公开(公告)号：US12003898B2

公开(公告)日：2024-06-04

申请号：US17954328

申请日：2022-09-28

申请人： Coretronic Corporation

发明人： Chun-Chieh Wang ,  Fan-Chieh Chang

IPC分类号： H04N9/31 ,  G01S7/4865 ,  G01S7/4915 ,  G01S17/08 ,  G01S17/89 ,  G06T5/80 ,  G06T7/60 ,  G06T7/80 ,  G06V10/24 ,  G06V30/16

CPC分类号： H04N9/3185 ,  G01S7/4865 ,  G01S7/4915 ,  G01S17/08 ,  G01S17/89 ,  G06T5/80 ,  G06T7/60 ,  G06V10/247 ,  G06V30/1607 ,  H04N9/3147 ,  H04N9/317

摘要： A projector and a projection method are provided. The projector includes a control device, a projection optical engine, a distance sensing device, and an image capturing device. The projection optical engine projects a first projection image to a projection surface according to first image data. The distance sensing device senses multiple distance parameters of a projection area. The image capturing device captures the first projection image to obtain a first captured image. The control device performs a keystone correction operation and a leveling correction operation on the first image data. The projection optical engine projects a second projection image to the projection surface according to the corrected first image data. The control device obtains a second captured image including the second projection image through the image capturing device, and analyzes the second captured image to project current projection image size information in the second projection image.

公开(公告)号：US11836266B2

公开(公告)日：2023-12-05

申请号：US18081539

申请日：2022-12-14

申请人： Redactable Inc.

发明人： Amanda Levay ,  Aleksandr Grinevskii

IPC分类号： G06F21/62 ,  G06V10/94 ,  G06V30/416 ,  G06V30/146 ,  G06V30/42 ,  G06V30/148 ,  G06V10/96 ,  G06V30/16

CPC分类号： G06F21/6218 ,  G06V10/95 ,  G06V10/96 ,  G06V30/1463 ,  G06V30/153 ,  G06V30/16 ,  G06V30/416 ,  G06V30/42

摘要： Systems and methods provide a deployable cloud-agnostic redaction container for performing optical character recognition and redacting information from a document using a cloud-based, guided redaction framework. An example method for document redaction includes receiving a plurality of documents and extracting pages from the plurality of documents. The method then determines, based on a load balancing criterion, a processing order for the pages extracted from the plurality of documents, and performs, based on the processing order, an optical character recognition process and a redaction process on the pages to generate redacted pages. The redacted pages are provided for transmission or storage to a cloud data management platform.

公开(公告)号：US20230222632A1

公开(公告)日：2023-07-13

申请号：US17570678

申请日：2022-01-07

申请人： SAP SE

发明人： Marek Polewczyk ,  Marco Spinaci

IPC分类号： G06T5/00 ,  G06V30/414 ,  G06V10/774 ,  G06V30/16

CPC分类号： G06T5/006 ,  G06V10/774 ,  G06V30/414 ,  G06V30/1607 ,  G06T2207/10008 ,  G06T2207/20081 ,  G06T2207/30176

摘要： A method may include determining, based at least on an image of a document, a plurality of text bounding boxes enclosing lines of text present in the document. A machine learning model may be trained to determine, based at least on the coordinates defining the text bounding boxes, the coordinates of a document bounding box enclosing the text bounding boxes. The document bounding box may encapsulate the visual aberrations that are present in the image of the document. As such, one or more transformations may be determined based on the coordinates of the document bounding box. The image of the document may be deskewed by applying the transformations. One or more downstream tasks may be performed based on the deskewed image of the document. Related methods and articles of manufacture are also disclosed.

公开(公告)号：US20230206668A1

公开(公告)日：2023-06-29

申请号：US18170902

申请日：2023-02-17

申请人： BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

发明人： Ruoyu GUO ,  Yuning DU ,  Chenxia LI ,  Qiwen LIU ,  Baohua LAI ,  Yanjun MA ,  Dianhai YU

IPC分类号： G06V30/19 ,  G06V30/18 ,  G06V30/16

CPC分类号： G06V30/19147 ,  G06V30/19173 ,  G06V30/18 ,  G06V30/16

摘要： The present disclosure provides a vision processing and model training method, device, storage medium and program product. A specific implementation solution is as follows: establishing an image classification network with the same backbone network as the vision model, performing a self-monitoring training on the image classification network by using an unlabeled first data set; initializing a weight of a backbone network of the vision model according to a weight of a backbone network of the trained image classification network to obtain a pre-training model, the structure of the pre-training model being consistent with that of the vision model, and optimize the weight of the backbone network by using real data set in a current computer vision task scenario, so as to be more suitable for the current computer vision task; then, training the pre-training model by using a labeled second data set to obtain a trained vision model.

公开(公告)号：US20230206659A1

公开(公告)日：2023-06-29

申请号：US18116582

申请日：2023-03-02

申请人： SK Telecom Co., Ltd.

发明人： Heeyul LEE ,  Chunghun KANG ,  YongSung KIM ,  Taewan KIM ,  Seungji YANG

IPC分类号： G06V20/62 ,  G06V30/16 ,  G06V30/19 ,  G06V20/70 ,  G06V30/148 ,  G06V30/18

CPC分类号： G06V20/625 ,  G06V20/70 ,  G06V30/16 ,  G06V30/18 ,  G06V30/153 ,  G06V30/19013 ,  G06T2207/30252 ,  G06T2210/12

摘要： There is provided a method of extracting characters from a license plate of a vehicle performed by a license plate character extraction device. The method comprises: converting a input image obtained by capturing the license plate of the vehicle into a grayscale image; generating a converted image based on a result of comparing a value of at least one pixel included in the grayscale image with a first average of values of pixels adjacent to the at least one pixel; generating a refined image based on a result of comparing the converted image with a binarized image obtained by binarizing the converted image; and extracting characters included in the refined image.

