DETAILED ACTION
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 .
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.
Claims 1, 15 and 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
A clustering technique is claimed, but the only mention of a clustering technique in the Specification is a dictionary learning technique (see par. 82). It is not clear how the claimed clustering technique is achieving the claimed elements.
Determining K mapping probability is claimed and the claims do not line up with the Specification regarding using a dictionary learning technique to determine the K mapping probability (see par. 82).
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-5, 7-13 and 15-20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Diego Carrera et al. (hereinafter Carrera) (“Defect Detection in SEM images of Nanofibrous Materials”).
Regarding claim 1: Carrera discloses receiving, by a controller including circuitry, a first image and a second image associated with the first image (Here, we present a novel solution to detect defects in nanofibrous materials by analyzing scanning electron microscope images. We employ an algorithm that learns, during a training phase, a model yielding sparse representations of the structures that characterize correctly produced nanofiborus materials. Defects are then detected by analyzing each patch of an input image and extracting features that quantitatively assess whether the patch conforms or not to the learned model. The proposed solution has been successfully validated over 45 images acquired from samples produced by a prototype electrospinning machine. The low computational times indicate that the proposed solution can be effectively adopted in a monitoring system for industrial production., Abstract); determining, using a clustering technique (Examiner is interpreting clustering technique to be dictionary learning) (In this paper, we present a novelty-detection algorithm, even though we refer to anomaly/defect since these terms are more appropriate to describe the considered application. We adopt an anomaly detection algorithm based on a dictionary yielding sparse representations, which are nowadays one of the leading models in image and signal processing applications [21], [43]. In particular, we pursue the approach in [19] to represent normal data, in which a dictionary is learned during an initial training phase. Then, test images are analyzed in a patch-wise manner, computing features that assess the conformance of each patch with the structures characterizing normal ones. Anomalies are then identified as outliers in the feature distribution. This approach proved to be particularly successful on image texture. A different anomaly detection algorithm that uses sparse representations is [24], where the anomalous data are identified during the sparse-coding stage by means of an ad hoc procedure. Convolutional-sparse models [44] were also shown to be effective in detecting anomalies, even though they are more computationally demanding than traditional patch-based models like those described in Section IV-A., section II C, third par.), N first feature descriptor(s) for L first pixel(s) in the first image and M second feature descriptor(s) for L second pixel(s) in the second image, wherein each of the L first pixel(s) is co-located with one of the L second pixel(s), and L, M, and N are positive integers (Section IV A and B); determining K mapping probability between a first feature descriptor of the N first feature descriptor(s) and each of K second feature descriptor(s) of the M second feature descriptor(s), wherein K is a positive integer (Section IV A and B and Fig. 2); and providing an output that indicates whether there is existence of an abnormal pixel representing a candidate defect on the sample based on a determination that one of the K mapping probabilities does not exceed a threshold value (Algorithm 1, item 7, threshold, p. 556) (dictionary learning framework, Abstract; Section II C third par.; Sections IV, A and B; Fig. 2).
Regarding claim 2: Carrera satisfies all the elements of claim 1. Carrera further discloses wherein each of the N first feature descriptor(s) represents a feature of a subset of the L first pixel(s), and each of the M second feature descriptor(s) represents a feature of a subset of the L second pixel(s) (Our dataset contains 45 SEM images (dimension 1024 × 696 pixels): five images are anomaly free, whereas 40 images contain anomalies of different size. For each image, we manually select all defects, defining the anomaly mask Ω that is used as a ground truth in our tests. Overall defects in these images are very small: on average they cover the 1.3% of the image, and only the 0.5% of the anomalies exceed the 2% of the image size., Section V, A, second paragraph).
