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.
Bibliographical noteFunding Information:
This research was supported by the KIAT (Korea Institute for Advancement of Technology) grant funded by the Korea Government (MOTIE: Ministry of Trade Industry and Energy) (No. N0001883 , HRD Program for Intelligent semiconductor Industry) and also supported by the MOTIE (Ministry of Trade, Industry & Energy) ( 10080568 ) and KSRC (Korea Semiconductor Research Consortium) support program for the development of the future semiconductor device.
© 2018 Elsevier B.V.
All Science Journal Classification (ASJC) codes
- Human-Computer Interaction
- Hardware and Architecture
- Electrical and Electronic Engineering