An end-to-end model for multi-view scene text recognition
文献类型：期刊论文
| 作者 | Banerjee, Ayan1; Shivakumara, Palaiahnakote2; Bhattacharya, Saumik3; Pal, Umapada1; Liu, Cheng-Lin4
|
| 刊名 | PATTERN RECOGNITION
 |
| 出版日期 | 2024-05-01 |
| 卷号 | 149页码:17 |
| 关键词 | Text detection Scene text recognition Siamese network Natural language model Genetic algorithm Multi-view text detection |
| ISSN号 | 0031-3203 |
| DOI | 10.1016/j.patcog.2023.110206 |
| 通讯作者 | Shivakumara, Palaiahnakote(S.Palaiahnakote@salford.ac.uk) |
| 英文摘要 | Due to the increasing applications of surveillance and monitoring such as person re-identification, vehicle reidentification and sports events tracking, the necessity of text detection and end-to-end recognition is also growing. Although the past deep learning-based models have addressed several challenges such as arbitraryshaped text, multiple scripts, and variations in the geometric structure of characters, the scope of the models is limited to a single view. This paper presents an end-to-end model for text recognition through refining the multi-views of the same scene, which is called E2EMVSTR (End-to-End Model for Multi-View Scene Text Recognition). Considering the common characteristics shared in multi-view texts, we propose a cycle consistency pairwise similarity-based deep learning model to find texts more efficiently in three input views. Further, the extracted texts are supplied to a Siamese network and semi-supervised attention embedding combinational network for obtaining recognition results. The proposed model combines natural language processing and genetic algorithm models to restore missing character information and correct wrong recognition results. In experiments on our multi-view dataset and several benchmark datasets, the proposed method is proven effective compared to the state-of-the-art methods. The dataset and codes will be made available to the public upon acceptance. |
| WOS关键词 | ATTENTION NETWORK ; IMAGES |
| 资助项目 | Ministry of Higher Education of Malaysia[FRGS/1/2020/ICT02/UM/02/4] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001166069400001 |
| 出版者 | ELSEVIER SCI LTD |
| 资助机构 | Ministry of Higher Education of Malaysia |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57833]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_模式分析与学习团队 |
| 通讯作者 | Shivakumara, Palaiahnakote |
| 作者单位 | 1.Indian Stat Inst, Kolkata, India 2.Univ Malaya, Fac Comp Sci & Informat Technol, Kuala Lumpur 50603, Malaysia 3.Indian Inst Technol Kharagpur, Dept E&ECE, Kharagpur, W Bengal, India 4.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Banerjee, Ayan,Shivakumara, Palaiahnakote,Bhattacharya, Saumik,et al. An end-to-end model for multi-view scene text recognition[J]. PATTERN RECOGNITION,2024,149:17. |
| APA | Banerjee, Ayan,Shivakumara, Palaiahnakote,Bhattacharya, Saumik,Pal, Umapada,&Liu, Cheng-Lin.(2024).An end-to-end model for multi-view scene text recognition.PATTERN RECOGNITION,149,17. |
| MLA | Banerjee, Ayan,et al."An end-to-end model for multi-view scene text recognition".PATTERN RECOGNITION 149(2024):17. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。