A Robust License Plate Recognition Model Based on Bi-LSTM
License plate detection and recognition are still important and challenging tasks in natural scenes. At present, most methods have favorable effect on license plate recognition under restrictive conditions, and most of such license plates are shot under good angle and light conditions. However, for...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9268976/ |
| _version_ | 1811341902604140544 |
|---|---|
| author | Yongjie Zou Yongjun Zhang Jun Yan Xiaoxu Jiang Tengjie Huang Haisheng Fan Zhongwei Cui |
| author_facet | Yongjie Zou Yongjun Zhang Jun Yan Xiaoxu Jiang Tengjie Huang Haisheng Fan Zhongwei Cui |
| author_sort | Yongjie Zou |
| collection | DOAJ |
| description | License plate detection and recognition are still important and challenging tasks in natural scenes. At present, most methods have favorable effect on license plate recognition under restrictive conditions, and most of such license plates are shot under good angle and light conditions. However, for license plates under non-restrictive conditions, such as dark, bright, rotated conditions etc. from the Chinese City Parking Dataset (CCPD), the performance of some methods of license plate recognition will be significantly reduced. In order to improve the accuracy of license plate recognition under unrestricted conditions, a robust license plate recognition model is proposed in this paper, which mainly includes license plate feature extraction, license plate character localization, and feature extraction of characters. First of all, the model can activate the regional features of characters and fully extract the character features of license plates. Then locate each license plate character through Bi-LSTM combined with the context location information of license plates. Finally, 1D-Attention is adopted to enhance useful character features after Bi-LSTM positioning, and reduce useless character features to realize effective acquisition of character features of license plates. A large number of experimental results demonstrate that the proposed algorithm has good performance under unrestricted conditions, which proves the effectiveness and robustness of the model. In CCPD-Base, CCPD-DB, CCPD-FN, CCPD-Tilt, CCPD-Weather, CCPD-Challenge and other sub-datasets, the recognition rates reach 99.3%, 98.5%, 98.6%, 96.4%, 99.3% and 86.6% respectively. |
| first_indexed | 2024-04-13T19:00:59Z |
| format | Article |
| id | doaj.art-17fce5539e6648c1b91d460a9d0fa3eb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-13T19:00:59Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-17fce5539e6648c1b91d460a9d0fa3eb2022-12-22T02:34:05ZengIEEEIEEE Access2169-35362020-01-01821163021164110.1109/ACCESS.2020.30402389268976A Robust License Plate Recognition Model Based on Bi-LSTMYongjie Zou0https://orcid.org/0000-0001-8425-3934Yongjun Zhang1https://orcid.org/0000-0002-7534-1219Jun Yan2https://orcid.org/0000-0003-2099-7162Xiaoxu Jiang3Tengjie Huang4Haisheng Fan5Zhongwei Cui6Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, College of Computer Science and Technology, Guizhou University, Guiyang, ChinaKey Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, College of Computer Science and Technology, Guizhou University, Guiyang, ChinaZhuhai Orbita Aerospace Science and Technology Company, Ltd., Zhuhai, ChinaZhuhai Orbita Aerospace Science and Technology Company, Ltd., Zhuhai, ChinaZhuhai Orbita Aerospace Science and Technology Company, Ltd., Zhuhai, ChinaZhuhai Orbita Aerospace Science and Technology Company, Ltd., Zhuhai, ChinaBig Data Science and Intelligent Engineering Research Institute, Guizhou Education University, Guiyang, ChinaLicense plate detection and recognition are still important and challenging tasks in natural scenes. At present, most methods have favorable effect on license plate recognition under restrictive conditions, and most of such license plates are shot under good angle and light conditions. However, for license plates under non-restrictive conditions, such as dark, bright, rotated conditions etc. from the Chinese City Parking Dataset (CCPD), the performance of some methods of license plate recognition will be significantly reduced. In order to improve the accuracy of license plate recognition under unrestricted conditions, a robust license plate recognition model is proposed in this paper, which mainly includes license plate feature extraction, license plate character localization, and feature extraction of characters. First of all, the model can activate the regional features of characters and fully extract the character features of license plates. Then locate each license plate character through Bi-LSTM combined with the context location information of license plates. Finally, 1D-Attention is adopted to enhance useful character features after Bi-LSTM positioning, and reduce useless character features to realize effective acquisition of character features of license plates. A large number of experimental results demonstrate that the proposed algorithm has good performance under unrestricted conditions, which proves the effectiveness and robustness of the model. In CCPD-Base, CCPD-DB, CCPD-FN, CCPD-Tilt, CCPD-Weather, CCPD-Challenge and other sub-datasets, the recognition rates reach 99.3%, 98.5%, 98.6%, 96.4%, 99.3% and 86.6% respectively.https://ieeexplore.ieee.org/document/9268976/Character localizationlicense plate detectionlicense plate recognition |
| spellingShingle | Yongjie Zou Yongjun Zhang Jun Yan Xiaoxu Jiang Tengjie Huang Haisheng Fan Zhongwei Cui A Robust License Plate Recognition Model Based on Bi-LSTM IEEE Access Character localization license plate detection license plate recognition |
| title | A Robust License Plate Recognition Model Based on Bi-LSTM |
| title_full | A Robust License Plate Recognition Model Based on Bi-LSTM |
| title_fullStr | A Robust License Plate Recognition Model Based on Bi-LSTM |
| title_full_unstemmed | A Robust License Plate Recognition Model Based on Bi-LSTM |
| title_short | A Robust License Plate Recognition Model Based on Bi-LSTM |
| title_sort | robust license plate recognition model based on bi lstm |
| topic | Character localization license plate detection license plate recognition |
| url | https://ieeexplore.ieee.org/document/9268976/ |
| work_keys_str_mv | AT yongjiezou arobustlicenseplaterecognitionmodelbasedonbilstm AT yongjunzhang arobustlicenseplaterecognitionmodelbasedonbilstm AT junyan arobustlicenseplaterecognitionmodelbasedonbilstm AT xiaoxujiang arobustlicenseplaterecognitionmodelbasedonbilstm AT tengjiehuang arobustlicenseplaterecognitionmodelbasedonbilstm AT haishengfan arobustlicenseplaterecognitionmodelbasedonbilstm AT zhongweicui arobustlicenseplaterecognitionmodelbasedonbilstm AT yongjiezou robustlicenseplaterecognitionmodelbasedonbilstm AT yongjunzhang robustlicenseplaterecognitionmodelbasedonbilstm AT junyan robustlicenseplaterecognitionmodelbasedonbilstm AT xiaoxujiang robustlicenseplaterecognitionmodelbasedonbilstm AT tengjiehuang robustlicenseplaterecognitionmodelbasedonbilstm AT haishengfan robustlicenseplaterecognitionmodelbasedonbilstm AT zhongweicui robustlicenseplaterecognitionmodelbasedonbilstm |