Enhanced Screen Content Image Compression: A Synergistic Approach for Structural Fidelity and Text Integrity Preservation

Fangtao Zhou, xiaofeng huang, Peng Zhang, Meng Wang, Zhao Wang, Yang Zhou, Haibing YIN

Abstract: With the rapid development of video conferencing and online education applications, screen content image (SCI) compression has become increasingly crucial. Recently, deep learning techniques have made significant strides in compressing natural images, surpassing the performance of traditional standards like versatile video coding. However, directly applying these methods to SCIs is challenging due to the unique characteristics of SCIs. In this paper, we propose a synergistic approach to preserve structural fidelity and text integrity for SCIs. Firstly, external prior guidance is proposed to enhance structural fidelity and text integrity by providing global spatial attention. Then, a structural enhancement module is proposed to improve the preservation of structural information by enhanced spatial feature transform. Finally, the loss function is optimized for better compression efficiency in text regions by weighted mean square error. Experimental results show that the proposed method achieves 13.3\% BD-Rate saving compared to the baseline window attention convolutional neural networks (WACNN) on the JPEGAI, SIQAD, SCID, and MLSCID datasets on average.

Primary Subject Area: [Systems] Transport and Delivery

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: Image compression is one of the most important technologies in the multimedia field. With the rapid development of information and communication technology, screen content images play a key role in various applications such as video conferencing (e.g., Zoom, Webex), online education (e.g., Google Classroom, Kahoot), social media (e.g., WeChat, Facebook), etc. In multimedia, images usually occupy a large storage space, and image compression technology can reduce the size of image files by reducing the redundant information of image data, thus saving storage space and transmission bandwidth.

Submission Number: 3527