handwritten devnagari character recognition di arora sandhya (5 risultati)

Taschenbuch. Condizione: Neu. Neuware -Handwriting recognition is a difficult problem, because of the great amount of variations in human handwriting. When observed in isolation also, characters are often ambiguous. We have implemented some soft computing techniques using structural and statistical feature sets for constrained handwritten isolated Devnagari characters and numerals. Some preprocessing steps are applied before extracting statistical and structural information of character image. As conventional histogram based method does not work for handwritten Devnagari characters, differential distance based technique is designed to find shirorekha and spine. Multilayer perceptron, support vector machines and edit distance classifiers are used for classification. Three MLP combination techniques namely: max, min and weighted majority scheme is applied. Two approaches for two stage classification is discussed in detail to improve the accuracy. As there are many similar shaped characters, character set is grouped in two sets-- certainty and confused character set. Relative difference measure is used for grouping of character sets. Each set is classified using different classifier.Books on Demand GmbH, Überseering 33, 22297 Hamburg 156 pp. Englisch.

Paperback. Condizione: Like New. Like New. book.

Taschenbuch. Condizione: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Handwriting recognition is a difficult problem, because of the great amount of variations in human handwriting. When observed in isolation also, characters are often ambiguous. We have implemented some soft computing techniques using structural and statistical feature sets for constrained handwritten isolated Devnagari characters and numerals. Some preprocessing steps are applied before extracting statistical and structural information of character image. As conventional histogram based method does not work for handwritten Devnagari characters, differential distance based technique is designed to find shirorekha and spine. Multilayer perceptron, support vector machines and edit distance classifiers are used for classification. Three MLP combination techniques namely: max, min and weighted majority scheme is applied. Two approaches for two stage classification is discussed in detail to improve the accuracy. As there are many similar shaped characters, character set is grouped in two sets-- certainty and confused character set. Relative difference measure is used for grouping of character sets. Each set is classified using different classifier. 156 pp. Englisch.

Condizione: New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Arora SandhyaSANDHYA ARORA is PhD., M.Tech. and B.E.(Computer Engineering), India. She is currently working as Assistant Professor in India,having teaching experience of 15 years. She has presented 5 papers in national and 4 papers i.

Taschenbuch. Condizione: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - Handwriting recognition is a difficult problem, because of the great amount of variations in human handwriting. When observed in isolation also, characters are often ambiguous. We have implemented some soft computing techniques using structural and statistical feature sets for constrained handwritten isolated Devnagari characters and numerals. Some preprocessing steps are applied before extracting statistical and structural information of character image. As conventional histogram based method does not work for handwritten Devnagari characters, differential distance based technique is designed to find shirorekha and spine. Multilayer perceptron, support vector machines and edit distance classifiers are used for classification. Three MLP combination techniques namely: max, min and weighted majority scheme is applied. Two approaches for two stage classification is discussed in detail to improve the accuracy. As there are many similar shaped characters, character set is grouped in two sets-- certainty and confused character set. Relative difference measure is used for grouping of character sets. Each set is classified using different classifier.