Search

To produce realistic synthetic images, it is important to shade objects based on real illumination conditions of a scene. Estimating the direction of the light source of the scene is a key factor to achieve this. Properly estimating this source under noisy conditions is very challenging, and it is a subject of intense research. Computational intelligence techniques offer promising way of tackling this problem. This paper presents a novel neural network-based approach for recovering light source direction in relation to the viewpoint direction of a graphical image in noisy environments. The estimated light source direction can be used for the generation of 3D images from 2D ones. Experiments are performed using both synthetic and real images in noisy scenes. Four synthetic surfaces where generated with varying light source directions for a total of 12 images. Three real images were also used with varying degrees of noise. The experimental results show that the proposed approach is robust and provides a good level of accuracy. [ABSTRACT FROM AUTHOR]

In remote sensing image processing, image approximation, or obtaining a high-resolution image from a corresponding low-resolution image, is an ill-posed inverse problem. In this paper, the regularization method is used to convert the image approximation problem into a solvable variational problem. In regularization, the constraints on smoothness and discontinuity are considered, and the original ill-posed problem is thereby converted to a well-posed optimization problem. In order to solve the variational problem, a Hopfield-type dynamic neural network is developed. This neural network possesses two states that describe the discrepancy between a pixel and adjacent pixels, the intensity evolution of a pixel and two kinds of corresponding weights. Based on the experiment in this study with a Landsat TM image free of added noise and a noisy image, the proposed approach provides better results than other methods. The comparison shows the feasibility of the proposed approach. [ABSTRACT FROM AUTHOR]

Abstract: Modular neural network is a popular neural network model which has many successful applications. In this paper, a sequential Bayesian learning (SBL) is proposed for modular neural networks aiming at efficiently aggregating the outputs of members of the ensemble. The experimental results on eight benchmark problems have demonstrated that the proposed method can perform information aggregation efficiently in data modeling. [Copyright &y& Elsevier]