An object recognition procedure using artificial neutral network is proposed in this paper. This algorithm will recognize objects in the images which are invariant to rotation, translation and scaling of objects. The Sobel operators are proposed to detect the boundary of the object. A Fourier descriptor pattern classifier is able to classify object without regard to rotation, translation and scale variation. Fourier descriptors of boundary image generate Feature vectors by truncation the high frequency components. A back-propagation neural network is proposed to recognize the object based on these Feature vectors.
PDF References Citation
How to cite this article
I.M. Qureshi and A. Jalil, 2002. Object Recognition Using ANN with Backpropogation Algorithm. Journal of Applied Sciences, 2: 281-287.
- Khotanzad, A. and J.H. Lu, 1990. Classification of invariant image representations using a neural network. IEEE Trans. Acoust. Speech Signal Process., 38: 1028-1038.
- Kim, H. and K. Nam, 1995. Object recognition of one-DOF tools by a back-propagation neural net. IEEE Trans. Neural Networks, 6: 484-487.
- Shridhara, M. and A. Badreldina, 1984. High accuracy character recognition algorithm using fourier and topological descriptors. Pattern Recognition, 17: 515-524.
- Hadie, R.C. and C.G. Boncelet, 1995. Gradient-based edge detection using non-linear edge enhancing prefilters. IEEE Trans. Image Process., 4: 1572-1577.