DocumentCode :
2082320
Title :
An efficient technique for ear detection in 3D: Invariant to rotation and scale
Author :
Prakash, Sachin ; Gupta, Puneet
Author_Institution :
Dept. of Comput. Sci. & Eng., Indian Inst. of Technol. Kanpur, Kanpur, India
fYear :
2012
fDate :
March 29 2012-April 1 2012
Firstpage :
97
Lastpage :
102
Abstract :
This paper proposes an efficient technique to detect ear from 3D profile face range images and is invariant to rotation and scale. It makes use of graph connected components constructed using the edges of the depth map image of the range data for ear detection. It can detect left and right ears at the same time without imposing any additional cost or specific training. The technique has been tested on University of Notre Dame 3D profile face database, Collection J2 (UND-J2) having range images with scale and pose variations. Results are also compared with the well known 3D ear detection techniques to show its superiority.
Keywords :
ear; edge detection; graph theory; object detection; visual databases; 3D profile face range images; Collection J2; UND-J2; University of Notre Dame 3D profile face database; depth map image edge; graph connected components; left ear detection; pose variations; right ear detection; rotation invariance; scale invariance; scale variations; Accuracy; Databases; Ear; Face; Image edge detection; Shape; Three dimensional displays; Biometrics; Connected Components; Ear Detection; Ear Localization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biometrics (ICB), 2012 5th IAPR International Conference on
Conference_Location :
New Delhi
Print_ISBN :
978-1-4673-0396-5
Electronic_ISBN :
978-1-4673-0397-2
Type :
conf
DOI :
10.1109/ICB.2012.6199765
Filename :
6199765
Link To Document :
بازگشت