Biometrics and Bioinformatics

C. T. Subash ¹, V. Sujitha ²

Affiliations
1 Tamilnadu College of Engineering, Coimbatore- 641659, IN
2 P.A College of Engineering & Technology, Pollachi-642002, IN

Abstract

In this paper, proposes a new approach for multimoda lbiometric personal Identification system. A combination of handgeometry and palmprint features improves the performance of palmprint based Identification system. First, the hand geometryIdentification system performs the feature extraction to obtain the geometrical information of the fingers and palm. Second, the region of interest (ROI) is detected and cropped by palm print Identification system from the hand image. The palm print features are extracted using Gabor filter from the ROI. After extraction, Feature level fusion (FLF) is performed to fuse the palm and hand features. The feature level fusion (FLF) of these features improves the recognition accuracy significantly. This paper proposes a new multimodalbiometric system that combines palm and hand geometry informationat feature level, with the experimental results showing that the presented approach significantly improves the Identification accuracy.

Keywords

Hand Geometry, Feature Level Fusion, Multimodal, Biometrics, Palmprint.

Full Text

     

R. Vinothkanna ¹, C. T. Subash ¹

Affiliations
1 IT Department, Tamilnadu College of Engineering, Coimbatore-641659, IN

Abstract

Fingerprint authentication remains as one of the most prominent biometric identification methods. In this paper, we propose to use the fingerprint valley instead of ridges for the Binarization and Thinning process to extract fingerprint valley minutiae, because lots of research has done on ridges not on valleys. We first use several preprocessing steps on the binary image in order to eliminate the spurious lakes and dots, and to reduce the spurious islands, bridges, and spurs in the skeleton image. By removing all the bug pixels introduced at the thinning stage, our algorithm can detect a maximum number of minutiae from the fingerprint skeleton using the Gabor filter. This allows the true minutiae preserved and false minutiae removed in post processing stages. Gabor filter has also given lots of best results on ridges extraction. So we tried gabor filter for valley extraction and we got number of minutiae extracted differs from ridges to valleys. The proposed method saves memory space, and also speeds up the whole procedure.

Keywords

Biometrics, Bug Pixel, Fingerprint Minutiae Extraction, Gabor Filter, Valleys.

Full Text