Research on Small Acceptance Domain Text Detection Algorithm Based on Attention Mechanism and Hybrid Feature Pyramid
In the traditional text detection process, the text area of the small receptive field in the video image is easily ignored, the features that can be extracted are few, and the calculation is large. These problems are not conducive to the recognition of text information. In this paper, a lightweight...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/21/3559 |
| _version_ | 1797468537936150528 |
|---|---|
| author | Mingzhu Liu Ben Li Wei Zhang |
| author_facet | Mingzhu Liu Ben Li Wei Zhang |
| author_sort | Mingzhu Liu |
| collection | DOAJ |
| description | In the traditional text detection process, the text area of the small receptive field in the video image is easily ignored, the features that can be extracted are few, and the calculation is large. These problems are not conducive to the recognition of text information. In this paper, a lightweight network structure on the basis of the EAST algorithm, the Convolution Block Attention Module (CBAM), is proposed. It is suitable for the spatial and channel hybrid attention module of text feature extraction of the natural scene video images. The improved structure proposed in this paper can obtain deep network features of text and reduce the computation of text feature extraction. Additionally, a hybrid feature pyramid + BLSTM network is designed to improve the attention to the small acceptance domain text regions and the text sequence features of the region. The test results on the ICDAR2015 demonstrate that the improved construction can effectively boost the attention of small acceptance domain text regions and improve the sequence feature detection accuracy of small acceptance domain of long text regions without significantly increasing computation. At the same time, the proposed network constructions are superior to the traditional EAST algorithm and other improved algorithms in accuracy rate P, recall rate R, and F-value. |
| first_indexed | 2024-03-09T19:07:51Z |
| format | Article |
| id | doaj.art-dc9f791b9c844d73895b2464bb2cfdb0 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T19:07:51Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-dc9f791b9c844d73895b2464bb2cfdb02023-11-24T04:25:53ZengMDPI AGElectronics2079-92922022-10-011121355910.3390/electronics11213559Research on Small Acceptance Domain Text Detection Algorithm Based on Attention Mechanism and Hybrid Feature PyramidMingzhu Liu0Ben Li1Wei Zhang2The Higher Educational Key Laboratory for Measuring & Control Technology and Instrumentation of Heilongjiang Province, Harbin University of Science and Technology, Harbin 150080, ChinaThe Higher Educational Key Laboratory for Measuring & Control Technology and Instrumentation of Heilongjiang Province, Harbin University of Science and Technology, Harbin 150080, ChinaThe Higher Educational Key Laboratory for Measuring & Control Technology and Instrumentation of Heilongjiang Province, Harbin University of Science and Technology, Harbin 150080, ChinaIn the traditional text detection process, the text area of the small receptive field in the video image is easily ignored, the features that can be extracted are few, and the calculation is large. These problems are not conducive to the recognition of text information. In this paper, a lightweight network structure on the basis of the EAST algorithm, the Convolution Block Attention Module (CBAM), is proposed. It is suitable for the spatial and channel hybrid attention module of text feature extraction of the natural scene video images. The improved structure proposed in this paper can obtain deep network features of text and reduce the computation of text feature extraction. Additionally, a hybrid feature pyramid + BLSTM network is designed to improve the attention to the small acceptance domain text regions and the text sequence features of the region. The test results on the ICDAR2015 demonstrate that the improved construction can effectively boost the attention of small acceptance domain text regions and improve the sequence feature detection accuracy of small acceptance domain of long text regions without significantly increasing computation. At the same time, the proposed network constructions are superior to the traditional EAST algorithm and other improved algorithms in accuracy rate P, recall rate R, and F-value.https://www.mdpi.com/2079-9292/11/21/3559lightweight network structurehybrid feature pyramidBLSTM networkacceptance domainattention mechanism |
| spellingShingle | Mingzhu Liu Ben Li Wei Zhang Research on Small Acceptance Domain Text Detection Algorithm Based on Attention Mechanism and Hybrid Feature Pyramid Electronics lightweight network structure hybrid feature pyramid BLSTM network acceptance domain attention mechanism |
| title | Research on Small Acceptance Domain Text Detection Algorithm Based on Attention Mechanism and Hybrid Feature Pyramid |
| title_full | Research on Small Acceptance Domain Text Detection Algorithm Based on Attention Mechanism and Hybrid Feature Pyramid |
| title_fullStr | Research on Small Acceptance Domain Text Detection Algorithm Based on Attention Mechanism and Hybrid Feature Pyramid |
| title_full_unstemmed | Research on Small Acceptance Domain Text Detection Algorithm Based on Attention Mechanism and Hybrid Feature Pyramid |
| title_short | Research on Small Acceptance Domain Text Detection Algorithm Based on Attention Mechanism and Hybrid Feature Pyramid |
| title_sort | research on small acceptance domain text detection algorithm based on attention mechanism and hybrid feature pyramid |
| topic | lightweight network structure hybrid feature pyramid BLSTM network acceptance domain attention mechanism |
| url | https://www.mdpi.com/2079-9292/11/21/3559 |
| work_keys_str_mv | AT mingzhuliu researchonsmallacceptancedomaintextdetectionalgorithmbasedonattentionmechanismandhybridfeaturepyramid AT benli researchonsmallacceptancedomaintextdetectionalgorithmbasedonattentionmechanismandhybridfeaturepyramid AT weizhang researchonsmallacceptancedomaintextdetectionalgorithmbasedonattentionmechanismandhybridfeaturepyramid |