A New Lightweight Script Independent Scene Text Style Transfer Network

doi:10.1142/S0218001423530038

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	A New Lightweight Script Independent Scene Text Style Transfer Network
	Shivakumara, Palaiahnakote 1; Roy, Ayush 2; Nandanwar, Lokesh 2; Pal, Umapada 2; Lu, Yue 3; Liu, Cheng-Lin 4,5
刊名	INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE
	2023-11-04
页码	29
关键词	Text detection style transfer CNN models multi-lingual transfer
ISSN号	0218-0014
DOI	10.1142/S0218001423530038
通讯作者	Shivakumara, Palaiahnakote(shiva@um.edu.my)
英文摘要	Scene text style transfer without a language barrier is an open challenge for the video and scene text recognition community because this plays a vital role in poster, web design, augmenting character images, and editing characters to improve scene text recognition performance and usability. This work presents a new model, called Script Independent Scene Text Style Transfer Network (SISTSTNet), for extracting scene characters and transferring text style simultaneously. The SISTSTNet performs mapping in language-independent feature space for transferring style. It is designed based on a Style Parameter Network and Target Encoder Network through lightweight MobileNetv3 convolutional and residual blocks to capture the style and shape to generate target characters. Similarly, a generative model is explored through the Visual Geometry Group (VGG) network for character replacement. The SISTSTNet is flexible and works on different languages and arbitrary examples in a neat and unified fashion. The experimental results on images in various languages, namely, English, Chinese, Hindi, Russian, Japanese, Arabic, Greek, and Bengali and cross-language validation demonstrate the effectiveness of the proposed method. The performance of the method is superior compared to the state-of-the-art methods in terms of quality measures, language independence, shape-preserving, and efficiency. The code and dataset will be released to the public to support reproducibility.
资助项目	Ministry of Higher Education of Malaysia ; Fundamental Research Grant Scheme (FRGS)[FRGS/1/2020/ICT02/UM/02/4] ; National Natural Science Foundation of China[62136001] ; Technology Innovation Hub, Indian Statistical Institute, Kolkata, India
WOS研究方向	Computer Science
语种	英语
出版者	WORLD SCIENTIFIC PUBL CO PTE LTD
WOS记录号	WOS:001104384200003
资助机构	Ministry of Higher Education of Malaysia ; Fundamental Research Grant Scheme (FRGS) ; National Natural Science Foundation of China ; Technology Innovation Hub, Indian Statistical Institute, Kolkata, India
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/55219]
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.Univ Malaya, Fac Comp Sci & Informat Technol, Kuala Lumpur 50603, Malaysia 2.Indian Stat Inst, Comp Vis & Pattern Recognit Unit, Kolkata, India 3.East China Normal Univ, Shanghai, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Shivakumara, Palaiahnakote,Roy, Ayush,Nandanwar, Lokesh,et al. A New Lightweight Script Independent Scene Text Style Transfer Network[J]. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE,2023:29.
APA	Shivakumara, Palaiahnakote,Roy, Ayush,Nandanwar, Lokesh,Pal, Umapada,Lu, Yue,&Liu, Cheng-Lin.(2023).A New Lightweight Script Independent Scene Text Style Transfer Network.INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE,29.
MLA	Shivakumara, Palaiahnakote,et al."A New Lightweight Script Independent Scene Text Style Transfer Network".INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE (2023):29.