Multiple Feature Integration for Writer Verification

VERIFICATION SUNG-HYUK CHA AND SARGUR N. SRIHARI Center of Excellence for Document Analysis and Recognition State University of New York at Bu alo, 14228, U.S.A. E-mail: fscha,[email protected] alo.edu Given two handwritten documents, the writer veri cation problem is to determine whether the two documents were written by the same person. It is tackled by extracting various features and classifying the patterns into their classes. Features are diverse in type while techniques in pattern recognition typically require that features be homogeneous. The solution proposed overcomes both the nonhomogeneity of features and the intractability of in nite number of writers by a dichotomy transformation. In this model, the distance between each homogeneous feature type is used. We integrate several distance measures for many feature types: element, histogram, string, convex hull, etc into one useful for writer veri cation. Experimental results with 1; 000 writers with three sample documents per writer, using only 12 feature distances, results in 97% accuracy.