The Community for Technology Leaders
Green Image
This paper aims to improve the performance of an HMM-based offline Thai handwriting recognition system through discriminative training and the use of fine-tuned feature extraction methods. The discriminative training is implemented by maximizing the mutual information between the data and their classes. The feature extraction is based on our proposed block-based PCA and composite images, shown to be better at discriminating Thai confusable characters. We demonstrate significant improvements in recognition accuracies compared to the classifiers that are not discriminatively optimized.
Character recognition, Hidden Markov Model, discriminative training, PCA, feature extraction, Thai handwriting recognition.

R. Nopsuwanchai, W. F. Clocksin and A. Biem, "Maximization of Mutual Information for Offline Thai Handwriting Recognition," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 28, no. , pp. 1347-1351, 2006.
95 ms
(Ver 3.3 (11022016))