Handwritten digit recognition using neural networks

Amanda Bischoff; Patrick S. P. Wang

doi:10.1117/12.135109

1 March 1992 Handwritten digit recognition using neural networks

Amanda Bischoff, Patrick S. P. Wang

Proceedings Volume 1608, Intelligent Robots and Computer Vision X: Neural, Biological, and 3-D Methods; (1992) https://doi.org/10.1117/12.135109
Event: Robotics '91, 1991, Boston, MA, United States

Abstract

Character and handwriting recognition is one of the most difficult problems of pattern recognition and artificial intelligence. Unlike the machine generated character, which is uniform throughout a document and often uniform between machines, each human being has a unique style of writing characters. With the infinite number of ways to record a character, it is a wonder that a person can understand his own script, let alone the script of another. Training a computer to recognize human-produced characters is a tremendous task in which researchers are just beginning to achieve some success. Primarily these methods rely on the use of algorithms to determine the similarities of two characters. Neural networks are an alternative technique now being explored. Four separate methods will be discussed in this paper. The first involves normalization, skeletonization, and feature extraction of a handwritten digit before application to a neural network for classification. The second simply applies a normalized digit to the neural net's input, and the network performs a 2-dimensional convolution on it in order to classify the digit. The third method involves a hierarchical network. The final technique incorporates time information into the system while using simple preprocessing and a small number of parameters. Their advantages and disadvantages are compared and discussed.

Citation Download Citation

Amanda Bischoff and Patrick S. P. Wang "Handwritten digit recognition using neural networks", Proc. SPIE 1608, Intelligent Robots and Computer Vision X: Neural, Biological, and 3-D Methods, (1 March 1992); https://doi.org/10.1117/12.135109

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available