A Robust Local Thresholding Method for Segmentation of Non-Uniform Coloured Documents

Abstract

Text document segmentation is one of the essential steps text document recognition and extraction systems. The existing segmenting methods are not much reliable for text with colour gradient and texture background. Also, long processing time of existing methods is unfavorable. Thus, aiming to have reliable segmentation and less processing time, a new local thresholding method is proposed in this study. The proposed method is based on pixel intensity magnification concept. Non-overlapping local window is used. The performance of proposed method is compared with that of Otsu’s method and Niblack’s method. The results show that the proposed method give more reliable segmentation compared to Otus’ method, 1.2 times longer processing time. Compared to Niblack’s method, the segmented results are comparable and the processing time is 5 times faster.