The image processing handbook (2nd ed.)
The image processing handbook (2nd ed.)
Handwritten Numerical Recognition Using Autoassociative Neural Networks
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
Accuracy Improvement of Handwritten Numeral Recognition by Mirror Image Learning
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Hi-index | 0.02 |
This paper studies on the mirror image learning algorithmfor the autoassociative neural networks and evaluatesthe performance by handwritten numeral recognitiontest. Each of the autoassociative networks is first trainedindependently for each class using the feature vector of theclass. Then the mirror image learning algorithm is appliedto enlarge the learning sample of each class by mirrorimage patterns of the confusing classes to achieve higherrecognition accuracy.Recognition accuracy of the autoassociative neural networkclassifier was improved by the mirror image learningfrom 98.76%to 99.23%in the recognition test for handwrittennumeral database IPTP CD-ROM1 [1].