Active shape models—their training and application
Computer Vision and Image Understanding
Efficient Pattern Recognition Using a New Transformation Distance
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Online Character Recognition Based on Elastic Matching and Quadratic Discrimination
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Handwritten character recognition using elastic matching and PCA
Proceedings of the International Conference on Advances in Computing, Communication and Control
PCM'10 Proceedings of the Advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II
PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part I
Hi-index | 0.00 |
For handwritten character recognition, a new elastic imagematching (EM) technique based on a class-dependentdeformation model is proposed. In the deformation model,any deformation of a class is described by a linear combinationof eigen-deformations, which are intrinsic deformationdirections of the class. The eigen-deformations canbe estimated statistically from the actual deformations ofhandwritten characters. Experimental results show that theproposed technique can attain higher recognition rates thanconventional EM techniques based on class-independentdeformation models. The results also show the superiorityof the proposed technique over those conventional EMtechniques in computational efficiency.