Performance analysis of integrated multimodal biometrics by means of soft computing techniques

Providing security by means of using traditional methods such as PINs, Passwords, access cards are being vulnerable to various attacks and are easily hacked by intruders or unauthorized users. The aim is to develop an efficient personal identification system to provide secure access for legitimate users which is a challenging task. In order to avoid these problems, the use of biométrie traits reliably provides efficient and effective solutions. Though unimodal biometrics faces various issues such as non-universality, distinctiveness, spoof attacks, noise in sensed data, intra-class variations. To overcome these issues, Multimodal biometrics based personal identification system is developed using Soft Computing Techniques. The biométrie traits such as fingerprint, palmprint and finger knuckle print are used for recognition system. Artificial Neural Networks (ANN) and Genetic Algorithm are used for this purpose. The Haralick features are used for the recognition system. The proposed system achieves excellent identification rate and higher user acceptability. Thus the proposed system reduces the FRR rate.