DocumentCode :
2733481
Title :
An Adaptively Automated Five-Class Fingerprint Classification Scheme Using Kohonens Feature Map and fuzzy ant clustering by centroid positioning
Author :
Srinivasan, T. ; Shivashankar, S. ; Archana, V. ; Rakesh, B.
Author_Institution :
Dept. of Comput. Sci. & Eng., Sri Venkateswara Coll. of Eng., Sriperumbudur
fYear :
2006
fDate :
6-6 Dec. 2006
Firstpage :
125
Lastpage :
130
Abstract :
In this paper we present a novel adaptively automated fingerprint classification scheme, which is computationally efficient and resolves both intra- class diversities and inter-class similarities. Initially, preprocessing of fingerprint images is carried out to enhance the image. As part of preprocessing scheme the denoising algorithm used endows better performance of system even in case of bad quality image. Directional image is computed to classify based on global shape. Principal component analysis is employed for dimensionality reduction and to get feature space that accounts for as much of the total variation as possible. Self-organizing maps are involved for further dimension reduction and data clustering. The learning process takes into account the large intra class diversity and the continuum of fingerprint pattern types. Finally a swarm intelligence based maps the class separated fingerprint images into their respective class resolving the inter-class similarities. The proposed approach achieves an accuracy of around 93% for five-class classification tested on NIST 4 without rejection.
Keywords :
feature extraction; fingerprint identification; image denoising; learning (artificial intelligence); pattern classification; pattern clustering; principal component analysis; self-organising feature maps; Kohonens feature map; adaptively automated five-class fingerprint classification scheme; centroid positioning; denoising algorithm; feature space; fingerprint images; fuzzy ant clustering; learning process; principal component analysis; self-organizing maps; swarm intelligence; Clustering algorithms; Fingerprint recognition; Image matching; Image resolution; Noise reduction; Particle swarm optimization; Principal component analysis; Self organizing feature maps; Shape; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Digital Information Management, 2006 1st International Conference on
Conference_Location :
Bangalore
Print_ISBN :
1-4244-0682-X
Type :
conf
DOI :
10.1109/ICDIM.2007.369341
Filename :
4221878
Link To Document :
بازگشت