Finding text in images via local thresholding

Texts appearing in images or videos are not only important sources of information but also significant entities for indexing and retrieval purposes. However, since text is often printed against a shaded or textured background it is often difficult to recognize. In this paper, an approach, which can automatically detect, localize and extract horizontally aligned text with different sizes, fonts and languages in images, is presented. The basic idea of our approach is to apply an appropriate local thresholding technique to sequences of line histogram differences in order to increase the robustness of text detection with respect to complex backgrounds. The performance of our approach is demonstrated by presenting experimental results for a set of images taken from video sequences.