DocumentCode :
1583806
Title :
Number Image Recognition Based on Neural Network Ensemble
Author :
Wang, Jian ; Yang, Jingfeng ; Li, Shaofa ; Dai, Qiufang ; Xie, Jiaxing
Author_Institution :
South China Agric. Univ., Guangzhou
Volume :
1
fYear :
2007
Firstpage :
237
Lastpage :
240
Abstract :
Handwritten number is hard to recognize due to there existing much noise, and the shape, size, thickness and position of each number may be different. This paper investigates the recognition of number image of fixed pixels based on the neural network ensemble. Firstly, the Bagging technique is used to obtain the training samples, secondly, the discrete Hopfield neural network is employed to remove the noise among the samples and associate the samples, then 20 single three layers feed forward neural networks are built up to construct neural network ensemble to obtain the recognition results through voting. The research shows that the fault-tolerant and generalization ability of the neural network ensemble is superior to the single best model for visual number recognition.
Keywords :
Hopfield neural nets; fault tolerant computing; generalisation (artificial intelligence); handwritten character recognition; image recognition; bagging technique; discrete Hopfield neural network; fault tolerance; generalization ability; handwritten number; neural network ensemble; number image recognition; visual number recognition; Bagging; Feedforward neural networks; Feeds; Handwriting recognition; Hopfield neural networks; Image recognition; Neural networks; Noise shaping; Pixel; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Natural Computation, 2007. ICNC 2007. Third International Conference on
Conference_Location :
Haikou
Print_ISBN :
978-0-7695-2875-5
Type :
conf
DOI :
10.1109/ICNC.2007.506
Filename :
4344189
Link To Document :
بازگشت