Patents Examined by Xuemei G Chen
-
Patent number: 11508050Abstract: A method for performing automatic visual inspection includes: capturing visual information of an object using a scanning system including a plurality of cameras; extracting, by a computing system including a processor and memory, one or more feature maps from the visual information using one or more feature extractors; classifying, by the computing system, the object by supplying the one or more feature maps to a complex classifier to compute a classification of the object, the complex classifier including: a plurality of simple classifiers, each simple classifier of the plurality of simple classifiers being configured to compute outputs representing a characteristic of the object; and one or more logical operators configured to combine the outputs of the simple classifiers to compute the classification of the object; and outputting, by the computing system, the classification of the object as a result of the automatic visual inspection.Type: GrantFiled: December 19, 2019Date of Patent: November 22, 2022Assignee: PACKSIZE LLCInventors: Carlo Dal Mutto, Francesco Peruch, Alexander Ou, Robert Hayes
-
Patent number: 11508037Abstract: A method for denoising an image includes: receiving, by a processing circuit of a user equipment, an input image; supplying, by the processing circuit, the input image to a trained convolutional neural network (CNN) including a multi-scale residual dense block (MRDB), the MRDB including: a residual dense block (RDB); and an atrous spatial pyramid pooling (ASPP) module; computing, by the processing circuit, an MRDB output feature map using the MRDB; and computing, by the processing circuit, an output image based on the MRDB output feature map, the output image being a denoised version of the input image.Type: GrantFiled: September 2, 2020Date of Patent: November 22, 2022Assignee: Samsung Electronics Co., Ltd.Inventors: Zengli Yang, Long Bao, Shuangquan Wang, Dongwoon Bai, Jungwon Lee
-
Patent number: 11488375Abstract: A method for performing illumination color prediction on an image in a neural network model, comprising: inputting an image to the neural network model; extracting a semantic-based illumination color feature of the image and a statistical rule-based illumination color feature of the image; and predicting an illumination color of the image according to the semantic-based illumination color feature and the statistical rule-based illumination color feature.Type: GrantFiled: June 30, 2020Date of Patent: November 1, 2022Assignee: CANON KABUSHIKI KAISHAInventor: Qiao Wang
-
Patent number: 11468542Abstract: This disclosure addresses the single-image compressive sensing (CS) and reconstruction problem. A scalable Laplacian pyramid reconstructive adversarial network (LAPRAN) facilitates high-fidelity, flexible and fast CS image reconstruction. LAPRAN progressively reconstructs an image following the concept of the Laplacian pyramid through multiple stages of reconstructive adversarial networks (RANs). At each pyramid level, CS measurements are fused with a contextual latent vector to generate a high-frequency image residual. Consequently, LAPRAN can produce hierarchies of reconstructed images and each with an incremental resolution and improved quality. The scalable pyramid structure of LAPRAN enables high-fidelity CS reconstruction with a flexible resolution that is adaptive to a wide range of compression ratios (CRs), which is infeasible with existing methods.Type: GrantFiled: January 17, 2020Date of Patent: October 11, 2022Assignee: ARIZONA BOARD OF REGENTS ON BEHALF OF ARIZONA STATE UNIVERSITYInventors: Fengbo Ren, Kai Xu, Zhikang Zhang
-
Patent number: 11460394Abstract: The present invention provides a corrosive environment monitoring method capable of short-term to long-term identification of the type of corrosive gas, without requiring a power source such as a commercial power source or a storage battery, in a narrow place inside an equipment housing of an electric or electronic device to be evaluated.Type: GrantFiled: January 29, 2019Date of Patent: October 4, 2022Assignee: Hitachi, Ltd.Inventor: Rintarou Minamitani
-
Patent number: 11461881Abstract: A method for processing images comprising: capturing a plurality of degraded images of a first real-world environment with a first sensor; processing each degraded image with a first, untrained convolutional neural network, via a Deep Image Prior approach, to obtain a plurality of clean images, wherein each clean image corresponds to a degraded image; pairing each clean image with its corresponding degraded image to create a plurality of degraded/clean image pairs; training, via a supervised learning approach, a machine learning model to learn a function for converting degraded images into restored images based on the plurality of degraded/clean image pairs; capturing a second plurality of degraded images of a second real-world environment; and using the trained machine learning model to convert the second plurality of degraded images into restored images based on the learned function.Type: GrantFiled: November 25, 2020Date of Patent: October 4, 2022Assignee: United States of America as represented by the Secretary of the NavyInventors: Shibin Parameswaran, Martin Thomas Jaszewski
-
Patent number: 11455813Abstract: Systems and methods are provided for producing a road layout model. The method includes capturing digital images having a perspective view, converting each of the digital images into top-down images, and conveying a top-down image of time t to a neural network that performs a feature transform to form a feature map of time t. The method also includes transferring the feature map of the top-down image of time t to a feature transform module to warp the feature map to a time t+1, and conveying a top-down image of time t+1 to form a feature map of time t+1. The method also includes combining the warped feature map of time t with the feature map of time t+1 to form a combined feature map, transferring the combined feature map to a long short-term memory (LSTM) module to generate the road layout model, and displaying the road layout model.Type: GrantFiled: November 12, 2020Date of Patent: September 27, 2022Inventors: Buyu Liu, Bingbing Zhuang, Samuel Schulter, Manmohan Chandraker
