Handwritten characters recognition based on nature-inspired computing and neuro-evolution

The enormous services obtainable by bank and postal systems are not 100 % guaranteed due to variability of handwriting styles. Various methods based on neural networks have been suggested to address this issue. Unfortunately, they often fall into local optima that arises from the use of old learning...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Applied intelligence (Dordrecht, Netherlands) Ročník 38; číslo 2; s. 146 - 159
Hlavní autoři:	Nebti, Salima, Boukerram, Abdellah
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Boston Springer US 01.03.2013 Kluwer Springer Nature B.V
Témata:	Algorithmics. Computability. Computer arithmetics Algorithms Applied sciences Artificial Intelligence Character recognition Computer Science Computer science; control theory; systems Connectionism. Neural networks Data processing. List processing. Character string processing Exact sciences and technology Genetic algorithms Handwriting Intelligence Machines Manufacturing Mechanical Engineering Memory organisation. Data processing Networks Neural networks Optimization Pattern recognition Pattern recognition. Digital image processing. Computational geometry Processes Proposals Recognition Software Theoretical computing Neuro-evolution Bees’ algorithm Co-evolution PSO Handwritten characters recognition Bank system Bees' algorithm Image processing Evolutionary algorithm Variability Aggregate model Voting Classification Swarm intelligence Majority rule Bayes decision Local search Minimal sum algorithm Global optimum Pattern recognition Neural network Character recognition Particle swarm optimization Radial basis function Optical character recognition Optimal solution Minimax method Manuscript character Artificial intelligence
ISSN:	0924-669X, 1573-7497
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	The enormous services obtainable by bank and postal systems are not 100 % guaranteed due to variability of handwriting styles. Various methods based on neural networks have been suggested to address this issue. Unfortunately, they often fall into local optima that arises from the use of old learning methods. Global optimization methods provided new directions for neural networks evolution that may be useful in recognition. This paper develops efficient algorithms that compute globally optimal solutions by exploiting the benefits of both swarm intelligence and neuro-evolution in a way to improve the overall performance of a character recognition system. Various adaptations implied to both MLP and RBF networks have been suggested namely: particle swarm optimization (PSO) and the bees algorithm (BA) for characters classification, MLP training or RBF design by co-evolution and effective combinations of MLPs, RBFs or SVMs as an attempt to overcome the drawbacks of old recognition methods. Results proved that networks combination proposals ensure the highest improvement compared to either standard MLP and RBF networks, the co-evolutionary alternatives or other classifiers combination based on common combination rules namely majority voting, the fusion rules of min, max, sum, average, product and Bayes, Decision template and the Behavior Knowledge Space (BKS).
Bibliografie:	SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 14 ObjectType-Article-1 ObjectType-Feature-2 content type line 23
ISSN:	0924-669X 1573-7497
DOI:	10.1007/s10489-012-0362-z