A new lightweight script independent scene text style transfer network
Document Type
Article
Publication Date
10-1-2023
Abstract
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.
Keywords
Text detection, Style transfer, CNN models, Multi-lingual transfer
Divisions
fsktm
Funders
Ministry of Education, Malaysia,Fundamental Research Grant Scheme (FRGS) [Grant no. FRGS/1/2020/ICT02/UM/02/4],National Natural Science Foundation of China (NSFC) [Grant no. 62136001],Technology Innovation Hub, Indian Statistical Institute, Kolkata, India
Publication Title
International Journal of Pattern Recognition and Artificial Intelligence
Volume
37
Issue
13
Publisher
World Scientific Publ Co Pte Ltd
Publisher Location
5 TOH TUCK LINK, SINGAPORE 596224, SINGAPORE