-
Patent number: 11455518Abstract: Systems and methods are described for user classification with semi-supervised machine learning. The systems and methods may include receiving user information for a first set of users, receiving survey data for a second set of users wherein the second set of users is a proper subset of the first set of users, training a first neural network and a second neural network based on the second set of users, mapping the user information for the first set of users to the embedding space using the first neural network, predicting category membership propensities for the first set of users using a low-density separation algorithm on the user information for the first set of users mapped to the embedding space, updating the first neural network and the second neural network based on the prediction, and reclassifying the first set of users based on the updated first neural network and the updated second neural network.Type: GrantFiled: November 12, 2019Date of Patent: September 27, 2022Assignee: ADOBE INC.Inventors: Michael Burkhart, Kyle Shan
-
Patent number: 11449702Abstract: The present disclosure relates to a system, method and non-transitory computer readable medium for reverse image searching. The system includes a storage device storing a set of instructions; and one or more processors in communication with the storage device. When executing the set of instructions, the one or more processors: obtain a target part of reference image features of a reference image; obtain a target part of target image features of a target image; determine, based on the target part of the reference image features and the target part of the target image features, whether the target image is similar to the reference image; and mark, upon a determination that the target image is similar to the reference image, the target image as a similar image of the reference image.Type: GrantFiled: January 22, 2020Date of Patent: September 20, 2022Assignee: ZHEJIANG DAHUA TECHNOLOGY CO., LTD.Inventor: Yufei Chen
-
Patent number: 11443170Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes obtaining a batch of labeled training items and a batch of unlabeled training items; processing the labeled training items and the unlabeled training items using the neural network and in accordance with current values of the network parameters to generate respective embeddings; determining a plurality of similarity values, each similarity value measuring a similarity between the embedding for a respective labeled training item and the embedding for a respective unlabeled training item; determining a respective roundtrip path probability for each of a plurality of roundtrip paths; and performing an iteration of a neural network training procedure to determine a first value update to the current values of the network parameters that decreases roundtrip path probabilities for incorrect roundtrip paths.Type: GrantFiled: November 15, 2017Date of Patent: September 13, 2022Assignee: Google LLCInventors: Philip Haeusser, Alexander Mordvintsev
-
Patent number: 11443414Abstract: A method of optimising an image signal processor (ISP), which is to be used to process sensor image data generating output image data. The method may include obtaining sensor image data; processing the sensor image data according to one or more ISP settings to produce output image data; producing quality metric data associated with the output image data and optimising the one or more ISP settings based on the quality metric data.Type: GrantFiled: October 20, 2020Date of Patent: September 13, 2022Assignee: Arm LimitedInventors: Maxim Novikov, James Stuart Imber, Yury Khrustalev, David Hanwell
-
Patent number: 11429824Abstract: A system, article, and method of deep supervision object detection for reducing resource usage is provided for image processing and that uses depth-wise dense blocks.Type: GrantFiled: September 11, 2018Date of Patent: August 30, 2022Assignee: Intel CorporationInventors: Jianguo Li, Jiuwei Li, Yuxi Li
-
Patent number: 11410309Abstract: The present disclosure provides a computer-implemented method, a device, and a computer program product for deep lesion tracker. The method includes inputting a search image into a first three-dimensional DenseFPN (feature pyramid network) of an image encoder and inputting a template image into a second three-dimensional DenseFPN of the image encoder to extract image features; encoding anatomy signals of the search image and the template image as Gaussian heatmaps, and inputting the Gaussian heatmap of the template image into a first anatomy signal encoders (ASE) and inputting the Gaussian heatmap of the search image into a second ASE to extract anatomy features; inputting the image features and the anatomy features into a fast cross-correlation layer to generate correspondence maps, and computing a probability map according to the correspondence maps; and performing supervised learning or self-supervised learning to predict a lesion center in the search image.Type: GrantFiled: March 26, 2021Date of Patent: August 9, 2022Assignee: PING AN TECHNOLOGY (SHENZHEN) CO., LTD.Inventors: Jinzheng Cai, Youbao Tang, Ke Yan, Adam P Harrison, Le Lu
-
Patent number: 11410281Abstract: A processor performing postprocessing obtains an input image containing both bright and dark regions. The processor obtains a threshold between a first pixel value of the virtual production display and a second pixel value of the virtual production display. The processor modifies the region according to predetermined steps producing a pattern unlikely to occur within the input image, where the pattern corresponds to a difference between the original pixel value and the threshold. The processor can replace the region of the input image with the pattern to obtain a modified image. The virtual production display can present the modified image. A processor performing postprocessing detects the pattern within the modified image displayed on the virtual production display. The processor calculates the original pixel value of the region by reversing the predetermined steps. The processor replaces the pattern in the modified image with the original pixel value.Type: GrantFiled: November 30, 2021Date of Patent: August 9, 2022Assignee: Unity Technologies SFInventors: Joseph W. Marks, Luca Fascione, Kimball D. Thurston, III, Millie Maier, Kenneth Gimpelson, Dejan Momcilovic, Keith F. Miller, Peter M. Hillman, Jonathan S. Swartz
