Advanced Authentication Scheme using Multimodal Biometric Scheme

Abstract

Fingerprint recognition has attracted various researchers and achieved great success. But, fingerprint alone may not be able to meet the increasing demand of high accuracy in today's biometric system. The purpose of our paper is to inspect whether the integration of palmprint and fingerprint biometric can achieve performance that may not be possible using a single biometric technology. Pre-processing is done for fingerprint and palmprint images separately in order to remove any noise. The next step is feature extraction. Minutiae algorithm is used for fingerprint feature extraction and Local Binary pattern for palmprint. Wavelet fusion is applied in order to fuse the extracted features and Support Vector Machine is used for matching. The main highlight of the project is multimodal biometrics which will give a better security and accuracy comparing to unimodel system.

“Feature level fusion of face, palm vein and palm print modalities using Discrete Cosine Transform”

“…Using minutiae extraction for fingerprint image, local binary pattern for extracting features of palm print and combining using wavelet based fusion technique outperforms individual modalities being used for recognition. This is sensitive to varying rotation and translation [13].We can go for DCT to extract information present in frequency domain and to utilize it during recognition stage.…”