公开(公告)号：US20240054760A1

公开(公告)日：2024-02-15

申请号：US18378405

申请日：2023-10-10

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Jinxi XIANG ,  Sen YANG ,  Jun ZHANG ,  Dongxian JIANG ,  Yingyong HOU ,  Xiao HAN

IPC分类号： G06V10/762 ,  G06V10/40 ,  G06V10/764 ,  G06V10/26 ,  G06V10/77 ,  G06V10/80 ,  G06V10/776

CPC分类号： G06V10/762 ,  G06V10/40 ,  G06V10/764 ,  G06V10/267 ,  G06V10/7715 ,  G06V10/806 ,  G06V10/776

摘要： An image detection method and apparatus are disclosed. The method includes: performing feature extraction processing on the image to obtain a feature representation subset of the image; generating attention weights corresponding to the at least two sub-image features; performing weighting aggregation processing on the at least two sub-image features according to the attention weights to obtain a first feature vector; performing clustering sampling processing on the at least two sub-image features to obtain at least two classification clusters comprising sampled sub-image features; determining a block sparse self-attention for each of the sampled sub-image features according to the at least two classification clusters and a block sparse matrix; determining a second feature vector according to at least two block sparse self-attentions respectively corresponding to the at least two classification clusters; and determining a classification result of the image according to the first feature vector and the second feature vector.

公开(公告)号：US11902701B2

公开(公告)日：2024-02-13

申请号：US18058243

申请日：2022-11-22

申请人： FUJIFILM CORPORATION

发明人： Makoto Kobayashi ,  Tomoyuki Kawai ,  Ryo Hasegawa ,  Hitoshi Sakurabu

IPC分类号： H04N5/77 ,  G06T3/40 ,  H04N9/64 ,  G06V40/16 ,  H04N23/84 ,  H04N25/76 ,  G06V10/26

CPC分类号： H04N5/772 ,  G06T3/4015 ,  G06V10/26 ,  G06V40/161 ,  H04N9/64 ,  H04N23/843 ,  H04N25/76 ,  H04N2209/042

摘要： An imaging apparatus includes a storage portion that stores captured image data obtained by imaging a subject by an imaging element and is incorporated in the imaging element, an output portion that is incorporated in the imaging element, and a plurality of signal processing portions that are disposed outside the imaging element, in which the output portion includes a plurality of output lines each disposed in correspondence with each of the plurality of signal processing portions and outputs each of a plurality of pieces of image data into which the captured image data stored in the storage portion is divided, to a corresponding signal processing portion among the plurality of signal processing portions from the plurality of output lines, and any of the plurality of signal processing portions combines the plurality of pieces of image data.

公开(公告)号：US11902522B2

公开(公告)日：2024-02-13

申请号：US17789651

申请日：2020-12-28

申请人： ZTE Corporation

发明人： Junping Gao ,  Zhenfeng Cui ,  Zhen Hu

IPC分类号： G06V30/148 ,  H04N19/12 ,  G06V10/26 ,  G06F40/126 ,  G06V30/19 ,  G06V30/18 ,  G06V30/14

CPC分类号： H04N19/12 ,  G06F40/126 ,  G06V10/26 ,  G06V30/1448 ,  G06V30/153 ,  G06V30/18133 ,  G06V30/19093

摘要： A character restoration method and apparatus, a storage medium, and an electronic device are provided. The character restoration method includes: a character identifier of a character in a text region is determined, where the character identifier is used for uniquely identifying the character; and encoding is performed at least according to the character identifier, and encoded data is sent to a receiving end, where the encoded data is used for the receiving end to decode the encoded data and restore the character according to the character identifier obtained after decoding, that is, encoding is performed merely according to a small amount of information, and then the information is obtained by decoding, so as to restore the character.

