Fingerprint pattern classification
Pattern Recognition
Computer vision for robotic systems: an introduction
Computer vision for robotic systems: an introduction
An approach to fingerprint filter design
Pattern Recognition
Segmentation of fingerprint images—a composite method
Pattern Recognition
IEEE Spectrum
Automatic personal identification using fingerprints
Automatic personal identification using fingerprints
Fingerprint classification and matching using a filterbank
Fingerprint classification and matching using a filterbank
Hi-index | 0.00 |
Fingerprint feature extraction and classification is always an interesting subject, in this paper besides of using effective methods for extraction of features a Fuzzy Neural Network has been introduced for classification and identification. For generating input patterns to feed the matching network, the algorithm extracts singular points and minutiae of each pattern by using the optimum segmentation and recovering methods. So for each pattern, a fingerprint feature image, let call it fingerprint feature map, has been found. Then this feature map is encoded and applied to the intelligent classifier. The learning speed and matching capability are improved by using the feature coding method. Necessary time for feature extraction and classifying of 100 different fingerprints with 220*176 dimensions and 315 dpi resolutions is less than 20 second. Also necessary space for storing image bank becomes small, up to 2.54 Kbyte per each feature map. The FNN is a clustering system with 5 feed forward layer and supervised learning algorithm.