|
|||
|---|---|---|---|
Iris Feature Extraction Based on Directional Image Representation C. Helen Sulochana1 and S. Selvan2 1Department of Electronics and Communication Engineering, Noorul Islam College of Engineering, Kanya Kumari District, Tamil Nadu, India
2Department of Information and Technology,
PSG College of Technology, Coimbatore, Tamil Nadu, India
In this paper we propose a new feature extraction method for iris recognition. The direction and enhancement of linear features is an important task in image processing applications. The directional filter bank (DFB) is used to provide a compact and efficient representation of features. This helps in fast classification using classical statistical methods. The proposed method decomposes the iris image into eight directional subband outputs using a DFB and then obtains directional energy distribution for each block of the subband output. Only dominant directional energy components are employed as elements of the input feature vector. These input feature vectors are compared with the template feature vectors. Experimental results show that efficient DFB structure and the directional specific information reduce processing time and increase the classification accuracy when compared with the Gabor filter bank method. Keywords: Biometrics, decidability index, directional filter bank, iris recognition, quincunx sampling
@ARTICLE{P1150640002, AUTHOR = {C. Helen Sulochana and S. Selvan}, TITLE = {Iris Feature Extraction Based on Directional Image Representation}, JOURNAL ={ICGST International Journal on Graphics, Vision and Image Processing},
YEAR = {2007},
VOLUME = {06}, ISSUE ={4}, PAGES={55--62} } ( |
|||
|
