Proposal of Seam Degree and Content Similarity for Web Page Segmentation
Jun Zeng, Brendan Flanagan, Qingyu Xiong, Junhao Wen, Sachio Hirokawa · 2013
Page segmentation has received great attention in recent years. However, most research has been based on some pre-defined heuristics or visual cues which may be not suitable for large-scale page segmentation. In this paper, we proposed two parameters: seam degree and content similarity, to indicate the coherent degree of a page block. Instead of analyzing pre-defined heuristics or visual cues, our method utilizes the visual and content features to determine whether a page block should be divided into smaller blocks. We also proposed a principled page segmentation method using these two parameters. An experiment was conducted to determine the relationship between the two parameters and the number of segment results. The empirical results also show that our segmentation method can effectively segment a page into different semantic parts.