Conference Proceeding

Fuzzy Edge Detection in Biometric Systems

Queensland Univ. of Technol., Brisbane
11/2007; DOI:10.1109/AIPR.2007.10 ISBN: 978-0-7695-3066-6 pp.139 - 144 In proceeding of: Applied Imagery Pattern Recognition Workshop, 2007. AIPR 2007. 36th IEEE
Source: IEEE Xplore

ABSTRACT This paper proposes a fuzzy logic based edge detector for feature extraction in biometric systems such as face and palm print recognition. Edge detection is carried out by means of global (histogram of gray levels) and local (pixels within in a window) information. The local information is fuzzified by employing a modified Gaussian membership function. Using the contrast intensification operator, the image is enhanced to the required level of visual quality by entropy optimization of fuzzification parameters. Furthermore, the local edge detection operator is applied on the enhanced image using parameters obtained from entropy optimization. Finally, a simple threshold is applied to produce the skeleton image. Results demonstrate that this edge detector is well suited for feature extraction in biometric image systems.

0 0
 · 
0 Bookmarks
 · 
34 Views
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Keywords

biometric image systems
 
biometric systems
 
contrast intensification operator
 
Edge detection
 
edge detector
 
enhanced image
 
entropy optimization
 
feature extraction
 
global
 
gray levels
 
local edge detection operator
 
local information
 
modified Gaussian membership function
 
simple threshold
 
skeleton image
 
visual quality