Abstract
This paper presents a novel algorithm to classify complex-rendered text images by examining the color levels of the adjacent sub-pixels. The proposed algorithm is different from the previous approaches in that it uses the combined characteristics of RGB sub-channels, whereas the previous approaches use independent characteristics of RGB sub-channels. Experimental results demonstrate that the proposed algorithm improves the classification accuracy over the previous best algorithm by 15.9% for complex-rendered texts. Furthermore, the compression method optimized for text sub-images significantly reduces the computational complexity without degradation in compression efficiency.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have