.png){kind=icon}
.png){kind=icon}
Return
Deep image compression using scene text quality assessment
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2023.109696.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 im-age quality assessment model to assess text quality in compressed images. The assessment model itera-tively 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 assess-ment model outperformed other deep-learning regression models. (c) 2023 Elsevier Ltd. All rights reserved.
Keywords:
Image compression
Scene text image
Text quality
Quality assessment
Regression model
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.