Detection and localization of text from natural scene images using texture features

Abstract

Text in camera captured images contains important and useful information. Text in images can be used for identification, indexing and retrieval. Detection and localization of text from camera captured images is still a challenging task due to high variability of text appearance. In this paper we propose an efficient algorithm, for detecting and localizing text in natural scene images. The method is based on texture feature extraction using first and second order statistics. The entire work is divided into two stages. Text regions are detected in the first stage using texture features. Discriminative functions are used to filter out non-text regions. In the second stage the detected text regions are merged and localized. An experimental results obtained shows that the proposed approach detects and localizes texts of various sizes, fonts, orientations and languages efficiently.