Text recognition method and apparatus

By acquiring the image feature sequence of the text image to identify the text line orientation and selecting an appropriate text recognition model, the problem of high computational load in existing technologies is solved, and efficient and accurate text recognition is achieved.

CN115410200BActive Publication Date: 2026-02-06HUAWEI TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202110506059.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-05-10
Publication Date
2026-02-06
Estimated Expiration
2041-05-10

Smart Images

  • Figure CN115410200B_ABST
    Figure CN115410200B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of character recognition in the technical field of artificial intelligence, in particular to the technical field of optical character recognition, and provides a text recognition method, which comprises the following steps: obtaining a text image to be recognized, each character in the text image extending along a single direction; obtaining an image feature sequence according to the text image, wherein the image feature sequence comprises 1*n features, and n is a natural number; recognizing a text line orientation according to the image feature sequence; and recognizing each character in the text image according to the image feature sequence and the text line orientation. Image feature sequence image feature sequence. The technical scheme provided by the application can recognize the text in the text image with an arbitrary angle of the text line orientation through the image feature sequence, and can reduce the operation amount of recognition, thereby improving the efficiency of recognizing the text.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Character recognition method and device and terminal

    CN107527059A

  • Character sequence recognition method and device based on computer vision, equipment and medium

    CN111832561A