Human Identity System by Employing Scale Invariant Feature Transform

Ms. V. L. Bagal; Prof. N. B. Sambre

Now days due to the increase in security requirements, biometric systems have been commonly utilized in many recognition applications. Multimodal has great demands to overcome the issue involved in single trait system and it has become one of the most important research areas of pattern recognition. We present multimodal face and fingerprint biometric verification system to improve the performance. We presented fusion of face and fingerprint to provide better accuracy. Simulation results shows that proposed multimodal recognition system is very efficient to reduce the false accept rate. Here we can take two images i.e. face and fingerprint of a person, decomposition of images is carried out by using DWT i.e. Discrete Wavelet Transform which gives better results , after decomposition , fusion of decomposition is carried out based on averaging of pixels which produces a fused image. Then SIFT (Scale Invariant Feature Transform), features are extracted from the fused image that are invariant to image rotation, scaling, translation, partly illumination. After extracting SIFT features matching is performed based on Euclidean distance.

Select Volume / Issues:

• Volume 3 Issue 6, Nov. 2012

Year:

2012

Type of Publication:

Article

Keywords:

Multimodal Biometric Fusion; Discrete Wavelet Transform DWT; Scale Invariant Feature Transform SIFT; Image Fusion; Image Matching

Journal:

IJECCE

Volume:

3

Number:

6

Pages:

1626-1629

Month:

November