A class-modular generalized learning vector quantization (GLVQ) ensemble method with outlier learning for handwritten digit recognition is proposed. A GLVQ classifier is a discriminative method. Though discriminative classifiers have the remarkable ability to solve character recognition problems, they are poor at outlier resistance. To overcome this problem, a GLVQ classifier trained with both digit images and outlier images is introduced. Moreover, the original 10-classification problem is separated into ten 2-classification problems using ten GLVQ classifiers, each of which recognizes its corresponding digit class. Experimental results of handwritten digit recognition and outlier rejection reveal that our method is far more superior at outlier resistance than a conventional GLVQ classifier, while maintaining its digit recognition performance.
A class-modular GLVQ ensemble with outlier learning for handwritten digit recognition
2003-01-01
319984 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
A Class-modular GLVQ Ensemble with Outlier Learning for Handwritten Digit Recognition
British Library Conference Proceedings | 2003
|Fourier descriptors and handwritten digit recognition
British Library Online Contents | 1993
|Graph-Based Handwritten Digit String Recognition
British Library Conference Proceedings | 1995
|Handwritten Digit Recognition Based on a Neural - SVM Combination
British Library Online Contents | 2010
|Handwritten Digit Recognition Using State-of-the-Art Techniques
British Library Conference Proceedings | 2002
|