中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
A New Language-Independent Deep CNN for Scene Text Detection and Style Transfer in Social Media Images

文献类型：期刊论文

作者Shivakumara, Palaiahnakote2; Banerjee, Ayan1; Pal, Umapada1; Nandanwar, Lokesh2; Lu, Tong5; Liu, Cheng-Lin3,4
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2023
卷号32页码:3552-3566
关键词Text detection style transfer deep learning EfficientNet social media images
ISSN号1057-7149
DOI10.1109/TIP.2023.3287038
通讯作者Shivakumara, Palaiahnakote(shiva@um.edu.my)
英文摘要Due to the adverse effect of quality caused by different social media and arbitrary languages in natural scenes, detecting text from social media images and transferring its style is challenging. This paper presents a novel end-to-end model for text detection and text style transfer in social media images. The key notion of the proposed work is to find dominant information, such as fine details in the degraded images (social media images), and then restore the structure of character information. Therefore, we first introduce a novel idea of extracting gradients from the frequency domain of the input image to reduce the adverse effect of different social media, which outputs text candidate points. The text candidates are further connected into components and used for text detection via a UNet++ like network with an EfficientNet backbone (EffiUNet++). Then, to deal with the style transfer issue, we devise a generative model, which comprises a target encoder and style parameter networks (TESP-Net) to generate the target characters by leveraging the recognition results from the first stage. Specifically, a series of residual mapping and a position attention module are devised to improve the shape and structure of generated characters. The whole model is trained end-to-end so as to optimize the performance. Experiments on our social media dataset, benchmark datasets of natural scene text detection and text style transfer show that the proposed model outperforms the existing text detection and style transfer methods in multilingual and cross-language scenario.
资助项目Ministry of Higher Education of Malaysia[FRGS/1/2020/ICT02/UM/02/4] ; Natural Science Foundation of China[61672273]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001022071600003
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Ministry of Higher Education of Malaysia ; Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/53612]  
专题多模态人工智能系统全国重点实验室
通讯作者Shivakumara, Palaiahnakote
作者单位1.Indian Stat Inst, Kolkata 700108, India
2.Univ Malaya, Fac Comp Sci & Informat Technol, Dept Comp Syst & Technol, Kuala Lumpur 50603, Malaysia
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
5.Nanjing Univ, Dept Comp Sci & Technol, Nanjing 210093, Peoples R China
推荐引用方式
GB/T 7714		 Shivakumara, Palaiahnakote,Banerjee, Ayan,Pal, Umapada,et al. A New Language-Independent Deep CNN for Scene Text Detection and Style Transfer in Social Media Images[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2023,32:3552-3566.
APA Shivakumara, Palaiahnakote,Banerjee, Ayan,Pal, Umapada,Nandanwar, Lokesh,Lu, Tong,&Liu, Cheng-Lin.(2023).A New Language-Independent Deep CNN for Scene Text Detection and Style Transfer in Social Media Images.IEEE TRANSACTIONS ON IMAGE PROCESSING,32,3552-3566.
MLA Shivakumara, Palaiahnakote,et al."A New Language-Independent Deep CNN for Scene Text Detection and Style Transfer in Social Media Images".IEEE TRANSACTIONS ON IMAGE PROCESSING 32(2023):3552-3566.

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。