Title:
TEXT DETECTION MODEL TRAINING METHOD AND APPARATUS, TEXT DETECTION METHOD, AND DEVICE
Document Type and Number:
WIPO Patent Application WO/2023/015941
Kind Code:
A1
Abstract:
A text detection model training method and a text detection method, relating to the fields of computer vision and deep learning, and applied to scenarios such as image processing and image recognition. The training method comprises: inputting a sample image into a text feature extraction submodel of a text detection model to obtain a text feature of the text in the sample image (S210), the sample image having labels indicating actual position information and an actual category; inputting a preset text vector into a text coding submodel of the text detection model to obtain a text reference feature (S220); inputting the text feature and the text reference feature into a decoding submodel of the text detection model to obtain a text sequence vector (S230); inputting the text sequence vector into an output submodel of the text detection model to obtain predicted position information and a predicted category (S240); and training the text detection model on the basis of the predicted category, the actual category, the predicted position information and the actual position information (S250).
Inventors:
ZHANG XIAOQIANG (CN)
QIN XIAMENG (CN)
ZHANG CHENGQUAN (CN)
YAO KUN (CN)
QIN XIAMENG (CN)
ZHANG CHENGQUAN (CN)
YAO KUN (CN)
Application Number:
PCT/CN2022/088393
Publication Date:
February 16, 2023
Filing Date:
April 22, 2022
Export Citation:
Assignee:
BEIJING BAIDU NETCOM SCI & TECH CO LTD (CN)
International Classes:
G06K9/62
Foreign References:
| CN113657390A | 2021-11-16 | |||
| CN112652393A | 2021-04-13 | |||
| CN112016543A | 2020-12-01 | |||
| CN112614128A | 2021-04-06 | |||
| US20210034981A1 | 2021-02-04 |
Other References:
VAIDWAN HRITIK; SETH NIKHIL; PARIHAR ANIL SINGH; SINGH KAVINDER: "A study on transformer-based Object Detection", 2021 INTERNATIONAL CONFERENCE ON INTELLIGENT TECHNOLOGIES (CONIT), IEEE, 25 June 2021 (2021-06-25), pages 1 - 6, XP033951383, DOI: 10.1109/CONIT51480.2021.9498550
ZHIGANG DAI; BOLUN CAI; YUGENG LIN; JUNYING CHEN: "UP-DETR: Unsupervised Pre-training for Object Detection with Transformers", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 7 April 2021 (2021-04-07), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081926836
"16th European Conference - Computer Vision – ECCV 2020", vol. 13, 1 January 1900, CORNELL UNIVERSITY LIBRARY,, 201 Olin Library Cornell University Ithaca, NY 14853, article CARION NICOLAS; MASSA FRANCISCO; SYNNAEVE GABRIEL; USUNIER NICOLAS; KIRILLOV ALEXANDER; ZAGORUYKO SERGEY: "End-to-End Object Detection with Transformers", pages: 213 - 229, XP047569461, DOI: 10.1007/978-3-030-58452-8_13
ZHIGANG DAI; BOLUN CAI; YUGENG LIN; JUNYING CHEN: "UP-DETR: Unsupervised Pre-training for Object Detection with Transformers", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 7 April 2021 (2021-04-07), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081926836
"16th European Conference - Computer Vision – ECCV 2020", vol. 13, 1 January 1900, CORNELL UNIVERSITY LIBRARY,, 201 Olin Library Cornell University Ithaca, NY 14853, article CARION NICOLAS; MASSA FRANCISCO; SYNNAEVE GABRIEL; USUNIER NICOLAS; KIRILLOV ALEXANDER; ZAGORUYKO SERGEY: "End-to-End Object Detection with Transformers", pages: 213 - 229, XP047569461, DOI: 10.1007/978-3-030-58452-8_13
Attorney, Agent or Firm:
CHINA SCIENCE PATENT & TRADEMARK AGENT LTD. (CN)
Download PDF: