Box clustering segmentation: A new method for vision-based web page preprocessing

box clustering, graph clustering, vision-based page segmentation, VIPS

This paper presents a novel approach to web page segmentation, which is one of substantial preprocessing steps when mining data from web documents. Most of the current segmentation methods are based on algorithms that work on a tree representation of web pages (DOM tree or a hierarchical rendering model) and produce another tree structure as an output. In contrast, our method uses a rendering engine to get an image of the web page, takes the smallest rendered elements of that image, performs clustering using a custom algorithm and produces a flat set of segments of a given granularity. For the clustering metrics, we use purely visual properties only: the distance of elements and their visual similarity. We experimentally evaluate the properties of our algorithm by processing 2400 web pages. On this set of web pages, we prove that our algorithm is almost 90% faster than the reference algorithm. We also show that our algorithm accuracy is between 47% and 133% of the reference algorithm accuracy with indirect correlation of our algorithms accuracy to the depth of inspected page structure. In our experiments, we also demonstrate the advantages of producing a flat segmentation structure instead of an hierarchy.