Recognition and identification of form document layouts
Kai Luo, Seyed Milad Mir Latifi, Kazem Taghva, Emma E. Regentova · 2004
We introduce a hierarchical tree representation to represent the logical structure of a form document. Different forms might have the same logical structure, so the representation will be ambiguous. We propose an improvement to solve the ambiguity problem by using the physical information of the blocks. A pixel tracing approach is used to extract form layout structures from form documents. Compared with Hough transform, it requires less computation. This algorithm has been tested on 50 different table forms. The algorithm applies to table form documents.