论文信息 - Cascade classifier: design and application to digit recognition

Cascade classifier: design and application to digit recognition

The focus of this paper is on machine learning. More specifically, a classifier combination is proposed. We name it "cascade classifier". Conceptually, this system is based on confusion analysis and local retraining mechanism. We describe its architecture. Experiments with handwritten digit images of the MNIST ("modified NIST") database are presented.

Hubert Emptoz | Jean Duong | H. Emptoz | J. Duong

[1] Fabio Roli,et al. Automatic Design of Multiple Classifier Systems by Unsupervised Learning , 1999, MLDM.

[2] David G. Stork,et al. Pattern Classification , 1973 .

[3] Gilbert Saporta,et al. Probabilités, Analyse des données et statistique , 1991 .

[4] Gilbert Saporta,et al. L'analyse des données , 1981 .

[5] Simon Haykin,et al. GradientBased Learning Applied to Document Recognition , 2001 .

[6] Shigeo Abe DrEng. Pattern Classification , 2001, Springer London.

[7] Fabio Roli,et al. Dynamic Classifier Selection , 2000, Multiple Classifier Systems.

[8] Robert Sabourin,et al. Proposition d'un classificateur en cascade : application à la reconnaissance de polices de caractères rares , 2004 .

[9] Lionel Prevost,et al. Combining model-based and discriminative classifiers: application to handwritten character recognition , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[10] Yoshua Bengio,et al. Gradient-based learning applied to document recognition , 1998, Proc. IEEE.