公开(公告)号：US20240046665A1

公开(公告)日：2024-02-08

申请号：US18268630

申请日：2021-12-22

申请人： SHANGHAI BLOKS TECHNOLOGY CO., LTD

发明人： Chao GAO ,  Chenlu LIU ,  Jialiang ZHAO ,  Shanjun LI

IPC分类号： G06V20/60 ,  G06V10/22 ,  G06V10/26 ,  G06T7/90

CPC分类号： G06V20/60 ,  G06V10/225 ,  G06V10/267 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/30242 ,  G06T2207/30252

摘要： A method for determining a complete icon includes: acquiring an image, and delineating determination regions in a peripheral region of the image; scanning and counting a number of pixels of a first color corresponding to an icon in the whole image and a number of pixels of a second color corresponding to an auxiliary identifier in each determination region; determining, if the number of pixels of the first color is less than or equal to a first threshold, or the number of pixels of the second color in one or more determination regions is less than or equal to a second threshold, that the icon is incomplete; and determining, if the number of pixels of the first color is greater than the first threshold, and the number of pixels of the second color in each of the determination regions is greater than the second threshold, that the icon is complete.

公开(公告)号：US20240046630A1

公开(公告)日：2024-02-08

申请号：US18359774

申请日：2023-07-26

申请人： Micron Technology, Inc.

发明人： Abhishek Chaurasia ,  Shakti Nagnath Wadekar

IPC分类号： G06V10/82 ,  G06V10/80 ,  G06V10/77 ,  G06V10/764 ,  G06V10/26

CPC分类号： G06V10/82 ,  G06V10/806 ,  G06V10/7715 ,  G06V10/764 ,  G06V10/26

摘要： A system for optimizing a vision transformer block for use with mobile vision transformers utilized for tasks, such as image classification, segmentation, and objected detection is disclosed. The system includes incorporating a 1×1 convolutional layer in place of a 3×3 convolutional layer in a fusion block of the vision transformer block to reduce constraints on scaling neural network size. Additionally, the system includes fusing local and global representations in the fusion block of the vision transformer block instead of fusing input features and global representations. Furthermore, the system includes fusing input features in the fusion block by adding the input features to the output of the 1×1 convolutional layer of the fusion block. Moreover, the system includes substituting a 3×3 convolutional layer in the local representation block of the vision transformer block with a depthwise-separable 3×3 convolutional layer. The optimized transformer block enhances image classification, segmentation, and object detection.

公开(公告)号：US20240037930A1

公开(公告)日：2024-02-01

申请号：US17877159

申请日：2022-07-29

申请人： Rakuten Group, Inc.

发明人： Geethu JACOB ,  Vishal AGARWAL ,  Bjorn STENGER

IPC分类号： G06V10/96 ,  G06V10/94 ,  G06T7/50 ,  G06V10/774 ,  G06V10/764 ,  G06V10/26 ,  G06T3/40 ,  G06N3/08

CPC分类号： G06V10/96 ,  G06V10/95 ,  G06T7/50 ,  G06V10/7747 ,  G06V10/764 ,  G06V10/26 ,  G06T3/4046 ,  G06N3/08 ,  G06T2207/20081

摘要： A method, system, apparatus, and non-transitory computer-readable medium for image processing using a multi-task neural network framework may be provided. The method be performed by one or more processors and may include receiving an input image, and performing an image processing task based on the input image using the multi-task neural network framework, wherein the multi-task neural network framework is trained using a combination of task specific losses, the task specific losses including a plurality of first losses associated with the multi-task neural network framework and a plurality of second losses associated with a plurality of single-task neural network models. The method may also include generating an output of the image processing task based on up sampling an output of the multi-task neural network framework.

公开(公告)号：US20240034372A1

公开(公告)日：2024-02-01

申请号：US18256957

申请日：2021-08-26

申请人： Siemens Mobility GmbH

发明人： Benjamin Hartmann ,  Benoit Bleuze ,  Albi Sema ,  Irina Vidal Migallon ,  San-Yu Huang ,  Christoph Reinbothe

IPC分类号： B61L23/04 ,  B61L15/00 ,  G06V10/774 ,  G06V10/10 ,  G06V10/82 ,  G06V20/58 ,  G06V10/26 ,  G06T7/50

CPC分类号： B61L23/041 ,  B61L15/0072 ,  G06V10/774 ,  G06V10/16 ,  G06V10/82 ,  G06V20/58 ,  G06V10/26 ,  G06T7/50 ,  G06T2207/30261 ,  G06T2207/20081 ,  G06T2207/20084

摘要： A method creates a training data set for optical railway detection with integrated obstacle detection. The method includes the following steps of: providing first images of railways for rail vehicles, each first image having a representation of a railway; providing second images of objects, each second image containing a representation of at least one object; combining the first and second images; and generating third images containing the combined first and second images. Each third image contains a representation of a railway with at least one object, and a number of the third images forming the training data set for the optical railway detection with integrated obstacle detection.

