Data Management

Extraction Method of Handwritten Digit Recognition Tested on the MNIST Database

Free registration required

Executive Summary

The neural networks are widely used for the recognition of characters. In this paper, the authors train and test a neural network classifier using MNIST database, the important step in the recognition is learning, they used descent of the gradient algorithm. 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.

  • Format: PDF
  • Size: 338.03 KB