International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 59 - Issue 9 |
Published: December 2012 |
Authors: Manas Ranjan Nayak, Saswat Nayak, Yetirajam Manas, Sangeeta Bhanja Chaudhuri, Subhagata Chattopadhyay |
![]() |
Manas Ranjan Nayak, Saswat Nayak, Yetirajam Manas, Sangeeta Bhanja Chaudhuri, Subhagata Chattopadhyay . Automatic Recognition of Handwritten Bengali Broken Characters (BBC): Simulating Human Pattern Matching. International Journal of Computer Applications. 59, 9 (December 2012), 27-32. DOI=10.5120/9578-4055
@article{ 10.5120/9578-4055, author = { Manas Ranjan Nayak,Saswat Nayak,Yetirajam Manas,Sangeeta Bhanja Chaudhuri,Subhagata Chattopadhyay }, title = { Automatic Recognition of Handwritten Bengali Broken Characters (BBC): Simulating Human Pattern Matching }, journal = { International Journal of Computer Applications }, year = { 2012 }, volume = { 59 }, number = { 9 }, pages = { 27-32 }, doi = { 10.5120/9578-4055 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2012 %A Manas Ranjan Nayak %A Saswat Nayak %A Yetirajam Manas %A Sangeeta Bhanja Chaudhuri %A Subhagata Chattopadhyay %T Automatic Recognition of Handwritten Bengali Broken Characters (BBC): Simulating Human Pattern Matching%T %J International Journal of Computer Applications %V 59 %N 9 %P 27-32 %R 10.5120/9578-4055 %I Foundation of Computer Science (FCS), NY, USA
This paper presents an automatic detection of handwritten Bengali Broken Characters (BBC) using a feed forward neural network (FFNN). It simulates the Human Visual System (HVS) the way human eye matches the patterns of the broken characters to a meaningful character and identifies it. Here the challenge is to detect and retrieve handwritten character which has been distorted up to 90%. The database consists of fifty bangle characters, each with twenty samples. Each character is presented as an image, which has been preprocessed, segmented and the features are then extracted. A new method has been proposed in this paper. It uses FFNN to calculate the mismatch for the recognition of a character, where it is observed that the distorted characters show very low mismatch with the original characters. For example, characters up to 70% distortions are found to be retrieved effectively.