Regarding claim 3: Carrera satisfies all the elements of claim 2. Carrera further discloses wherein the abnormal pixel is in the subset of the L first pixel(s) (Let us denote by s : X → R+ the SEM image depicting the nanostructures to analyze for anomaly detection purposes, where X ⊂ Z2 is the regular pixel grid corresponding to the image domain. The image intensity2 at pixel c ∈ X is denoted by s(c). Our goal is to locate anomalous regions in s; as such, the problem can be formulated as estimating the unknown anomaly mask Ω(c) = 0 if c falls inside a normal region 1 if c falls inside an anomalous region (1) which has to report as many anomalies as possible, independently of their dimension and shape. In particular, we are interested in estimating an anomaly mask Ω that 1) covers most of the anomalous regions in s and that 2) reports the largest number of anomalies, including the smallest ones., Section III).
Regarding claim 4: Carrera satisfies all the elements of claim 1. Carrera further discloses wherein the first image is an inspection image generated by an image inspection apparatus scanning the sample, the second image is a design layout image associated with the sample, and the abnormal pixel is in the first image (SEM images, Section V, A, pars. 1-2).
Regarding claim 5: Carrera satisfies all the elements of claim 1. Carrera further discloses wherein the first image is a design layout image associated with the sample (SEM image), the second image is an inspection image generated by an image inspection apparatus scanning the sample, and the abnormal pixel is in the second image (inspect samples by SEM imaging and detecting defects, Section II, B).
Regarding claim 7: Carrera satisfies all the elements of claim 4. Carrera further discloses wherein the image inspection apparatus comprises a charged-particle beam tool (Scanning Electron Microscope, Abstract) or an optical beam tool.
Regarding claim 8: Carrera satisfies all the elements of claim 1. Carrera further discloses wherein the clustering technique comprises a dictionary learning technique (dictionary learning framework, Abstract; Section II, C, third par.; Sections IV, A and B; Fig. 2).
Regarding claim 9: Carrera satisfies all the elements of claim 8. Carrera further discloses wherein determining the K mapping probability comprises: determining data representing a first set of image features and the N first feature descriptor(s) by inputting a first region of the first image to the dictionary learning technique (dictionary learning framework, Abstract; Section II, C, third par.; Sections IV, A and B; Fig. 2), wherein each of the N first feature descriptor(s) comprises data representing a linear combination of the first set of image features (dictionary learning framework, Abstract; Section II, C, third par.; Sections IV, A and B; Fig. 2); determining data representing a second set of image features and the M second feature descriptor(s) by inputting a second region of the second image to the dictionary learning technique (dictionary learning framework, Abstract; Section II, C, third par.; Sections IV, A and B; Fig. 2), wherein each of the M second feature descriptor(s) comprises data representing a linear combination of the second set of image features, and each pixel of the first region is co- located with one pixel of the second region; and determining the K mapping probability between the first feature descriptor and each of the K second feature descriptor(s) (dictionary learning framework, Abstract; Section II, C, third par.; Sections IV, A and B; Fig. 2).
Regarding claim 10: Carrera satisfies all the elements of claim 1. Carrera further discloses generating a visual representation for at least one of the K mapping probability, the N first feature descriptor(s), or the M second feature descriptor(s), wherein the visual representation comprises at least one of a histogram representing the K mapping probability, a first two-dimensional map representing the K mapping probability at each of the L first pixel(s), a second two-dimensional map representing the K mapping probability at each of the L second pixel(s), a third two-dimensional map representing overlay of the L first pixel(s) and the second two-dimensional map, or a fourth two-dimensional map representing overlay of the L second pixel(s) and the first two-dimensional map (Fig. 2 and Our only assumption is that, for training purposes, a set of normal (i.e., anomaly free) images T is given, while no training images containing anomalous regions are required. This is a fair assumption, since anomalous regions might be very different in shape, dimension, and appearance, and a training set might not encompass all possible anomalies that could occur during operations. In this sense, anomalies remain unknown and we detect as anomalous any region that do not conform the structure of normal data., Section III, last par.).
Regarding claim 11: Carrera satisfies all the elements of claim 1. Carrera further discloses wherein each of the K mapping probability represents a probability of mapping relationships between each pixel associated with the first feature descriptor and a pixel being co-located with the each pixel and being associated with one of the K second feature descriptor(s) (Section IV, A and B).
