DocumentCode :
2967034
Title :
Handwritten Character Recognition Using Histograms of Oriented Gradient Features in Deep Learning of Artificial Neural Network
Author :
Iamsa-at, Suthasinee ; Horata, Punyaphol
Author_Institution :
Dept. of Comput. Sci., Khon Kaen Univ., Khon Kaen, Thailand
fYear :
2013
fDate :
16-18 Dec. 2013
Firstpage :
1
Lastpage :
5
Abstract :
Feature extraction plays an essential role in hand written character recognition because of its effect on the capability of classifiers. This paper presents a framework for investigating and comparing the recognition ability of two classifiers: Deep-Learning Feedforward-Backpropagation Neural Network (DFBNN) and Extreme Learning Machine (ELM). Three data sets: Thai handwritten characters, Bangla handwritten numerals, and Devanagari handwritten numerals were studied. Each data set was divided into two categories: non-extracted and extracted features by Histograms of Oriented Gradients (HOG). The experimental results showed that using HOG to extract features can improve recognition rates of both of DFBNN and ELM. Furthermore, DFBNN provides higher slightly recognition rates than those of ELM.
Keywords :
backpropagation; feature extraction; feedforward neural nets; handwritten character recognition; Bangla handwritten numerals; DFBNN; Devanagari handwritten numerals; ELM; Thai handwritten characters; artificial neural network; deep learning feedforward backpropagation neural network; extreme learning machine; feature extraction; handwritten character recognition; histograms; oriented gradient features; recognition rates; Accuracy; Character recognition; Feature extraction; Handwriting recognition; Neural networks; Testing; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
IT Convergence and Security (ICITCS), 2013 International Conference on
Conference_Location :
Macao
Type :
conf
DOI :
10.1109/ICITCS.2013.6717840
Filename :
6717840
Link To Document :
بازگشت