Invalid face images verifying for face recognition with partial occlusion

From an observation on the joint distribution of similarity scores obtained by our proposed similarity calculation method, we propose a novel measurement for verifying the invalid testing images in face recognition. The new measurement shows improved performance over traditional residuals-based decision measurement and robustness to partial occlusion.

[1]  Zhi-Hua Zhou,et al.  Recognizing partially occluded, expression variant faces from single training image per person with SOM and soft k-NN ensemble , 2005, IEEE Transactions on Neural Networks.

[2]  Zengfu Wang,et al.  A Similarity Measure Based on Hausdorff Distance for Human Face Recognition , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[3]  Hui Lin,et al.  Robust person identification with face and iris by modified PUM method , 2009, 2009 International Conference on Apperceiving Computing and Intelligence Analysis.

[4]  N. Sudha,et al.  Gray Hausdorff distance measure for comparing face images , 2006, IEEE Transactions on Information Forensics and Security.

[5]  Jie Lin,et al.  Robust face recognition with partially occluded images based on a single or a small number of training samples , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.