A New Lightweight Script Independent Scene Text Style Transfer Network
- 1 October 2023
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 37 (13)
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
Funding Information
- Fundamental Research Grant Scheme (FRGS/1/2020/ICT02/UM/02/4)
- National Natural Science Foundation of China (62136001)
This publication has 46 references indexed in Scilit:
- Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization2017
- Learning from Simulated and Unsupervised Images through Adversarial Training2017
- EAST: An Efficient and Accurate Scene Text Detector2017
- Awesome Typography: Statistics-Based Text Effects Transfer2017
- Style Transfer Via Texture SynthesisIEEE Transactions on Image Processing, 2017
- Very deep convolutional neural network based image classification using small training sample size2015
- Scene Text Recognition Using Structure-Guided Character Detection and Linguistic KnowledgeIEEE Transactions on Circuits and Systems for Video Technology, 2014
- Writer Adaptation with Style Transfer MappingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Robust text detection in natural images with edge-enhanced Maximally Stable Extremal Regions2011
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004