Universiti Teknologi Malaysia Institutional Repository

Adaptive neural network classifier for extracted invariants of handwritten digits

Keng, L. H. and Shamsuddin, Siti Mariyam (2004) Adaptive neural network classifier for extracted invariants of handwritten digits. Journal of Information and Communication Technology (JICT), 3 (1). pp. 1-17. ISSN 2180-3862

Full text not available from this repository.

Official URL: http://jict.uum.edu.my/index.php/previous-issues/1...


We propose an adaptive activation function of neural network classifier for isolated handwritten digits that undergo basic transformations. The utilized network is a backpropagation network with sigmoid and arctangent activation functions. The performance of network with both activation functions is compared. The results show that the network applying an adaptive activation function between layers converged much faster compared to non-adaptive activation functions with 50% iterations reduction. In this study, we also present experimental results of feature extraction between Zernike and d-geometric for better feature representations. Results show that Zernike features are better at representing isolated handwritten digits compared to d-geometric features with an accuracy up to 87%.

Item Type:Article
Uncontrolled Keywords:handwritten digit, Zernike moments, adaptive activation function
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System
ID Code:28194
Deposited By: Yanti Mohd Shah
Deposited On:18 Sep 2012 06:11
Last Modified:30 Nov 2018 07:07

Repository Staff Only: item control page