Model matching based on association graph for form image understanding

A new method of image understanding for forms based on model matching is proposed in this paper as the basis of OCR which can read a variety of forms. The outline of this method is described as follows. Ruled lines are extracted from the input image of a form. These lines are used for understanding the form, taking into account their feature attributes and the relationships between them. Each line in the input image of a form as expected to correspond to a line in one of the model forms, which are described as structured features. This correspondence is represented by a node in an association graph where an arc represents compatible correspondences established on the basis of feature relationships. The best match is found as the largest maximal clique in the association graph. Experimental results show the method is robust and effective for poor quality document images and also for various styles of forms.