Karhunen-Loeve (KL) transform is optimal for many signal detection, communication and filtering applications. An explicit solution of the KL integral equation for a practical case when the covariance function of a stationary process is exponentially oscillating is proposed.

A new algorithm for computing precise estimates of the motion vectors of moving objects in a sequence of images is presented. The proposed method is a fusion of block-matching motion estimation and global optimization technique. To avoid some contradictions between global optimization techniques and piece-wise smooth values of sought motion vectors, a hidden segmentation model is utilized. Computer simulation and experimental results demonstrate a good performance of the method in terms of dynamic motion analysis.

A new method for computing precise estimates of the motion vectors of moving objects in a sequence of images is proposed. The proposed method is based on dynamic programming matching applied along chain-coded binary contours of images. This significantly reduces the computational complexity of the correspondence matching applied to the 2-D optimization problem. Computer simulation and experimental results demonstrate a good performance of the method in terms of dynamic motion analysis.

A novel effective method for detection and removal impulse noise in highly corrupted color images is proposed. This detection-estimation method consists of two steps. Outliers are first detected using spatial relations between the color components. Then the detected noise pixels are replaced with the output of the vector median filter over a local spatially connected area excluding the outliers. Simulation results in a test color image show a superior performance of the proposed filtering algorithm comparing to the conventional vector median filter. The comparisons are made using a mean square error and a mean absolute error criteria.

This paper presents a restoration method using several degraded observed images obtained through a technique known as microscanning. It is shown that microscanning provides sufficient spatial information for image restoration with minimal information about the original image and without knowing the interference function that causes degradation.

Fast algorithms for computing the running type-I discrete sine transform (DST-I) and type-III discrete sine transform (DST-III) are proposed. The algorithms are based on a recursive relationship between three subsequent local discrete sine spectra. The computational complexity of the algorithms is compared with that of fast DST-I and DST-III algorithms. Fast inverse algorithms for signal processing in the running discrete sine transform domains are also proposed.