Title :
Recognition and identification of form document layouts
Author :
Luo, Kai ; Latifi, Shahram ; Taghva, Kazem ; Regentova, Emma
Author_Institution :
Nevada Univ., Las Vegas, NV, USA
Abstract :
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.
Keywords :
Hough transforms; document handling; frame based representation; pattern recognition; Hough transform; ambiguity problem; form document; form layout extraction; hierarchical tree representation; logical structure; pixel tracing; table form document; Character recognition; Data mining; Face detection; Government; Image databases; Information technology; Optical character recognition software; Strips; Testing; Tree graphs;
Conference_Titel :
Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004. International Conference on
Print_ISBN :
0-7695-2108-8
DOI :
10.1109/ITCC.2004.1286662