A Novel Approach for Biometric Identification through Palm and Hand Geometry

Abstract

In this paper, proposes a new approach for multimodalbiometric personal Identification system. A combination of handgeometry and palmprint features improves the performance ofpalmprint based Identification system. First, the hand geometryIdentification system performs the feature extraction to obtain thegeometrical information of the fingers and palm. Second, the regionof interest (ROI) is detected and cropped by palmprint Identificationsystem from the hand image. The palmprint features are extractedusing Gabor filter from the ROI. After extraction, Feature levelfusion (FLF) is performed to fuse the palm and hand features. Thefeature level fusion (FLF) of these features improves the recognitionaccuracy significantly. This paper proposes a new multimodalbiometric system that combines palm and hand geometry informationat feature level, with the experimental results showing that thepresented approach significantly improves the Identificationaccuracy.