The multiple biometrics feature can achieve high accuracy due to its stable and uniqueness of features. In this paper, the Scale Invariant Feature Transform (SIFT) algorithm and Speeded Up Robust Features (SURF) algorithm are compared to analyze the speed and accuracy of multiple biometrics to extract pixel energy. The SIFT and SURF method extracts local feature points for all biometrics, then identifies the scale invariant in each biometrics and then express key points used to local patterns around the key points. The fuzzy-c mean algorithm is utilized segmentation after pre-processing is applied to all images using a brightness image. The result of the experiment proved that the SURF algorithm is faster than SIFT

Speeded Up Robust Features (SURF), fuzzy c mean segmentation, Scale Invariant Feature Transformation (SIFT)