Flash webpage segmentation based on image perception using DWT and morphological operations

Abstract

Web page segmentation is an important step for many applications such as Information Retrieval, Noise Removal, Full Text Search, Information Extraction, and Automatic page adaptation and so on can benefit from this structure. Many segmentation methods have been proposed on HTML Web page segmentation whereas Flash Web pages have been omitted because of their less availability. But in recent days, we can see many Flash Web pages taking their appearance. In this paper, we are proposing segmentation method by using image processing techniques after processing Web pages as images, because of their unavailability of semantic structure. We perform the experimental analysis based on ground truth analysis (actual blocks in Web page as per human perception) and obtained the better performance level. We also measure the usefulness of Flash Web page blocks.