Title :
Hand geometry pattern recognition through Gaussian mixture modelling
Author :
Sanchez-Reillo, R.
Author_Institution :
ETSI Telecomunicacion, Univ. Politecnica de Madrid, Spain
Abstract :
Gaussian mixture modelling (GMM) is a statistical pattern recognition technique usually applied to speaker identification. This technique can be used with morphological features extracted from images. Therefore, this technique is applied to hand geometry biometrics in order to improve the results obtained with other verification techniques. This biometric technique, which is considered to be a low-medium security one, can be applied to high security environments due to its error rates below 5%. The features to enter the GMM algorithm can be extracted from a color image of the hand (both the top and the side view of it). This image can then be processed and its edge detected before a morphological analysis is performed, thus obtaining a feature vector as small as 12 bytes. In this paper, after a short introduction and a general overview of the GMMs, the whole process is explained
Keywords :
Gaussian processes; biometrics (access control); computational geometry; edge detection; feature extraction; image colour analysis; statistical analysis; Gaussian mixture modelling; biometrics; color image; edge detection; features extraction; hand geometry; morphological analysis; statistical pattern recognition; Biometrics; Color; Error analysis; Feature extraction; Geometry; Image analysis; Image edge detection; Pattern recognition; Performance analysis; Security;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.906228