Proceedings ArticleDOI
A comparison of feedforward and self-organizing approaches to the font orientation problems
Reads0
Chats0
TLDR
The problem of determining the orientation of printed text is considered, and a feedforward network with structure and parameters derived using optimal detection theory and the learning vector quantization self-organizing networks of T. Kohonen are described.Abstract:
The problem of determining the orientation of printed text is considered. The problem differs considerably from traditional optical character recognition, and its application to automatic inspection requires efficient processing and highly accurate results. Two methods are described. The first is a feedforward network, with structure and parameters derived using optimal detection theory. The second method makes use of the learning vector quantization self-organizing networks of T. Kohonen (Self-organization and Associative Memory, Springer-Verlag, 1988). Experimental results and a complete implementation are described. Both techniques are found to be successful and their relative advantages are discussed. >read more
Citations
More filters
Bibliography of Self-Organizing Map (SOM) Papers: 1981-1997
TL;DR: A comprehensive list of papers that use the Self-Organizing Map algorithms, have bene ted from them, or contain analyses of them is collected and provided both a thematic and a keyword index to help find articles of interest.
Patent
A technique for object orientation detection using a feed-forward neural network
TL;DR: In this paper, an image of the features or text is used to extract lines using horizontal bitmap sums, and then individual symbols using vertical bitmap sum while using thresholds with each of the sums.
Book ChapterDOI
Modification of Kohonen's SOFM to Simulate Cortical Plasticity Induced by Coactivation Input Patterns
TL;DR: A modification of Kohonens SOFMin is presented to simulate cortical plasticity induced by coactivation patterns by introducing a probabilistic mode of stimulus presentation and substituting the winner-takes- all mechanism by selecting the winner from a set of best matching neurons.
Journal ArticleDOI
Implementing expert system rule conditions by neural networks
TL;DR: The synergy of rules and detector predicates combines the advantages of both worlds: it maintains the clarity of the rule-based knowledge representation at the higher reasoning levels without sacrificing the power of noise-tolerant pattern association offered by neural computing methods.
References
More filters
Book
Self Organization And Associative Memory
TL;DR: The purpose and nature of Biological Memory, as well as some of the aspects of Memory Aspects, are explained.
Proceedings ArticleDOI
Probabilistic neural networks for classification, mapping, or associative memory
TL;DR: It can be shown that by replacing the sigmoid activation function often used in neural networks with an exponential function, a neural network can be formed which computes nonlinear decision boundaries, which yields decision surfaces which approach the Bayes optimal under certain conditions.
Proceedings ArticleDOI
Statistical pattern recognition with neural networks: benchmarking studies
TL;DR: Three basic types of neural-like networks, backpropagation network, Boltzmann machine, and learning vector quantization, were applied to two representative artificial statistical pattern recognition tasks, each with varying dimensionality.
Statistical pattern recognition with neural networks: benchmarking studies.
TL;DR: In this article, three basic types of neural-like networks (Backpropagation network, Boltzmann machine, and Learning Vector Qumtization) were applied to two representative artificial statistical pattern recognition tasks, each with varying dimensionality.