A Comparative Study of Segmentation in Mixed-Mode Images

The detection and extraction of text regions in an image is a well known problem in the computer vision research area. Text extraction is a critical and essential step as it sets up the quality of the final recognition result. It aims at segmenting text from background, i.e isolating text pixels from those of background. Since readymade mixed mode image data is not available, it is necessary to create our own database. The database plays an important role as segmentation is to be done in an image. In educational videos and in presentation of lectures, graphic play an important role. In television industry text and images are simultaneously transmitted. In such similar application compression of data and bandwidth play an important role. To achieve better compression and bandwidth utilization properly, an efficient segmentation technique is necessary. In this paper, we analyze mixed mode images by two methods. General Terms Image processing, Edge based text extraction, Connected Component based text extraction.