doi: 10.18178/ijfcc.2017.6.3.499
Text Region Extraction in High Contrasting Image
,
,
,
Dong Seog Han
- School of Electronics Engineering, Kyungpook National University, Daegu, Korea.
Abstract
In this paper, a text region extraction system withhigh contrasting text images for self-driving cars is proposed.The maximally stable extremal regions (MSER) method isusually used to extract text regions. Images must be convertedto grayscale to process with the MSER method. However, theperformance of MSER by using grayscale images has a poorability of capturing regions of interest in bad conditions such ashigh-contrast, low-luminance, much light reflection, and so on.An MSER system with a contrast-limited adaptive histogramequalization (CLAHE) instead of conventional MSER istherefore proposed. CLAHE is utilized as a pre-processingmethod in MSER to detect text regions. The proposed methodachieves a precision of 81% and a recall of 82%. However, thosefor the MSER with grayscale are 63% and 55%, respectively.
Keywords
- CLAHE
- MSER
- stroke width transform
- textregion extraction
How to Cite
Seokjun Kang, Daewoong Cha, Youngwoo Kim, and Dong Seog Han, "Text Region Extraction in High Contrasting Image," International Journal of Future Computer and Communication, vol. 6, no. 3, pp. 106-109, 2017. https://doi.org/ 10.18178/ijfcc.2017.6.3.499
Copyright & License
Copyright © 2017 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).