A Robust Method for Unknown Structure Form Analysis
LI Xing-yua · 1999
The analysis of unknown forms is a challenging and important problem in document processing.Current methods can only tolerate small breaks in form lines. In this paper, a strategy is proposed for analyzingunknown structure and filled forms based on extracted lines. lndividual edges are validated using knowledge of features of the extracted lines and their local proxirnity. ln a process of scanning the horizontal and verticallines, candidate edges are validated and rectangles are generated if their surrounding edges and their combinationare all valid. To preserve the constraints and make full use of global information, the process is recursivelyapplied. The rectangle extraction can tolerate large breaks in form lines, ignore irrelevant segments and dealwith complex configurations such as embedded rectangles. After rectangle extraction, other form componentsare extracted by searching the remaining segments. Experiments on a collection of forms with handwritten fieldsand documents with tables show that the proposed approach works well even on poor quality images.