Patents by Inventor Jianfa Zou
Jianfa Zou has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11676358Abstract: The present application discloses a method and apparatus for digitizing paper data, an electronic device and a storage medium, relating to fields of image processing and cloud computing, in particular to image recognition technologies. The method includes: determining a standard template according to an image to be processed and mark information corresponding to the image to be processed, wherein the image to be processed is obtained by photographing paper data and the standard template is used to represent a reference coordinate system of the image to be processed; recognizing graphic handwriting information comprised in the image to be processed; and generating digitized data corresponding to the image to be processed according to the graphic handwriting information and the standard template.Type: GrantFiled: June 16, 2021Date of Patent: June 13, 2023Assignee: Beijing Baidu Netcom Science Technology Co., Ltd.Inventors: Yabo Liu, Jianfa Zou, Lei Nie, Feng Huang
-
Patent number: 11615524Abstract: A product defect detection method and apparatus, an electronic device, and a storage medium are provided. A method includes: acquiring a multi-channel image of a target product; inputting the multi-channel image to a defect detection model, wherein the defect detection model includes a plurality of convolutional branches, a merging module and a convolutional headbranch; performing feature extraction on each channel in the multi-channel image by using the plurality of convolutional branches, to obtain a plurality of first characteristic information; merging the plurality of first characteristic information by using the merging module, to obtain second characteristic information; performing feature extraction on the second characteristic information by using the convolutional headbranch, to obtain third characteristic information to be output by the defect detection model; and determining defect information of the target product based on the third characteristic information.Type: GrantFiled: January 7, 2021Date of Patent: March 28, 2023Assignee: Beijing Baidu Netcom Science Technology Co., Ltd.Inventors: Ye Su, Lei Nie, Jianfa Zou, Feng Huang
-
Publication number: 20220036533Abstract: Provided are an image defect detection method and apparatus, an electronic device, a storage medium and a product. The method includes acquiring a to-be-detected image; obtaining a restored image corresponding to the to-be-detected image based on the to-be-detected image, at least one mask image group and a plurality of defect-free positive sample images, where each mask image group includes at least two binary images having a complementary relationship, and different mask image groups have different image sizes; and locating a defect of the to-be-detected image based on the to-be-detected image and each restored image. The solution solves the problem in which a related defect detection method requires numerous manual operations and has a low detection accuracy due to subjective factors of a worker.Type: ApplicationFiled: August 11, 2021Publication date: February 3, 2022Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Huihui XIAO, Lei NIE, Jianfa ZOU, Feng HUANG
-
Publication number: 20220004752Abstract: The present application discloses a method and apparatus for digitizing paper data, an electronic device and a storage medium, relating to fields of image processing and cloud computing, in particular to image recognition technologies. According to the solution provided by the present application, graphic handwriting information included in an image to be processed can be recognized, and the handwriting information can be combined with a reference coordinate system of the image to be processed to obtain digitized data, in this way, paper data can still be converted into digitized data even when graphic data is included in the paper data.Type: ApplicationFiled: June 16, 2021Publication date: January 6, 2022Inventors: Yabo Liu, Jianfa Zou, Lei Nie, Feng Huang
-
Publication number: 20210407062Abstract: A product defect detection method and apparatus, an electronic device, and a storage medium are provided. A method includes: acquiring a multi-channel image of a target product; inputting the multi-channel image to a defect detection model, wherein the defect detection model includes a plurality of convolutional branches, a merging module and a convolutional headbranch; performing feature extraction on each channel in the multi-channel image by using the plurality of convolutional branches, to obtain a plurality of first characteristic information; merging the plurality of first characteristic information by using the merging module, to obtain second characteristic information; performing feature extraction on the second characteristic information by using the convolutional headbranch, to obtain third characteristic information to be output by the defect detection model; and determining defect information of the target product based on the third characteristic information.Type: ApplicationFiled: January 7, 2021Publication date: December 30, 2021Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Ye SU, Lei NIE, Jianfa ZOU, Feng HUANG