公开(公告)号：US20240029458A1

公开(公告)日：2024-01-25

申请号：US18250877

申请日：2021-10-29

申请人： DICELLA SP. Z O.O.

发明人： Aleksandra KUBICA-MISZTAL ,  Krzysztof MISZTAL ,  Jacek HAJTO

IPC分类号： G06V20/69 ,  G06V10/36 ,  G06V10/20 ,  G06V10/86 ,  G06V10/26

CPC分类号： G06V20/698 ,  G06V20/695 ,  G06V10/36 ,  G06V10/255 ,  G06V10/86 ,  G06V10/273

摘要： A method for analysing microscopic images of a blood smear allowing to determine the number of thrombocytes in a tested sample. The present disclosure uses an algorithm which allows for differentiating between platelets from other blood cells (including erythrocytes), and then counts the quantity of thrombocytes (number/μl) and determines their size (μm). The method includes providing a grayscale microscopic image of platelets, segmenting and analysing the image, wherein the step of segmentation and analysis of the image comprises analysing light regions of the image and analysing dark regions of the image, including detecting distinctive regions in the image using a maximally stable external regions algorithm; calculating for each light and dark region identified its convex hull and filtering the results obtained by shape; removing nesting regions; identifying aggregates; classifying cells into platelets and other blood constituents; and determining the number of platelets and masks thereof.

公开(公告)号：US20240029428A1

公开(公告)日：2024-01-25

申请号：US17870632

申请日：2022-07-21

申请人： Sanjana Ryali ,  Sivani Ryali

发明人： Sanjana Ryali ,  Sivani Ryali

IPC分类号： G06V20/10 ,  G06V10/774 ,  G06V10/26 ,  G06V10/94 ,  G06V10/776

CPC分类号： G06V20/176 ,  G06V10/774 ,  G06V10/26 ,  G06V10/945 ,  G06V10/776

摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining whether a physical environment includes structural features that comply with accessibility guidelines. In one example method, input data, which can include image data representing an image of a particular portion of a physical environment, can be received from a client device. The image data can be input to a trained accessibility feature detection model, which can be trained to detect a particular structural feature and determine whether it meets a first accessibility guideline for the particular structural feature. The data output by the model can be used to determine whether the image data includes the particular structural feature that meets the first accessibility guideline, and based on this determination, an accessibility report can be generated and provided for display on the client device.

公开(公告)号：US20240020954A1

公开(公告)日：2024-01-18

申请号：US17812596

申请日：2022-07-14

申请人： ADOBE INC.

发明人： Sachin Kelkar ,  Ajinkya Gorakhnath Kale ,  Midhun Harikumar

IPC分类号： G06V10/774 ,  G06T5/00 ,  G06T7/194 ,  G06V10/771 ,  G06V10/776 ,  G06V10/26 ,  G06V10/75 ,  G06F16/532

CPC分类号： G06V10/774 ,  G06T5/005 ,  G06T7/194 ,  G06V10/771 ,  G06V10/776 ,  G06V10/267 ,  G06V10/759 ,  G06F16/532 ,  G06T2207/20081 ,  G06V2201/10

摘要： Systems and methods for image processing, and specifically for generating object-agnostic image representations, are described. Embodiments of the present disclosure receive a training image including a foreground object and a background, remove the foreground object from the training image to obtain a modified training image, inpaint a portion of the modified training image corresponding to the foreground object to obtain an inpainted training image, encode the training image and the inpainted training image using a machine learning model to obtain an encoded training image and an encoded inpainted training image, and update parameters of the machine learning model based on the encoded training image and the encoded inpainted training image.