원문정보
초록
영어
This paper deals with an optical character recognition (OCR) system of handwritten digit, with the use of neural networks (MLP multilayer perceptron). And a method of extraction of characteristics based on the digit form, this method is tested on the MNIST handwritten isolated digit database (60000 images in learning and 10000 images in test). This work has achieved approximately 80% of success rate for MNIST database identification.
목차
Abstract
1. Introduction
2. Database
3. Preprocessing
4. Extraction
4.1 Dilatation of Image
4.2 Detection of the Characteristic Zones of the Image
5. Neural networks
5.1 The Perceptron (Rosenblatt, 1958-1962)
5.2 The multi-layer Perceptron (MLP)
5.3 Learning Algorithm
5.4 Methodological Issues
6. Classification
6.1 Experimental Results
7. Conclusion
Acknowledgements
References
1. Introduction
2. Database
3. Preprocessing
4. Extraction
4.1 Dilatation of Image
4.2 Detection of the Characteristic Zones of the Image
5. Neural networks
5.1 The Perceptron (Rosenblatt, 1958-1962)
5.2 The multi-layer Perceptron (MLP)
5.3 Learning Algorithm
5.4 Methodological Issues
6. Classification
6.1 Experimental Results
7. Conclusion
Acknowledgements
References
키워드
저자정보
참고문헌
자료제공 : 네이버학술정보