Principles of artificial intelligence
Principles of artificial intelligence
Training with noise is equivalent to Tikhonov regularization
Neural Computation
SIAM Journal on Computing
Training Set Expansion in Handwritten Character Recognition
Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Perceptual Model of Handwriting Drawing Application to the Handwriting Segmentation Problem
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Generation of Synthetic Training Data for an HMM-based Handwriting Recognition System
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Solving analogies on words: an algorithm
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Robust Boosting for Learning from Few Examples
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Learning by analogy: a classification rule for binary and nominal data
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Hi-index | 0.00 |
This paper is basically concerned with a practical problem: the on-the-fly quick learning of handwritten character recognition systems. More generally, it explores the problem of generating new learning examples, especially from very scarce (2 to 5 per class) original learning data. It presents two different methods. The first one is based on applying distortions on original characters using knowledgeon handwriting properties like speed, curvature etc. The second one consists in generation based on the notion of analogical dissimilaritywhich quantifies the analogical relation "Ais to Balmost as Cis to D". We give an algorithm to compute the k-least dissimilar objects D, hence generating knew objects from three examples A, Band C. Finally, we experimentally prove the efficiency of both methods, especially when used in conjunction.