Detailed Action
1. Claims 1-4 are pending in this Application.
Notice of Pre-AIA or AIA Status
2. 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 § 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 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.
3. Claims 1 and 3 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by
Zhu et al., (hereafter Zhu), “A Method for Surface Defect Detection of Tempered Glass Based on Polarization Characteristics and Unsupervised Learning”, 2024 China Automation, conference, IEEE 2024, pub. 2024.
As to claim 1, Zhu teaches A system for detecting surface defects in an irregular reflective surface (Abstract, A Method for Surface Defect Detection of Tempered Glass Based on Polarization Characteristics and Unsupervised Learning) comprising:
a polarization camera, arranged to provide images of the surface, the images representing multiple polarization angles from the surface (Fig.3, page 2 left col., section II, page 3 left col., section III 1st par., A system 1st par, using a linear polarizer, 1/4 wave plate, and CCD camera collects light reflected from dust and defects. This setup extracts polarization features to tell dust apart from defects. The Mueller matrix describes how media change light waves based on wavelength and angles of incidence in and refraction or …);
a feature extraction process programmed to extract features from the images (page 2 Section B left col., 1st par., unsupervised learning surface anomaly detection method is trained on normal images. In the training stage, the feature vectors of the normal samples are extracted and a suitable distribution is constructed; in the inference stage, the feature vectors of the image to be detected are extracted …),
the features being one or more of the following: Angle of Linear Polarization (AOL)
thereby providing defect feature data (As is shown in Fig 2, after inputting two grayscale images with different polarization states into the polarization feature extraction module, extracting the grayscale values of the images and then divide them to get the polarization feature map Ip, and input the polarization feature map into the Fast Flow model, which can locate the anomalies in the images and distinguish the dust from the defects), and a neural network trained to receive defect feature data, to process the defect feature data, and to provide output indicating a defect in the surface (Figs.1-2, page 2 Section B 2nd- 3rd pars., As is shown in Fig 2, after inputting two grayscale images with different polarization states into the polarization feature extraction module, extracting the grayscale values of the images and then divide them to get the polarization feature map Ip, and input the polarization feature map into the Fastflow model, which can locate the anomalies in the images and distinguish the dust from the defect, wherein the unsupervised learning method used in this paper is Fastflow.).
As to claim 3, Zhu teaches the neural network is a convolutional neural network (Fig. 2, page 2 Section B 2nd- 3rd pars., The unsupervised learning method that apply Fastflow, wherein the Fastflow uses 3×3 and 1×1 convolutional cores. Thus, unsupervised learning model is convolutional neural network).
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 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.
4. Claim 2 and 4 rejected under 35 U.S.C. 103 as being unpatentable over
Zhu, “A Method for Surface Defect Detection of Tempered Glass Based on Polarization Characteristics and Unsupervised Learning”, in view of ,Javier et al., ( hereafter Javier), Sensor 2021, pub. 12/31/2021.
Regarding claim 2 , while Zhu teaches claim 1, but fails to teach claim 2.
On the other hand, in the same field of endeavor tan optical system that uses polarization of light to detect defect of coated paperboard based on image data of Javier teaches the polarization camera is a split-pixel polarization camera ( page 3 1st par., Javier teaches high-resolution pixelated camera system (i.e. split-pixel polarization camera). Javier specifically teaches a method of measuring the polarization properties of polyethylene (PE)-coated paperboard and uncoated substrates using a high-resolution pixelated camera system instead of standard point measurements, enabling full, spatially resolved polarization analysis. The split-pixel polarization camera (often called a pixelated polarization camera))
It would have been obvious to a person of ordinary skill in the art before the effective
filing date of the claimed invention to replace the standard CCD camera with a linear polarizer and a quarter-wave plate taught by Zhu with the pixelated polarization camera taught by Javier.
The suggestion and motivation for doing this would have been that Javier's camera allows users of Zhu to instantly capture full Stokes parameters (linear and circular polarization) in real-time on every shot, eliminating the motion blur and manual rotation limits of sequential filter setups while reducing glare and reflections in fast-moving scenes.
