Neuro-fuzzy Analysis of Document Images by the KERNEL System

Document image analysis represents one of the most relevant topics in the field of image processing: many research efforts have been devoted to devising automatic strategies for document region classification. In this paper, we present a peculiar strategy to extract numerical features from segmented image regions, and their employment for classification purposes by means of the KERNEL system, a particular neuro-fuzzy framework suitable for application in predictive tasks. The knowledge discovery process performed by KERNEL proved to be effective in solving the problem of distinguishing between textual and graphical components of a document image. The information embedded into sample data is organised in form of a fuzzy rule base, which results to be accurate and comprehensible for human users.

[1]  Anil K. Jain,et al.  Document Representation and Its Application to Page Decomposition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Shahram Latifi,et al.  Document segmentation using polynomial spline wavelets , 2001, Pattern Recognit..

[3]  Hong Yan,et al.  Text region extraction in a document image based on the Delaunay tessellation , 2003, Pattern Recognit..

[4]  S.C. Hinds,et al.  A document skew detection method using run-length encoding and the Hough transform , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[5]  Giovanna Castellano,et al.  KERNEL: A Matlab Toolbox for Knowledge Extraction and Refinement by NEural Learning , 2002, International Conference on Computational Science.

[6]  William K. Pratt,et al.  Digital Image Processing: PIKS Inside , 2001 .

[7]  Venu Govindaraju,et al.  Analysis of textual images using the Hough transform , 1989, Machine Vision and Applications.

[8]  Matti Pietikäinen,et al.  Document skew estimation without angle range restriction , 1999, International Journal on Document Analysis and Recognition.