyze for defects in the enhanced images provided by the image enhancing model”).
Although the cited prior art recites using a machine learning model to detect defects in semiconductor images, and recites using an image enhancing model to enhance low resolution images of a semiconductor wafer, the cited prior art does not explicitly teach “collecting, based on a result of the first defect detection process, a first image set and a second image set among the one or more input images, wherein the first image set includes those images among the input images for which no defect was detected in the first defect detection process,” “generating, by using the second AI-based model, at least one first image enhancement profile for the first image set” and “modifying, by using a third AI-based model, the first image set based on at least one first image enhancement profile.” As best understood in light of the specification, a first image enhancement profile is information that may be used to modify a first image set using an AI-based model, the enhancement profile itself generated using an AI-based model. Specification [0051] discloses “The generation of the image enhancement profile may include, for example, a restoration process, a de-noising process, a de-blurring process, and/or a resolution enhancement process, etc.”
Although Yang teaches an image enhancing model, Yang does not explicitly teach a separate AI-based model that generates information used to perform the image enhancing. Yang, Fig. 12 discloses how the image enhancing model is trained, but even under the broadest reasonable interpretation, Yang does not explicitly teach training the image enhancing model using a first image set that includes images for which no defect was detected.
PNG
media_image1.png
549
580
media_image1.png
Greyscale
Fig. 12 of Yang
Additionally, Sherman teaches a step of further processing (Step 206, “Train a second ML model using a second training set comprising at least part of the set of images labeled with detected defects”). However, Sherman teaches further processing images labeled with defects, and does not explicitly teach further processing on images for which no defect was detected, as required by Claim 1. Thus, although the cited prior art teaches multiple steps of image processing, filtering, and enhancing on images of semiconductor wafers in order to detect defects, none of the previously cited prior art explicitly teaches generating an image set of images for which no defect was detected, generating an enhancement profile based on these images using an AI-based mode, and modifying this image set based on the enhancement profile.
PNG
media_image2.png
535
628
media_image2.png
Greyscale
Fig. 2 of Sherman
Thus, none of the previously cited prior art, alone or on combination, provides a motivation to teach the ordered combination of “A method for detecting defects in semiconductor wafers, the method comprising: receiving, from a user device or an imaging device, input images of the semiconductor wafers; performing, by using a first Artificial Intelligence (AI)-based model, a first defect detection process on the input images to detect defects in the respective input images; collecting, based on a result of the first defect detection process, a first image set and a second image set among the one or more input images, wherein the first image set includes those images among the input images for which no defect was detected in the first defect detection process, and wherein the second image set includes those images among the input images for which any defects were detected in the first defect detection process; generating, by using the second AI-based model, at least one first image enhancement profile for the first image set; modifying, by using a third AI-based model, the first image set based on at least one first image enhancement profile; and performing a second defect detection process on the modified first image set to detect previously undetected defects in the input images in the modified first image set.”
Regarding Claim 10, Sherman et al. (US 2024/0428396 A1) in view of Yang et al. (US 12,707,940 B2) teaches “An apparatus for multi-level defect detection in semiconductor wafers, the system comprising:
a memory; and
one or more processors communicatively coupled with the memory” (Sherman, [0057] discloses “The processing circuitry 102 can comprise one or more processors (not shown separately) and one or more memories (not shown separately)”), “wherein the memory stores instructions configured to cause the one or more processors to perform a process comprising:
receiving input images of the semiconductor wafers” (Sherman, [0080] discloses “A plurality of images of a semiconductor specimen acquired by an examination tool can be obtained (202)”);
“performing, by using a first AI-based model, a defect detection process on the input images to detect defects in the input images” (Sherman, [0080] discloses “The plurality of images can be processed (204) using a first ML model (e.g., the ML model 104) for defect detection, thereby obtaining, from the plurality of images, a set of images labeled with detected defects”; where a first ML model is a first AI-based model);
based on a result of the defect detection process,(Sherman, [0080] discloses “The plurality of images can be processed (204) using a first ML model (e.g., the ML model 104) for defect detection, thereby obtaining, from the plurality of images, a set of images labeled with detected defects”);
modifying, by using a third AI-based model, the first image set, the modifying performed (Yang, column 4, lines 29-32 and lines 34-36 discloses “In step 504, an image enhancing model is used to enhance the low resolution images of the regions of the semiconductor wafer captured by the camera to produce enhanced images of the semiconductor wafer” and “The image enhancing model may include a machine learning model, e.g., a generative adversarial network (GAN)”; where an image enhancing model is a third AI-based model); “and
re-performing the defect detection process on the modified first image set to detect one or more previously undetected defects in the modified first image set” (Yang, column 4, lines 54-58 discloses “In step 506, a defect detection model is used to analyze for defects in the enhanced images provided by the image enhancing model”).
