Combining singular point and co-occurrence matrix for fingerprint classification

Authors:
Geevar C. Zacharias;P. Sojan Lal
Affiliations:
M.E.S College of Engineering;Mahatma Gandhi University, Kerala, India
Venue:
Proceedings of the Third Annual ACM Bangalore Conference
Year:
2010

Citing 7
Cited 0

Fingerprint pattern classification

Pattern Recognition
A Multichannel Approach to Fingerprint Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fingerprint Classification by Directional Image Partitioning

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Intrinsic Coordinate System for Fingerprint Matching

AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication
Fingerprint classification using fast Fourier transform and nonlinear discriminant analysis

Pattern Recognition
Type Classification of Fingerprints: A Syntactic Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Filterbank-based fingerprint matching

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Fingerprint classification is an important part of fingerprint identification system that works on large databases to increase its matching speed. In this paper, an automatic fingerprint classification method is proposed to classify the fingerprint images by combining singular points and Gray Level Co-occurrence Matrix (GLCM) features. Co-occurrence matrices can be used to extract features from the fingerprint image because these are composed of regular texture patterns. First, the fingerprint image is preprocessed and a unique reference point is detected to determine a Region-of-Interest (ROI). ROI is then partitioned into 4 different regions to extract 4 sets of 4 GLCM features from each region. To achieve this, 4 co-occurrence matrixes are computed from each region with a predefined set of parameters. A feature vector consisting of 64 features is used to train a feed-forward neural network for classifying the input image into 5 different classes. The accuracy of 97.14% with no rejection is achieved and the experiment result shows that the method is reliable for fingerprint classification.