- 专利标题: Methods and systems for structured text detection, and non-transitory computer-readable medium
-
申请号: US16052584申请日: 2018-08-01
-
公开(公告)号: US10937166B2公开(公告)日: 2021-03-02
- 发明人: Donglai Xiang , Yan Xia
- 申请人: BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD
- 申请人地址: CN Beijing
- 专利权人: BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD
- 当前专利权人: BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD
- 当前专利权人地址: CN Beijing
- 代理机构: Syncoda LLC
- 代理商 Feng Ma
- 优先权: CN201610561355.7 20160715
- 主分类号: G06F40/279
- IPC分类号: G06F40/279 ; G06K9/00 ; G06K9/46 ; G06K9/62 ; G06N3/08 ; G06T7/11 ; G06N3/04 ; G06F40/186 ; G06T7/70 ; G06N5/04 ; G06T3/40 ; G06T3/60
摘要:
A method for structured text detection includes: receiving, by a convolutional neural network, a to-be-detected image and at least one character region template, the to-be-detected image includes structured text, the at least one character region template includes locations of N first character regions with N being an integer equal to or greater than 1, and the location of each first character region is obtained based on locations of second character regions corresponding to the each first character region in M sample images that are of the same type as the to-be-detected image, where M is an integer equal to or greater than 1; and obtaining, by the convolutional neural network, an actual location of the structured text in the to-be-detected image according to the at least one character region template. A system for structured detection and a non-transitory computer-readable medium are also provided.
公开/授权文献
信息查询