This Article 
 Bibliographic References 
 Add to: 
An evaluation of multimodal 2D+3D face biometrics
April 2005 (vol. 27 no. 4)
pp. 619,620,621,622,623,624
We report on the largest experimental study to date in multimodal 2D+3D face recognition, involving 198 persons in the gallery and either 198 or 670 time-lapse probe images. PCA-based methods are used separately for each modality and match scores in the separate face spaces are combined for multimodal recognition. Major conclusions are: 1) 2D and 3D have similar recognition performance when considered individually, 2) combining 2D and 3D results using a simple weighting scheme outperforms either 2D or 3D alone, 3) combining results from two or more 2D images using a similar weighting scheme also outperforms a single 2D image, and 4) combined 2D+3D outperforms the multi-image 2D result. This is the first (so far, only) work to present such an experimental control to substantiate multimodal performance improvement.

[1] S. Lao, Y. Sumi, M. Kawade, and F. Tomita, “3D Template Matching for Pose Invariant Face Recognition Using 3D Facial Model Built with Isoluminance Line Based Stereo System,” Proc. Int'l Conf. Pattern Recognition, vol. 2, pp. 911-916, 2000.
[2] Y. Wang, C. Chua, and Y. Ho, “Facial Feature Detection and Face Recognition from 2D and 3D Images,” Pattern Recognition Letters, vol. 23, pp. 1191-1202, 2002.
[3] C. Beumier and M. Acheroy, “Automatic Face Verification from 3D and Grey Level Clues,” Proc. 11th Portuguese Conf. Pattern Recognition, pp. 95-101, 2000.
[4] F. Tsalakanidou, S. Malassiotis, and M. Strintzis, “Integration of 2D and 3D Images for Enhanced Face Authentication,” Proc. Sixth Int'l Conf. Automated Face and Gesture Recognition, pp. 266-271, May 2004.
[5] K. Chang, K. Bowyer, and P. Flynn, “Face Recognition Using 2D and 3D Facial Data,” Proc. ACM Workshop Multimodal User Authentication, pp. 25-32, Dec. 2003.
[6] K. Chang, K. Bowyer, and P. Flynn, “Multi-Biometrics Using Facial Appearance, Shape, and Temperature,” Proc. Sixth IEEE Int'l Conf. Face and Gesture Recognition, pp. 43-48, 2004.
[7] K. Bowyer, K. Chang, and P. Flynn, “A Short Survey of 3D and Multi-Modal 3D+2D Face Recognition,” Proc. Int'l Conf. Pattern Recognition, 2004.
[8] N. Poh, S. Bengio, and J. Korczak, “A Multi-Sample Multi-Source Model for Biometric Authentication,” Proc. IEEE Workshop Neural Networks for Signal Processing, pp. 375-384, 2002.
[9] J. Phillips, H. Moon, S. Rizvi, and P. Rauss, “The FERET Evaluation Methodology for Face-Recognition Algorithms,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 10, pp. 1090-1104, Oct. 2000.
[10] W. Yambor, B. Draper, and R. Beveridge, “Analyzing PCA-Based Face Recognition Algorithms: Eigenvector Selection and Distance Measures,” Proc. Second Workshop Empirical Evaluation in Computer Vision, 2000.
[11] J. Min, P. Flynn, and K. Bowyer, “Using Multiple Gallery and Probe Images Per Person to Improve Performance of Face Recognition,” Technical Report TR-03-7, Univ. of Notre Dame, 2003.
[12] G. Givens, R. Beveridge, B. Draper, and D. Bolme, “A Statistical Assessment of Subject Factors in the Pca Recognition of Human Faces,” Proc. Workshop Statistical Analysis in Computer Vision (CVPR), 2003.

Index Terms:
Biometrics,Face recognition,Probes,Image recognition,Speech,Image sensors,Lenses,Terminology,Digital cameras,multisample.,Index Terms- Biometrics,face recognition,three-dimensional face,multimodal
"An evaluation of multimodal 2D+3D face biometrics," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 4, pp. 619,620,621,622,623,624, April 2005, doi:10.1109/TPAMI.2005.70
Usage of this product signifies your acceptance of the Terms of Use.