Lossless compression of human static signatures

Author

Lee, Luan Ling ; Lizarraga, Miguel Gustavo

Author_Institution

Univ. Estadual de Campinas, Sao Paulo, Brazil

Volume

2

fYear

1996

fDate

14-18 Oct 1996

Firstpage

835

Abstract

This paper describes a lossless compression method for static human signatures applicable to personal identification. The method consists of four sequential procedures: (1) the static signature image bounding; (2) the signature image partition; (3) the elimination of redundancies in the signature image patterns, and (4) the code optimization through the truncated Huffman coding. Experimental results reveal that the proposed method is capable of achieving a compression rate of 96.98% over human static signatures on average if the images are intelligently partitioned

Keywords

Huffman codes; entropy codes; feature extraction; handwriting recognition; image coding; image recognition; image segmentation; optimisation; code optimization; compression rate; entropy coding; experimental results; human static signatures; lossless compression; personal identification; redundancies elimination; signature image partition; signature image patterns; static signature image bounding; truncated Huffman coding; Authentication; Authorization; Data mining; Digital signatures; Feature extraction; Handwriting recognition; Humans; Image coding; Optimization methods; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 1996., 3rd International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-2912-0

Type

conf

DOI

10.1109/ICSIGP.1996.566215

Filename

566215