公开(公告)号：US11682221B1

公开(公告)日：2023-06-20

申请号：US17160572

申请日：2021-01-28

申请人： United Services Automobile Association (USAA)

发明人： Charles Lee Oakes, III ,  Randy Ray Morlen ,  Michael Frank Morris ,  Reynaldo Medina, III ,  Greg Alan Harpel ,  Gabriel Glenn Gavia ,  Bharat Prasad ,  Frank Kyle Major ,  Jeffrey Neal Pollack

IPC分类号： G06Q40/02 ,  G06V30/40 ,  G06Q20/04 ,  G06Q20/10 ,  G06V30/16 ,  H04N101/00 ,  H04N23/60 ,  H04N23/63

CPC分类号： G06V30/40 ,  G06Q20/04 ,  G06Q20/042 ,  G06Q20/108 ,  G06Q40/02 ,  G06V30/16 ,  H04N23/632 ,  H04N23/64 ,  H04N2101/00 ,  H04N2201/001 ,  H04N2201/0084 ,  H04N2201/0096

摘要： A digital camera processing system with software to manage taking photos with a digital camera. Camera software controls the digital camera. A downloaded software component controls the digital camera software and causes a handheld mobile device to perform operations. The operations may include instructing a user to have the digital camera take photos of a check; displaying an instruction on a display of the handheld mobile device to assist the user in having the digital camera take the photos; or assisting the user as to an orientation for taking the photos with the digital camera. The digital camera processing system may generate a log file including a bi-tonal image formatted as a TIFF image.

公开(公告)号：US20230102804A1

公开(公告)日：2023-03-30

申请号：US18077026

申请日：2022-12-07

申请人： BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

发明人： Xiyan LIU ,  Junjie CAI ,  Kai ZHONG ,  Jianzhong YANG ,  Deguo XIA ,  Tongbin ZHANG ,  Zhen LU

IPC分类号： G06V10/24 ,  G06V30/16 ,  G06V10/774 ,  G06V10/77

摘要： A method of rectifying a text image, a training method, an electronic device, and a medium, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision, deep learning technology, intelligent transportation and high-precision maps. An exemplary implementation includes: performing, based on a gating strategy, a plurality of first layer-wise processing on a text image to be rectified, so as to obtain respective feature maps of a plurality of layer levels, wherein each of the feature maps includes a text structural feature related to the text image to be rectified, and the gating strategy is configured to increase an attention to the text structural feature; and performing a plurality of second layer-wise processing on the respective feature maps of the plurality of layer levels, so as to obtain a rectified text image corresponding to the text image to be rectified.

公开(公告)号：US20220198814A1

公开(公告)日：2022-06-23

申请号：US17603139

申请日：2019-08-14

申请人： Hewlett-Packard Development Company, L.P.

发明人： Sebastien Tandel ,  Ricardo Ribani ,  Ricardo Farias Bidart Piccoli ,  Tiago de Padua

IPC分类号： G06V30/146 ,  G06V30/16

摘要： An example non-transitory computer-readable medium includes instructions executable by a processor to detect boundaries of a representation of a document page in a captured image, model the boundaries of the representation of the document page as nonlinear curves, use the nonlinear curves to transform pixels of the representation of the document page into pixels of a dewarped representation of the document page, and output a dewarped image based on the dewarped representation of the document page.

公开(公告)号：US20240362937A1

公开(公告)日：2024-10-31

申请号：US18766599

申请日：2024-07-08

申请人： ExlService Holdings, Inc.

发明人： Ankit Malviya ,  Shubhanshu Kumar Singh ,  Vishu Mittal ,  Anish Goswami ,  Chaithanya Manda ,  Saurabh Khanna ,  Sarika Pal

IPC分类号： G06V30/146 ,  G06V30/16 ,  G06V30/18 ,  G06V30/19

CPC分类号： G06V30/147 ,  G06V30/16 ,  G06V30/18 ,  G06V30/19147

摘要： A text recognition system causes a trained region encoder to determine a region of interest of an image file. The system modifies a first image associated with the first region of interest (e.g., parsed out from the first region) to generate a data augmentation entity that includes a modified image. Using a trained instance encoder, the system generates a first set of visual instances corresponding to the first region of interest image and a second set of visual instances corresponding to the data augmentation entity. The system generates the corresponding first and second sequences. By executing a self-supervised contrastive loss function on the first and second sequences, the system automatically updates a continual knowledge distillation model of the trained region encoder. The system provides the first sequence to an instance decoder to generate output text in response to the prompt.

公开(公告)号：US12106532B2

公开(公告)日：2024-10-01

申请号：US17929553

申请日：2022-09-02

申请人： CANON KABUSHIKI KAISHA

发明人： Reiji Misawa

IPC分类号： G06F3/12 ,  G06V10/24 ,  G06V30/14 ,  G06V30/16 ,  G06V30/244 ,  H04N1/00

CPC分类号： G06V10/242 ,  G06V30/1456 ,  G06V30/16 ,  G06V30/245 ,  H04N1/00824

摘要： An inspection apparatus selects at least one character area, in a first preview image obtained by reading and previewing a print product, sets a direction, for a character in the selected character area, registers the set direction and the character in the selected character area in association with each other, selects at least one character inspection area, in a second preview image obtained by reading and previewing a print product as an inspection target, sets a direction, for a character in the selected character inspection area, rotates the character inspection area to match the set direction, with the direction set for the character in the selected character area, performs character recognition, for the character in the rotated character inspection area, and inspects the character inspection area, based on a result of the character recognition and a result of recognizing the character in the selected character area.