A background based adaptive page segmentation algorithm

A novel page segmentation algorithm is provided in this paper. Based on the extraction of the background, it offers the benefit of being adaptive to the context of the document and to be insensitive to the orientation of the text blocks. It involves a two-dimensional isotropic structuring element used to characterized the white streams. This element is a disk approximated by a regular octagon which can be recursively generated. Another advantage of the proposed method is that a hierarchical segmentation can be derived from the image built upon the octagonal pattern. This tree allows to perform an isotropic multi-scale smearing, which leads to a physical segmentation. The algorithms are based on an input-time tracing principle and use a single scan of the image, they are very well suited to a real-time implementation.