Paper
1 March 1992 Handwritten digit recognition using neural networks
Amanda Bischoff, Patrick S. P. Wang
Author Affiliations +
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.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
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
Lens.org Logo
CITATIONS
Cited by 3 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Neural networks

Computer vision technology

Machine vision

Robot vision

Robots

Feature extraction

Pattern recognition

RELATED CONTENT

Contemporary deep recurrent learning for recognition
Proceedings of SPIE (May 01 2017)
Pattern Recognition Using A Neural Network
Proceedings of SPIE (February 19 1988)
Neural network approach for inventory control
Proceedings of SPIE (November 01 1992)
Pattern recognition using stochastic neural networks
Proceedings of SPIE (August 20 1993)
Improved adaptive resonance theory
Proceedings of SPIE (February 01 1991)
Fuzzy Logic Inference Neural Networks
Proceedings of SPIE (March 01 1990)
Prototype neural network pattern recognition testbed
Proceedings of SPIE (February 01 1991)

Back to Top