-
Patent number: 11393248Abstract: Disclosed are a data detection method and device, a computer equipment, and a storage medium. The method includes: obtaining a designated identification picture including a human face; correcting the designated identification picture to be placed in a preset standard posture to obtain an intermediate picture; inputting the intermediate picture into a preset face feature point detection model to obtain multiple face feature points; calculating a cluster center position of the face feature points, and generating a minimum bounding rectangle of the face feature points; retrieving a standard identification picture from a preset database; scaling the standard identification picture in proportion to obtain a scaled picture; overlapping a reference center position in the scaled picture and a cluster center position in the intermediate picture, so as to obtain an overlapping part in the intermediate picture; and marking the overlapping part as an identification body of the designated identification picture.Type: GrantFiled: June 29, 2020Date of Patent: July 19, 2022Assignee: PING AN TECHNOLOGY (SHENZHEN) CO., LTD.Inventor: Jinlun Huang
-
Patent number: 11386538Abstract: Provided are an image processing apparatus, an image processing method, and a storage medium that can determine an anomaly while reducing influence of an individual difference of images. The image processing apparatus includes: a first generation unit that generates a first estimation image including at least a predetermined region of an inspection target by using a part of an inspection image including the inspection target; a second generation unit that estimates a difference between the first estimation image and the inspection image to generate a second estimation image by using the part of the inspection image; a comparison unit that compares the first estimation image with the inspection image; and an output unit that outputs a comparison result obtained by the comparison unit, and the comparison unit compares a difference between the first estimation image and the inspection image with the second estimation image.Type: GrantFiled: January 21, 2019Date of Patent: July 12, 2022Assignee: NEC CORPORATIONInventor: Shinichiro Yoshida
-
Patent number: 11386580Abstract: A system, device, and a method for guiding a user to comply with one or more application-specific requirements by using sequentially two or more neural networks run on one more video frame of a scene to detect at least one requirement of the one or more application-specific requirements. Upon the detection result, the application guides a user to adjust the scene based on the detection until the scene is adjusted to meet the application-specific requirements.Type: GrantFiled: August 13, 2021Date of Patent: July 12, 2022Assignee: GOODSIZE INC.Inventors: Dmitrii Ulianov, Sergei Sherman, Ilya Krotov
-
Patent number: 11381737Abstract: An image quality of a captured image captured by a camera is adjusted to be close to a predetermined image quality. A first image quality evaluation value is obtained on the basis of developed image data obtained by performing development processing on captured image data. An image quality parameter group in the development processing is obtained to decrease a difference between the first image quality evaluation value and a second image quality evaluation value serving as a reference. Alternatively, a plurality of first image quality evaluation values is obtained on the basis of a plurality of pieces of developed image data obtained by performing development processing on each of a plurality of pieces of captured image data. An image quality parameter group in the development processing is obtained to decrease a difference between each of the plurality of first image quality evaluation values and a second image quality evaluation value.Type: GrantFiled: March 19, 2019Date of Patent: July 5, 2022Assignee: SONY CORPORATIONInventor: Daisuke Nakao
-
Patent number: 11373095Abstract: Machine learning multiple features of an item depicted in images. Upon accessing multiple images that depict the item, a neural network is used to machine train on the plurality of images to generate embedding vectors for each of multiple features of the item. For each of multiple features of the item depicted in the images, in each iteration of the machine learning, the embedding vector is converted into a probability vector that represents probabilities that the feature has respective values. That probability vector is then compared with a value vector representing the actual value of that feature in the depicted item, and an error between the two vectors is determined. That error is used to adjust parameters of the neural network used to generate the embedding vector, allowing for the next iteration in the generation of the embedding vectors. These iterative changes continue thereby training the neural network.Type: GrantFiled: December 23, 2019Date of Patent: June 28, 2022Inventors: Oren Barkan, Noam Razin, Noam Koenigstein, Roy Hirsch, Nir Nice
-
Patent number: 11367169Abstract: Disclosed herein is a method for processing a picture of an automatic driving vehicle. The method for processing a picture of an automatic driving vehicle according to an embodiment of the present disclosure includes obtaining a first image from a camera while a vehicle on which the camera is driving, generating a prediction signal for predicting a sign of occurrence of White-Out from the first image, when a quantity of light which is a threshold brightness or higher from the first image, storing the first image during a first period when the prediction signal is generated, and predicting and correcting a second image based on the first image stored during the first period and a correction model, when the second image in which the White-Out occurs in the first image is detected on a specific time during the first period, and the correction model is a result of learning the second image by processing high dynamic range (HDR) image.Type: GrantFiled: April 26, 2019Date of Patent: June 21, 2022Assignee: LG ELECTRONICS INC.Inventor: Jonghoon Chae