Image Registration with Regularized Neural Network
In this paper, we propose a new method to improve the image registration accuracy in feedforward neural networks (FNN) based scheme. In the proposed method, Bayesian regularization is applied to improve the generalization capability of the FNN. The features extracted from the image sets by kernel independent component analysis (KICA) technique are input vectors of regularized FNN. The outputs of the neural network are those translation, rotation and scaling parameters with respect to reference and observed image sets. Comparative experiments are performed between FNN with regularization and without regularization under various conditions. The results show that the proposed method is much improved not only at accuracy but also remarkably at robust to noise.
KeywordsDiscrete Cosine Transform Image Registration Feedforward Neural Network Registration Accuracy Noisy Condition
Unable to display preview. Download preview PDF.
- 1.Elhanany, I., Sheinfeld, M., Beckl, A., et al.: Robust Image Registration Based on Feedforward Neural Networks. In: IEEE International Conference on System, Man and Cybernetics, vol. 2, pp. 1507–1511 (2000)Google Scholar
- 2.Wu, J., Xie, J.: Zernike Moment-based Image Registration Scheme Utilizing Feedforward Neural Networks. The 5th World Congress on Intelligent Control and Automation 5, 4046–4048 (2004)Google Scholar
- 4.Xu, A.B., Jin, X., Guo, P., Bie, R.F.: KICA Feature Extraction in Application to FNN based Image Registration. In: The 2006 International Joint Conference on Neural Networks (to appear)Google Scholar
- 5.Guo, P.: Studies of Model Selection and Regularization for Generalization in Neural Networks with Applications. PhD Thesis, the Chinese University of Hong Kong (2001)Google Scholar
- 6.Liu, Q.S., Cheng, J., Lu, H., Ma, S.: Modeling Face Appearance with Nonlinear Independent Component Analysis. In: Sixth IEEE International Conference on Automatic Face and Gesture Recognition (FGR 2004), vol. 2, pp. 761–766 (2004)Google Scholar
- 7.Cheng, J., Liu, Q.S., Lu, H.: Texture Classification Using Kernel Independent Component Analysis. In: Proceedings of the 17th Int. Conf. on Pattern Recognition, vol. 1, pp. 620–623 (2004)Google Scholar
- 11.Hagan, M.T., Menhaj, M.: Training Feedforward Networks with Marquardt Algorithm. IEEE Trans. Neural Networks 1(1), 113–118 (1994)Google Scholar
- 12.Foresee, F.D., Hagan, M.T.: Gauss-Newton approximation to Bayesian regularization. In: Proceedings of the 1997 International Joint Conference on Neural Networks, pp. 1930–1935 (1997)Google Scholar
- 13.Doan, C.D., Liong, S.Y.: Generalization for Multilayer Neural Network: Bayesian Regularization or Early Stopping. In: Proceedings of Asia Pacific Association of Hydrology and Water Resources 2nd Conference (2004)Google Scholar
- 14.Guo, P., Lyu, M.R., Chen, C.L.P.: Regularization Parameter Estimation for Feedforward Neural Networks. IEEE Trans. Neural Networks 33(1), 35–44 (2003)Google Scholar