DocumentCode :
2660209
Title :
A morphing technique for facial image representation
Author :
Kouzani, Abbas Z. ; Nahavandi, S. ; Kouzani, N. ; Kong, L.X. ; She, F.H.
Author_Institution :
Sch. of Eng. & Technol., Deakin Univ., Geelong, Vic., Australia
Volume :
2
fYear :
2000
fDate :
2000
Firstpage :
1378
Abstract :
Presents a method for the representation of facial images. The proposed method consists of two modules: face-image matching and face-image morphing. In the first module, the correspondence between two images are calculated for all pixel locations. A novel area-based matching method is proposed that makes use of the concept of the fractal dimension, and develops a non-parametric local transform as a basis for establishing the correspondence between two face images. In the second module, a mapping is performed for deformation of the source face image on to the target face image. This is done to map the pixels in the source face image to the location of their corresponding pixels in the target image
Keywords :
face recognition; image matching; image morphing; image representation; subroutines; area-based matching method; face image matching; face image morphing; facial image representation; fractal dimension; image correspondence; image deformation; modules; nonparametric local transform; pixel locations; Australia; Distance measurement; Eyes; Face detection; Face recognition; Fractals; Image representation; Mouth; Nose; Pixel;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man, and Cybernetics, 2000 IEEE International Conference on
Conference_Location :
Nashville, TN
ISSN :
1062-922X
Print_ISBN :
0-7803-6583-6
Type :
conf
DOI :
10.1109/ICSMC.2000.886046
Filename :
886046
Link To Document :
بازگشت