Think globally, fit locally: unsupervised learning of low dimensional manifolds
The Journal of Machine Learning Research
Ear Recognition using Improved Non-Negative Matrix Factorization
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04
IEEE Transactions on Pattern Analysis and Machine Intelligence
Force field feature extraction for ear biometrics
Computer Vision and Image Understanding
Shape and structural feature based ear recognition
SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
Hi-index | 0.00 |
Ear recognition with variant poses is an important problem. In this paper locally linear embedding (LLE) is introduced considering the advantages of LLE, by analyzing the shortcomings of most ear recognition methods currently when dealing with pose variations. Experimental results demonstrate that applying LLE for ear recognition with variant poses is feasible and can obtain the better recognition rate, which shows the validity of this algorithm.