Text Detection and Localization in Low Quality Video Images through Image Resolution Enhancement Technique

text information plays an important role in semantic- based video analysis, indexing, and retrieval. Text embedded in the image or video contains very useful information like the name of the person, title, location and sometimes brief description of the image. Many algorithms have been proposed to detect and localize the text information present in video images. In this paper, we proposed a methodology to enhance the quality of the image and then detect and localize text regions from low quality video images. Experimental results show the proposed method achieves improved precision rate and recall rate. them to localize text regions. Edge based methods focus on the high contrast between the background and text and the edges of the text boundary are identified and merged. Later several heuristics are required to filter out non-text regions. But, the presence of noise, complex background, and significant degradation in the low resolution image can affect the extraction of connected components and identification of boundary lines, thus making both the approaches inefficient. Texture analysis techniques are good choice for solving such a problem as they give global measure of properties of a region. In this paper, resolution enhancement technique has been employed on low quality video images by using interpolation which generates sharper high resolution image. Texture based text detection and segmentation is applied on the enhanced image. The proposed method is robust enough to detect text regions from low quality video images, and achieves improved precision rate and recall rate.