Open world face recognition with credibility and confidence measures
作者： Fayin Li , Harry Wechsler
关键词:
摘要: This paper describes a novel framework for the Open World face recognition problem, where one has to provide Reject option. Based upon algorithmic randomness and transduction, particular form of induction, we describe TCM-kNN (Transduction Confidence Machine - kNearest Neighbor) algorithm recognition. The proposed performs much better than PCA is comparable with Fisherfaces. In addition rejection, can assign credibility ("likelihood") confidence ("lack ambiguity") measures identification decisions taken.
springer.com
sci-hub.st 参考文章(9)
Ilia Nouretdinov, Thomas Melluish, Volodya Vovk, Ridge Regression Confidence Machine international conference on machine learning. pp. 385- 392 ,(2001)
Volodya Vovk, Alexander Gammerman, Craig Saunders, None, Machine-Learning Applications of Algorithmic Randomness international conference on machine learning. pp. 444- 453 ,(1999)
Paul Vitányi, Ming Li, An Introduction to Kolmogorov Complexity and Its Applications ,(1993)
Kostas Proedrou, Ilia Nouretdinov, Volodya Vovk, Alex Gammerman, Transductive Confidence Machines for Pattern Recognition Lecture Notes in Computer Science. pp. 381- 390 ,(2002) , 10.1007/3-540-36755-1_32
P.Jonathon Phillips, Harry Wechsler, Jeffery Huang, Patrick J. Rauss, The FERET database and evaluation procedure for face-recognition algorithms Image and Vision Computing. ,vol. 16, pp. 295- 306 ,(1998) , 10.1016/S0262-8856(97)00070-X
Pat Langley, Editorial: On Machine Learning Machine Learning. ,vol. 1, pp. 5- 10 ,(1986) , 10.1023/A:1022687019898
Chengjun Liu, H. Wechsler, Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition IEEE Transactions on Image Processing. ,vol. 11, pp. 467- 476 ,(2002) , 10.1109/TIP.2002.999679
A. Gammerman, V. Vapnik, V. Vovk, Learning by transduction uncertainty in artificial intelligence. pp. 148- 155 ,(1998)
Ming Li, Paul Vitányi, An Introduction to Kolmogorov Complexity and Its Applications Springer New York. ,(1997) , 10.1007/978-1-4757-2606-0