Although the cited prior art recites using a machine learning model to detect defects in semiconductor images, and recites using an image enhancing model to enhance low resolution images of a semiconductor wafer, the cited prior art does not explicitly teach “forming a first image set to include those of the input images for which no defects were detected” “generating, by using the second AI-based model, an image enhancement profile for the first image set” and “modifying, by using a third AI-based model, the first image set, the modifying performed according to the generated image enhancement profile.” As best understood in light of the specification, an image enhancement profile is information that may be used to modify a first image set using an AI-based model, the enhancement profile itself generated using an AI-based model. Specification [0051] discloses “The generation of the image enhancement profile may include, for example, a restoration process, a de-noising process, a de-blurring process, and/or a resolution enhancement process, etc.”
Although Yang teaches an image enhancing model, Yang does not explicitly teach a separate AI-based model that generates information used to perform the image enhancing. Yang, Fig. 12 discloses how the image enhancing model is trained, but even under the broadest reasonable interpretation, Yang does not explicitly teach training the image enhancing model using a first image set that includes images for which no defect was detected.
Additionally, Sherman teaches a step of further processing (Step 206, “Train a second ML model using a second training set comprising at least part of the set of images labeled with detected defects”). However, Sherman teaches further processing images labeled with defects, and does not explicitly teach further processing on images for which no defect was detected, as required by Claim 10. Thus, although the cited prior art teaches multiple steps of image processing, filtering, and enhancing on images of semiconductor wafers in order to detect defects, none of the previously cited prior art explicitly teaches generating an image set of images for which no defect was detected, generating an enhancement profile based on these images using an AI-based mode, and modifying this image set based on the enhancement profile.
Thus, none of the previously cited prior art, alone or on combination, provides a motivation to teach the ordered combination of “An apparatus for multi-level defect detection in semiconductor wafers, the system comprising: a memory; and one or more processors communicatively coupled with the memory, wherein the memory stores instructions configured to cause the one or more processors to perform a process comprising: receiving input images of the semiconductor wafers; performing, by using a first AI-based model, a defect detection process on the input images to detect defects in the input images; based on a result of the defect detection process, forming a first image set to include those of the input images for which no defects were detected and forming a second image set to include those of the input images for which any defects were detected; generating, by using the second AI-based model, an image enhancement profile for the first image set; modifying, by using a third AI-based model, the first image set, the modifying performed according to the generated image enhancement profile; and re-performing the defect detection process on the modified first image set to detect one or more previously undetected defects in the modified first image set.”
Regarding Claim 17, Sherman et al. (US 2024/0428396 A1) in view of Yang et al. (US 12,707,940 B2) teaches “A method comprising:
applying a defect detection process to a set of images of semiconductor wafers” (Sherman, [0080] discloses “A plurality of images of a semiconductor specimen acquired by an examination tool can be obtained (202).” Sherman, [0080] discloses “The plurality of images can be processed (204) using a first ML model (e.g., the ML model 104) for defect detection, thereby obtaining, from the plurality of images, a set of images labeled with detected defects”);
“dividing the input images into Sherman, [0080] discloses “The plurality of images can be processed (204) using a first ML model (e.g., the ML model 104) for defect detection, thereby obtaining, from the plurality of images, a set of images labeled with detected defects”);
applying an image-enhancement process to the first image set
applying the image-enhancement process to the second image set (Yang, column 4, lines 29-32 and lines 34-36 discloses “In step 504, an image enhancing model is used to enhance the low resolution images of the regions of the semiconductor wafer captured by the camera to produce enhanced images of the semiconductor wafer” and “The image enhancing model may include a machine learning model, e.g., a generative adversarial network (GAN)”);
“applying the defect detection process to the enhanced first image set and applying the defect detect process to the enhanced second image set” (Yang, column 4, lines 54-58 discloses “In step 506, a defect detection model is used to analyze for defects in the enhanced images provided by the image enhancing model”); “and
Although the cited prior art recites using a machine learning model to detect defects in semiconductor images, and recites using an image enhancing model to enhance low resolution images of a semiconductor wafer, the cited prior art does not explicitly teach “dividing the input images into a first image set consisting of those of the images for which the defect detection process did not detect any defects,” “determining a first image-enhancement profile based on the first image set and determining a second image-enhancement profile based on the second image set; applying an image-enhancement process to the first image set according to the first image-enhancement profile; applying the image-enhancement process to the second image set according to the second image-enhancement profile,” and “eliminating from the enhanced first image set any images thereof for which the second application of the defect detection process did not detect any defects, generating a new first image-enhancement profile for the thus-reduced enhanced first image set, and applying the defect detection process thereto.”