Regarding claim4 , while Zhu teaches claim 1, but fails to teach claim 4.
On the other hand Javier teaches the surface is a surface of packaging ( Fig.1, page 3 1st par., Javier specifically teaches a method of measuring the polarization properties of polyethylene (PE)-coated paperboard and uncoated substrates using a high-resolution pixelated camera system instead of standard point measurements, enabling full, spatially resolved polarization analysis.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Javier’s surface-defect and coating-discontinuity detection method into Zhu’s tempered glass inspection system, because both address non-destructive optical quality control for sheet-like manufactured substrates with functional outer finishes, and applying Javier’s real-time scanning analytics would yield predictable automated defect resolution.
Prior art not used in rejections but pertinent to the claims or disclosure.
a. “Surface Inspection Sensor”, US 20220381556 A1, pub., 12/01/2022, to Yacoubian; Aras, disclosed:
digital distortion correction is achieved using neural computation such as training a neural network to transform a distorted image to an expected image and applying the same computation steps to a defect map to produce a distortion free defect map (see [0121]).
FIG. 22 is a pictorial block diagram illustrating a schematic of inspection unit 2200 for detecting defects using inspection apparatus combined with a projected pattern for image distortion correction, combined with position determination to produce a defect map 2240 of the entire inspected object or structure 2216. The sensor head 2201 contains pattern generator 1800 depicted in FIG. 18 that projects a pattern onto the inspected surface. The sensor head 2201 is connected to control and processing electronics 2212 (see [0122])
In alternative embodiments, sensor arrangements described herein use multiple polarization angle measurements using pixelated polarizers in front of the camera (see[0162]) .
b. “Polarized Capture Device For Discriminating Features Of Objects” JP 2022547646 A pub. 11/15/2022, disclosed:
In one embodiment, information obtained from two raw images (or two sets of image data) S120 and S121 captured by two polarization image sensors 120 and 121 are used by feature extractor 170 to It is possible to extract features or characteristics of Various algorithms can be implemented in feature extractor 170 to extract features. In some embodiments, an unsupervised learning method (e.g., a machine learning method) such as a K-means cluster approach is implemented in feature extractor 170 and can include, for example, DOLP and/or AOLP values ( see page 9 3rd par.,).
Polarization capture devices or systems according to various embodiments of the present invention have various applications in many fields, all of which are within the scope of the present invention. For example, such polarization capture devices or systems are useful for target detection and identification, material inspection, stress inspection and visualization, defect detection, image contrast enhancement, transparent object detection, surface reflection reduction, depth mapping, 3D surface reconstruction, robotics It can be implemented in other systems for vision, biology, etc. (see )
Polarization capture devices or systems according to various embodiments of the present invention have various applications in many fields, all of which are within the scope of the present invention. For example, such polarization capture devices or systems are useful for target detection and identification, material inspection, stress inspection and visualization, defect detection, image contrast enhancement, transparent object detection, surface reflection reduction, depth mapping, 3D surface reconstruction, robotics It can be implemented in other systems for vision, biology, etc. Several exemplary implementations of polarization capture devices or systems in near-eye displays (“NEDs”) are described below(see page 15 3rd par.,)
(detect$3 or determin$3 or obtain$3 or identify$3 or sens$4)
identifying
Contact Information
Any inquiry concerning this communication or earlier communication from the examiner should be directed to Mekonen Bekele whose telephone number is (469) 295-9077.The examiner can normally be reached on Monday -Friday from 9:00AM to 6:50 PM Eastern Time.
If attempt to reach the examiner by telephone are unsuccessful, the examiner’s supervisor Eng, George can be reached on (571) 272-7495.The fax phone number for the organization where the application or proceeding is assigned is 571-237-8300. Information regarding the status of an application may be obtained from the patent Application Information Retrieval (PAIR) system. Status information for published application may be obtained from either Private PAIR or Public PAIR.
Status information for unpublished application is available through Privet PAIR only.
For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have question on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866.217-919 (tool-free)
//MEKONEN T BEKELE/ Primary Examiner, Art Unit 2699
Prosecution Insights