-
Publication number: 20210073973Abstract: Provided are a method and an apparatus for component fault detection based on an image, and a specific implementation is: when it is determined that an image shot by an image pickup apparatus for a component to be tested with a first shooting parameter does not meet a preset condition, adjusting the first shooting parameter to a second shooting parameter; controlling the image pickup apparatus to shoot for the component to be tested with the second shooting parameter to obtain a first image that meets the preset condition; and performing fault detection on the component to be tested according to the first image. The image pickup apparatus can be adjusted in real time, so that the image can be used for fault detection only when meeting the preset condition, thereby the image is kept stable, and the accuracy rate of component fault identification based on an image is improved.Type: ApplicationFiled: May 11, 2020Publication date: March 11, 2021Inventors: Jianfa ZOU, Ye SU, Minghao LIU, Lei NIE, Jiabing LENG, Yawei WEN, Tehui HUANG, Yulin XU, Jiangliang GUO, Xu LI
-
Patent number: 10575006Abstract: A video data decoding device and method. The device has an entropy decoder, and a WPP status control module for selecting an operating status according to a syntax structure of a coding tree unit. The device further has a memory selector for controlling the operating status of a memory. The memory has one buffer memory and two update memories. When the number of columns of a row of coding tree units currently decoded is larger than three, the context data of the coding tree units currently decoded is written into the buffer memory and one of the update memories; and when it is determined that the context data of the coding tree units referred by a first coding tree unit in a next row of coding tree units is available when the next row of coding tree units starts to be parsed, the data in the buffer memory is replicated.Type: GrantFiled: April 21, 2016Date of Patent: February 25, 2020Assignee: ALLWINNER TECHNOLOGY CO., LTD.Inventors: Yongjie Fu, Jianfa Zou
-
Publication number: 20180234690Abstract: A video data decoding device and method. The device has an entropy decoder, and a WPP status control module for selecting an operating status according to a syntax structure of a coding tree unit. The device further has a memory selector for controlling the operating status of a memory. The memory has one buffer memory and two update memories. When the number of columns of a row of coding tree units currently decoded is larger than three, the context data of the coding tree units currently decoded is written into the buffer memory and one of the update memories; and when it is determined that the context data of the coding tree units referred by a first coding tree unit in a next row of coding tree units is available when the next row of coding tree units starts to be parsed, the data in the buffer memory is replicated.Type: ApplicationFiled: April 21, 2016Publication date: August 16, 2018Applicant: ALLWINNER TECHNOLOGY CO., LTD.Inventors: Yongjie FU, Jianfa ZOU
-
Patent number: 9916494Abstract: An example method for positioning feature points of a human face edge including fitting a profile edge curve of a human face edge in a human face image according to the human face image; calculating by using a preset human face edge feature point calculation model to obtain feature points of the human face edge in the human face image; calculating by using a preset convergence algorithm to obtain feature information of a convergence feature point corresponding to each feature point; determining respectively whether a distance from each feature point to the profile edge curve is greater than a distance from a respective corresponding convergence feature point to the profile edge curve; and determining whether a magnitude of overall position change of all the feature points of the human face edge in the human face image before and after the above determination is less than a preset threshold.Type: GrantFiled: March 24, 2016Date of Patent: March 13, 2018Assignee: Alibaba Group Holding LimitedInventors: Jianfa Zou, Ying Huang, Yan Chen
-
Publication number: 20160283780Abstract: An example method for positioning feature points of a human face edge including fitting a profile edge curve of a human face edge in a human face image according to the human face image; calculating by using a preset human face edge feature point calculation model to obtain feature points of the human face edge in the human face image; calculating by using a preset convergence algorithm to obtain feature information of a convergence feature point corresponding to each feature point; determining respectively whether a distance from each feature point to the profile edge curve is greater than a distance from a respective corresponding convergence feature point to the profile edge curve; and determining whether a magnitude of overall position change of all the feature points of the human face edge in the human face image before and after the above determination is less than a preset threshold.Type: ApplicationFiled: March 24, 2016Publication date: September 29, 2016Inventors: Jianfa Zou, Ying Huang, Yan Chen