Writer identification by writer's invariants

A. Bensefia1, A. Nosary1, T. Paquet1, L. Heutte1
1Laboratoire Perception Systèmes Information, UFR des Sciences, Université de Rouen, France

Tóm tắt

This communication deals with the problem of writer identification. If the assumption of writing individuality is true then graphical fragments that constitute it should be individual too. Therefore we propose a morphological grapheme based analysis to make writer identification. Template Matching is the core of the approach. The redundancy of the individual patterns in a writing, defined as the writer's invariants, allows to compress the handwritten texts while maintaining good identification performance. Two series of tests are reported. The first series is designed to evaluate the relevance of our approach of identification on a basis of 88 writers by evaluating the influence of the text representation (with or without invariants) on the quality of the method. The method gives about 97,7% of correct identification when using large compressed samples of handwriting. The second series of tests is designed to evaluate the influence of the sample size of the writing to be identified on the quality of the method. It is shown that writer identification can reach a correct identification rate of 92,9% using only samples of 50 graphemes of each writing.

Từ khóa

#Writing #Testing #Handwriting recognition #Feature extraction #Fingerprint recognition #Genetics #Technical drawing #Noise reduction #Noise measurement #Conferences

Tài liệu tham khảo

10.1016/0031-3203(91)90055-A duda, 2000, Pattern Classification and Scene Analysis cha, 2000, Multiple feature integration for writer verification, 7th International Workshop on Frontiers in Handwriting Recognition IWFHR VII, 333 10.1016/S0031-3203(99)00063-1 10.1016/0031-3203(89)90059-9 nosary, 2002, Automatic Recognition of Handwritten Texts Through Writer Adaptation 10.1109/ICDAR.1999.791900 10.1109/ICDAR.2001.953763 10.1016/S0031-3203(99)00006-0 srihari, 2001, Individuality of handwritig: A validity study, Proc ICDAR'01, 106