☰ Category

Handwritten Devnagari Character Recognition using Soft Computing

 

Marketed By :  LAP LAMBERT Academic Publishing   Sold By :  Kamal Books International  
Delivery in :  10-12 Business Days

 

Check Your Delivery Options

Product Out of Stock Subscription

(Notify me when this product is back in stock)

Rs. 4,396

Availability: Out of stock

 
  • Product Description
 

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.

Product Specifications
SKU :COC24564
AuthorSandhya Arora,Debotosh Bhattacharjee and Mita Nasipuri
LanguageEnglish
BindingPaperback
Number of Pages156
Publishing Year2012-10-11T00:00:00.000
ISBN978-3659278419
Edition1 st
Book TypeMathematics
Country of ManufactureIndia
Product BrandLAP LAMBERT Academic Publishing
Product Packaging InfoBox
In The Box1 Piece
Product First Available On ClickOnCare.com2015-07-28 00:00:00
0 Review(s)