Image compression is a fundamental technology for Internet communication engineering. However, a high compression rate with general methods may degrade images, resulting in unreadable texts. In this paper, we propose an image compression method for maintaining text quality. We developed a scene text image quality assessment model to assess text quality in compressed images. The assessment model iteratively searches for the best-compressed image holding high-quality text. Objective and subjective results showed that the proposed method was superior to existing methods. Furthermore, the proposed assessment model outperformed other deep-learning regression models.
@article{arxiv.2305.11373,
title = {Deep Image Compression Using Scene Text Quality Assessment},
author = {Shohei Uchigasaki and Tomo Miyazaki and Shinichiro Omachi},
journal= {arXiv preprint arXiv:2305.11373},
year = {2023}
}