|
|||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
Neuro Genetic-Nearest Neighbor Based Data Mining Techniques for Fingerprint Classification and Recognition System K. Umamaheswari 1 S.Sumathi2 S. N. Sivanandam3 K. K. N. Anburajan4 1. Dept. of IT, PSG College of Technology, Coimbatore, India 2,4. Dept. of EEE, PSG College of Technology, Coimbatore, India 3. Dept. of CSE, PSG College of Technology, Coimbatore, India
The proposed fingerprint classification using Data
Mining technique, Neuro Genetic-Nearest Neighbor based
recognition, overcomes low recognition rate, low accuracy,
increased time of recovery and improves the classification
rate. The proposed method involves various stages like image
enhancement, line detector based feature extraction and
neural network classification using Learning Vector
Quantization and Kohonen networks. Optimization of the
neural parameters and recognition of images are done using
Genetic algorithm based K Nearest Neighbor algorithm. The
system is trained and tested on Fingerprint Database
obtained from university of Bologna Italy, which consists of
900 samples. The exact image is recognized precisely from
the classified database rather than the original set of
database using Crisp and Fuzzy K Nearest Neighbor algorithm.
This increases recognition accuracy and reduced execution
time. The system is one of the most reliable methods of
personal verification. This can be widely used in criminal
identification, access authority verification, ATM card
verification and many other civilian applications. Keywords: Fingerprint Recognition, Data Mining, K Nearest Neighbor algorithms, Neural Network and Genetic algorithm.
(
Biography:
BibTex: @ARTICLE{P1150729006, AUTHOR = {K. Umamaheswari and S. Sumathi and S. N. Sivanandam and K. K. N. Anburajan}, TITLE = {neuro genetic-nearest neighbor based DATA mINING TECHNIQUES FOR FINGER print classification and recognition system}, JOURNAL ={ICGST International Journal on Graphics, Vision and Image Processing, GVIP},
YEAR = {2007},
VOLUME = {07}, ISSUE ={3}, PAGES={39--50} }
( |
|||||||||||
|