Forensics in Telecommunications, Information and Multimedia. Second International Conference, e-Forensics 2009, Adelaide, Australia, January 19-21, 2009, Revised Selected Papers

Research Article

A Novel Handwritten Letter Recognizer Using Enhanced Evolutionary Neural Network

Download
525 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-02312-5_1,
        author={Fariborz Mahmoudi and Mohsen Mirzashaeri and Ehsan Shahamatnia and Saed Faridnia},
        title={A Novel Handwritten Letter Recognizer Using Enhanced Evolutionary Neural Network},
        proceedings={Forensics in Telecommunications, Information and Multimedia. Second International Conference, e-Forensics 2009, Adelaide, Australia, January 19-21, 2009, Revised Selected Papers},
        proceedings_a={E-FORENSICS},
        year={2012},
        month={5},
        keywords={Handwritten Character Recognition Neural Network Hybrid Evo-lutionary Algorithm EANN},
        doi={10.1007/978-3-642-02312-5_1}
    }
    
  • Fariborz Mahmoudi
    Mohsen Mirzashaeri
    Ehsan Shahamatnia
    Saed Faridnia
    Year: 2012
    A Novel Handwritten Letter Recognizer Using Enhanced Evolutionary Neural Network
    E-FORENSICS
    Springer
    DOI: 10.1007/978-3-642-02312-5_1
Fariborz Mahmoudi1,*, Mohsen Mirzashaeri1,*, Ehsan Shahamatnia1,*, Saed Faridnia1,*
  • 1: Islamic Azad University
*Contact email: Mahmoudi@QazvinIAU.ac.ir, Mirzashaeri@QazvinIAU.ac.ir, E.Shahamatnia@QazvinIAU.ac.ir, SFaridnia@QazvinIAU.ac.ir

Abstract

This paper introduces a novel design for handwritten letter recognition by employing a hybrid back-propagation neural network with an enhanced evolutionary algorithm. Feeding the neural network consists of a new approach which is invariant to translation, rotation, and scaling of input letters. Evolutionary algorithm is used for the global search of the search space and the back-propagation algorithm is used for the local search. The results have been computed by implementing this approach for recognizing 26 English capital letters in the handwritings of different people. The computational results show that the neural network reaches very satisfying results with relatively scarce input data and a promising performance improvement in convergence of the hybrid evolutionary back-propagation algorithms is exhibited.