As best understood in light of the specification, an image enhancement profile is information that may be used to modify a first image set using an AI-based model, the enhancement profile itself generated using an AI-based model. Specification [0051] discloses “The generation of the image enhancement profile may include, for example, a restoration process, a de-noising process, a de-blurring process, and/or a resolution enhancement process, etc.”
Although Yang teaches an image enhancing model, Yang does not explicitly teach a separate AI-based model that generates information used to perform the image enhancing. Yang, Fig. 12 discloses how the image enhancing model is trained, but even under the broadest reasonable interpretation, Yang does not explicitly teach training the image enhancing model using a first image set that includes images for which no defect was detected.
Additionally, Sherman teaches a step of further processing (Step 206, “Train a second ML model using a second training set comprising at least part of the set of images labeled with detected defects”). However, Sherman teaches further processing images labeled with defects, and does not explicitly teach further processing on images for which no defect was detected, as required by Claim 17. Thus, although the cited prior art teaches multiple steps of image processing, filtering, and enhancing on images of semiconductor wafers in order to detect defects, none of the previously cited prior art explicitly teaches generating an image set of images for which no defect was detected, generating an enhancement profile based on these images using an AI-based mode, modifying this image set based on the enhancement profile, and “eliminating from the enhanced first image set any images thereof for which the second application of the defect detection process did not detect any defects, generating a new first image-enhancement profile for the thus-reduced enhanced first image set, and applying the defect detection process thereto.”
Thus, none of the previously cited prior art, alone or on combination, provides a motivation to teach the ordered combination of “A method comprising: applying a defect detection process to a set of images of semiconductor wafers; dividing the input images into a first image set consisting of those of the images for which the defect detection process did not detect any defects and a second image set consisting of those of the images for which the detect detection process detected any defects; determining a first image-enhancement profile based on the first image set and determining a second image-enhancement profile based on the second image set; applying an image-enhancement process to the first image set according to the first image-enhancement profile; applying the image-enhancement process to the second image set according to the second image-enhancement profile; applying the defect detection process to the enhanced first image set and applying the defect detect process to the enhanced second image set; and eliminating from the enhanced first image set any images thereof for which the second application of the defect detection process did not detect any defects, generating a new first image-enhancement profile for the thus-reduced enhanced first image set, and applying the defect detection process thereto.”
Dependent Claims 2-9 and 11-16 contain all allowable subject matter of their respective independent claims and thus are also allowable. Note that Claims 2, 3, and 17 are objected to, above.
Any comments considered necessary by applicant must be submitted no later than the payment of the issue fee and, to avoid processing delays, should preferably accompany the issue fee. Such submissions should be clearly labeled “Comments on Statement of Reasons for Allowance.”
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Lei et al. (US 2025/0166161 A1) discloses a method for improving wafer defect classification nuisance rate, using a multi-phase machine learning classifier to identify sets of defects into defect types.
Yonezawa (US 6928185 B2) discloses a defect inspection methods for a semiconductor wafer, including multiple defect inspection steps before determining a semiconductor wafer is defective.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CAROLINE TABANCAY DUFFY whose telephone number is (703)756-1859. The examiner can normally be reached Monday - Friday 8:00 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, Amandeep Saini can be reached at 5712723382. 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.
/CAROLINE TABANCAY DUFFY/Examiner, Art Unit 2662 /AMANDEEP SAINI/Supervisory Patent Examiner, Art Unit 2662
Prosecution Insights