Patents by Inventor Lemeng PAN

Lemeng PAN 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).

  • Method, apparatus, and system for recognizing text in image
    Patent number: 12299399
    Abstract: A method for recognizing a text in an image includes: obtaining a plurality of recognition results of a to-be-recognized text in an image according to a plurality of recognition methods (S201); obtaining semantic information of the recognition results (S202); obtaining feature information of the image, where the feature information of the image can represent information around the to-be-recognized text in the image (S203); and determining a target recognition result of the to-be-recognized text from the plurality of recognition results based on the feature information of the image and the semantic information of the plurality of recognition results (S204). According to the method, accuracy of determining the most accurate recognition result from the plurality of recognition results can be improved, that is, a precise recognition result can be obtained.
    Type: Grant
    Filed: May 10, 2022
    Date of Patent: May 13, 2025
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Lin Du, Alfred Chixiong Shen, Lemeng Pan
  • METHOD, APPARATUS, AND SYSTEM FOR RECOGNIZING TEXT IN IMAGE
    Publication number: 20220262151
    Abstract: A method for recognizing a text in an image includes: obtaining a plurality of recognition results of a to-be-recognized text in an image according to a plurality of recognition methods (S201); obtaining semantic information of the recognition results (S202); obtaining feature information of the image, where the feature information of the image can represent information around the to-be-recognized text in the image (S203); and determining a target recognition result of the to-be-recognized text from the plurality of recognition results based on the feature information of the image and the semantic information of the plurality of recognition results (S204). According to the method, accuracy of determining the most accurate recognition result from the plurality of recognition results can be improved, that is, a precise recognition result can be obtained.
    Type: Application
    Filed: May 10, 2022
    Publication date: August 18, 2022
    Inventors: Lin DU, Alfred Chixiong SHEN, Lemeng PAN