End-to-end scene text detection and recognition algorithm based on Transformer decoders
Aiming at the detection and recognition task of arbitrary shape text in scene, a novelty scene text detection and recognition algorithm which could be trained by end-to-end algorithm was proposed.Firstly, the detection branch of text aware module based on segmentation idea was introduced to detect s...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2023-05-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023070/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539192064049152 |
|---|---|
| author | Jinzhi ZHENG Ruyi JI Libo ZHANG Chen ZHAO |
| author_facet | Jinzhi ZHENG Ruyi JI Libo ZHANG Chen ZHAO |
| author_sort | Jinzhi ZHENG |
| collection | DOAJ |
| description | Aiming at the detection and recognition task of arbitrary shape text in scene, a novelty scene text detection and recognition algorithm which could be trained by end-to-end algorithm was proposed.Firstly, the detection branch of text aware module based on segmentation idea was introduced to detect scene text from visual features extracted by convolutional network.Then, a recognition branch based on Transformer vision module and Transformer language module encoded the text features of the detection results.Finally, the text features encoded by the fusion gate in the recognition branch were fused to output the scene text.The experimental results on the three benchmark datasets of Total-Text, ICDAR2013 and ICDAR2015 show that the proposed algorithm has excellent performance in recall, precision, F-score, and has certain advantages in efficiency. |
| format | Article |
| id | doaj-art-4f7081a30f4746e4b54cb3936d4c3a65 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2023-05-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-4f7081a30f4746e4b54cb3936d4c3a652025-01-14T07:23:51ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-05-0144647859838270End-to-end scene text detection and recognition algorithm based on Transformer decodersJinzhi ZHENGRuyi JILibo ZHANGChen ZHAOAiming at the detection and recognition task of arbitrary shape text in scene, a novelty scene text detection and recognition algorithm which could be trained by end-to-end algorithm was proposed.Firstly, the detection branch of text aware module based on segmentation idea was introduced to detect scene text from visual features extracted by convolutional network.Then, a recognition branch based on Transformer vision module and Transformer language module encoded the text features of the detection results.Finally, the text features encoded by the fusion gate in the recognition branch were fused to output the scene text.The experimental results on the three benchmark datasets of Total-Text, ICDAR2013 and ICDAR2015 show that the proposed algorithm has excellent performance in recall, precision, F-score, and has certain advantages in efficiency.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023070/text detectiontext recognitionend-to-endTransformer |
| spellingShingle | Jinzhi ZHENG Ruyi JI Libo ZHANG Chen ZHAO End-to-end scene text detection and recognition algorithm based on Transformer decoders Tongxin xuebao text detection text recognition end-to-end Transformer |
| title | End-to-end scene text detection and recognition algorithm based on Transformer decoders |
| title_full | End-to-end scene text detection and recognition algorithm based on Transformer decoders |
| title_fullStr | End-to-end scene text detection and recognition algorithm based on Transformer decoders |
| title_full_unstemmed | End-to-end scene text detection and recognition algorithm based on Transformer decoders |
| title_short | End-to-end scene text detection and recognition algorithm based on Transformer decoders |
| title_sort | end to end scene text detection and recognition algorithm based on transformer decoders |
| topic | text detection text recognition end-to-end Transformer |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023070/ |
| work_keys_str_mv | AT jinzhizheng endtoendscenetextdetectionandrecognitionalgorithmbasedontransformerdecoders AT ruyiji endtoendscenetextdetectionandrecognitionalgorithmbasedontransformerdecoders AT libozhang endtoendscenetextdetectionandrecognitionalgorithmbasedontransformerdecoders AT chenzhao endtoendscenetextdetectionandrecognitionalgorithmbasedontransformerdecoders |