Improving Pattern Recognition Rate by Gaussian Hopfield Neural Network

Abstract:

Article Preview

English letters cannot be recognized by the Hopfield Neural Network if it contains noise over 50%. This paper proposes a new method to improve recognition rate of the Hopfield Neural Network. To advance it, we add the Gaussian distribution feature to the Hopfield Neural Network. The Gaussian filter was added to eliminate noise and improve Hopfield Neural Network’s recognition rate. We use English letters from ‘A’ to ‘Z’ as training data. The noises from 0% to 100% were generated randomly for testing data. Initially, we use the Gaussian filter to eliminate noise and then to recognize test pattern by Hopfield Neural Network. The results are we found that if letters contain noise between 50% and 53% will become reverse phenomenon or unable recognition [6]. In this paper, we propose to uses multiple filters to improve recognition rate when letters contain noise between 50% and 53%.

Info:

Periodical:

Advanced Materials Research (Volumes 189-193)

Edited by:

Zhengyi Jiang, Shanqing Li, Jianmin Zeng, Xiaoping Liao and Daoguo Yang

Pages:

2042-2045

Citation:

S. J. Chuang et al., "Improving Pattern Recognition Rate by Gaussian Hopfield Neural Network", Advanced Materials Research, Vols. 189-193, pp. 2042-2045, 2011

Online since:

February 2011

Export:

Price:

$41.00

[1] Chu-Cheng Chen, Nonlinear System Identification Using Gaussian-Hopfield Neural Networks, Fu Jen Catholic University, (2004).

[2] Si-yan Lin, The Hopfield Neural Networks for Automatic Semiconductor Wafer Defect Inspection, National Yunlin University of Science and Technology, (2006).

[3] Kuen-Ming Lan, Hopfield Neural Networks Approaches for Solving Bilevel Linear Programming Problems, National Tsing Hua University, (2008).

[4] Yeh, I-Cheng, Neural Network Model of Application and Implementation, Scholars Books, (2003).

[5] Shang-Li Wu, Ming-Te Lin, C-digital image processing Windows/X-Window corresponding", Seiki Inoue, Nobuyuki Yagi, Masaki Hayashi, Eisuke Nakasu, Kouji Mitani, Makoto Okui, "CGengo de Manabu Jissen Gazou Shori Windows/X-Window Taiou, Vol. 5, No. 5, pp.83-86, Chuan Hwa Books, in chinese, (2010).

[6] Chien-Chih Kao, Chien-Ming Huang, Shang-Jen Chuang, Fang-Tsung Liu, Modified Hopfield Neural Network and its recognition application, Proceedings of 2010 National Symposium on System Science and Engineering, Taipei, (2010).

DOI: https://doi.org/10.4028/www.scientific.net/amr.189-193.2042