Finger- image Segmentation using K-means clustering and a comparative analysis with L*A*B* method and detection of the segment using Correlation and Fourier-Series
Keywords:
K-means, L*A*B*, Correlation, Fourier -Series, FingerAbstract
Image segmentation is an important component in many image analysis and computer vision tasks.
Finger-print recognition security systems deploy dormant, contact based scanners that rob the system of its viable
flexibility. In this paper, foundation for a contactless finger-image recognition system is laid. Using K-means
clustering method, finger images, captured using smart-phones, are segmented to extract the finger region. The
same is accomplished using L*A*B* image segmentation algorithm, and a comparative analysis is framed.
Basically a computer based application, Contactless security system demands an automated tool dedicated for
identifying the desired finger-segment from the complete image. For this purpose, two independent algorithms,
namely- correlation and FFT are practiced. The earlier segmentation results, obtained from both the methods, are
employed in these algorithms and the results are scrutinized.