Regarding claim 12: Carrera satisfies all the elements of claim 1. Carrera further discloses wherein L is greater than one, and M, N, and K are greater than or equal to one (dictionary learning framework, Abstract; Section II C third par.; Sections IV, A and B; Fig. 2).
Regarding claim 13: Carrera satisfies all the elements of claim 1. Carrera further discloses further comprising: aligning the first image and the second image before determining the N first feature descriptor(s) and the M second feature descriptor(s) (dictionary learning framework, Abstract; Section II C third par.; Sections IV, A and B; Fig. 2).
Regarding claim 15: Arguments analogous to those stated in the rejection of claim 1 are applicable. Additionally, an image inspection apparatus configured to scan a sample and generate an inspection image of the sample is taught by Carrera (scanning electron microscope that scans images in order to detect defects, Abstract).
Regarding claim 16: Carrera satisfies all the elements of claim 15. Arguments analogous to those stated in the rejection of claim 2 are applicable.
Regarding claim 17: Carrera satisfies all the elements of claim 16. Arguments analogous to those stated in the rejection of claim 3 are applicable.
Regarding claim 18: Carrera satisfies all the elements of claim 15. Arguments analogous to those stated in the rejection of claim 4 are applicable.
Regarding claim 19: Carrera satisfies all the elements of claim 15. Arguments analogous to those stated in the rejection of claim 5 are applicable.
Regarding claim 20: Arguments analogous to those stated in the rejection of claim 1 are applicable. A non-transitory computer-readable medium is inherently taught as evidenced by scanning electron microscope and various memories stored therein.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 6 and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Carrera in view of Wu et al. (hereinafter Wu) (US 2006/0291714 A1).
Regarding claim 6: Carrera satisfies all the elements of claim 4. Carrera further discloses wherein the design layout image (SEM images, Section V, A, pars. 1-2)
Carrera fails to specifically address is generated based on a file in a graphic database system format, a graphic database system II format, an open artwork system interchange standard format, or a Caltech intermediate format.
Wu discloses is generated based on a file in a graphic database system format, a graphic
database system II format, an open artwork system interchange standard format, or a Caltech intermediate format (In another example, instead of using acquired image data to define the background proximate the defect, the defect location may be determined in the GDS file of the design pattern (decorated or un-decorated with RET features). A portion of the design pattern data in the GDS file proximate the defect may be selected. The background in the GDS file may be compared to other defective locations as is done with the reference die images. The additional locations can then be correlated to the defect location from the original inspection. The additional locations may also be designated for review (e.g., by SEM)., par. 83).
It would have been obvious to a person of ordinary skill in the art before the effective
filing date of the claimed invention to include is generated based on a file in a graphic database system format, a graphic database system II format, an open artwork system interchange standard format, or a Caltech intermediate format in order to determine the defect location in the GDS file of the design pattern as taught by Wu (par. 83).
Regarding claim 14: Carrera satisfies all the elements of claim 1. Carrera further discloses further comprising:
Carrera fails to specifically address providing a user interface for configuring a parameter.
Wu discloses providing a user interface for configuring a parameter (FIG. 6 is a screenshot illustrating one example of a user interface that can be used to sort defects detected by the methods described herein. In particular, a user will be able to choose which subgroups of background to use for binning of the defects, and FIG. 6 illustrates one possible user interface for selecting the subgroups. As shown in FIG. 6, the user interface includes Defects Flow box 12, which includes a number of options for the user. For example, Defects Flow box 12 includes Filtering by Priorities section 14. In this section, the user may select the defect priorities to use for filtering. The priorities may be selected individually by clicking on the boxes next to the priority numbers. Alternatively, the user may select all priorities or none of the priorities by clicking one of the buttons below the listing of the individual priorities., par. 100).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include providing a user interface for configuring a parameter in order to allow the user to sort according to their preferences as taught by Wu (par. 100).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHARLOTTE M BAKER whose telephone number is (571)272-7459. The examiner can normally be reached Mon - Fri 8:00-5:00.
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 at (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.
/CHARLOTTE M BAKER/Primary Examiner, Art Unit 2664
13 February 2026