Üç Boyutluekil Bilgisiyle Yüz Tanimada Siralamaya Dayali Karar Birletirimi Rank-based Decision Fusion for 3D Shape-based Face Recognition

In 3D face recognition systems, 3D facial shape information plays an important role. Various shape representations have been proposed in the literature. The most popular techniques are based on point clouds, surface normals, facial profiles, and statistical analysis of depth images. The contribution of the presented work can be divided into two parts. In the first part, we have developed face classifiers which uses these popular techniques. A comprehensive comparison of these representation methods are given using 3D RMA dataset. Experimental results show the linear discriminant analysisbased representation of depth images and point cloud representations are the best ones. In the second part of the paper, two different multiple-classifier architectures are developed which fuse individual shape-based face recognizers in a parallel and a serial fashion at the decision level. It is shown that a significant performance improvement is possible when using rank-based decision fusion in ensemble methods.

[1]  Berk Gökberk,et al.  3D shape-based face recognition using automatically registered facial surfaces , 2004, ICPR 2004.

[2]  Feng Han,et al.  3D human face recognition using point signature , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[3]  Evangelos E. Milios,et al.  Matching range images of human faces , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[4]  Patrick J. Flynn,et al.  A Survey Of 3D and Multi-Modal 3D+2D Face Recognition , 2004 .

[5]  Anil K. Jain,et al.  Matching 2.5D Scans for Face Recognition , 2004, ICBA.

[6]  Zhaohui Wu,et al.  Automatic 3D face verification from range data , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[7]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Gordon Erlebacher,et al.  A novel technique for face recognition using range imaging , 2003, Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings..

[9]  Tieniu Tan,et al.  Automatic 3D face recognition combining global geometric features with local shape variation information , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[10]  Hiromi T. Tanaka,et al.  Curvature-based face surface recognition using spherical correlation. Principal directions for curved object recognition , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[11]  Jaechang Shim,et al.  3D Face Recognition using Statistical Multiple Features for the Local Depth Information , 2003 .

[12]  Michael G. Strintzis,et al.  Use of depth and colour eigenfaces for face recognition , 2003, Pattern Recognit. Lett..

[13]  Daniel Rueckert,et al.  Evaluation of automatic 4D face recognition using surface and texture registration , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[14]  Gulzar A. Khuwaja,et al.  An Adaptive Combined Classifier System for Invariant Face Recognition , 2002, Digit. Signal Process..

[15]  Anil K. Jain,et al.  Integrating Range and Texture Information for 3D Face Recognition , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[16]  Ofer Melnik,et al.  Mixed group ranks: preference and confidence in classifier combination , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Marc Acheroy,et al.  Face verification from 3D and grey level clues , 2001, Pattern Recognit. Lett..

[18]  Chin-Seng Chua,et al.  Facial feature detection and face recognition from 2D and 3D images , 2002, Pattern Recognit. Lett..

[19]  Patrick J. Flynn,et al.  Face Recognition Using 2D and 3D Facial Data , 2003 .

[20]  Adnan Acan,et al.  Multiple classifier implementation of a divide-and-conquer approach using appearance-based statistical methods for face recognition , 2004, Pattern Recognit. Lett..