An Unsupervised Approach for Video Text Localization

Abstract

A new video text localization approach is proposed. First, some pre-processing techniques, including color space conversion and histogram equalization, are applied to the input video frames to obtain the enhanced gray-scale images. Features are then extracted using wavelet transform to represent the texture property of text regions. Next, an unsupervised fuzzy c-means classifier is performed to discriminate candidate text pixels from background. Effective operations such as the morphological dilation operation and logical AND operation are applied for locating text blocks. A projection analysis technique is then employed to extract text lines. Finally, some geometric heuristics are used to remove noise regions and refine location of text lines. Experimental results indicate that the proposed approach is superior to other three representative approaches in term of total detection rate.