RuiZhen Zhao

  • Citations Per Year
Learn More
Wavelet threshold denoising is a powerful method for suppressing noise in signals and images. However, this method often uses a coordinate-wise processing scheme, which ignores the structural properties in the wavelet coefficients. We propose a new wavelet denoising method using sparse representation which is a powerful mathematical tool recently developed.(More)
Abstract-Compressed Sensing (CS), a new area of signal processing, seeks to reconstruct sparse or compressible signal from a small number of measurements. Mostly, random matrix is used as measurement matrix, such as Gaussian, Bernoulli and Fourier matrices. However, those matrices are difficult to implement in hardware, so deterministic matrices are(More)
Wavelet threshold denoising is a powerful method for suppressing noise in signals and images. However, this method uses a coordinate-wise processing scheme, which ignores the structural properties in the wavelet coefficients. We propose a new denoising method using sparse representation which is a powerful mathematical tool developed only recently. Instead(More)
Traditional VLAD method only uses the SITF feature. Since the SITF feature represents the local gradient information, thus VLAD representation based on SITF feature of image has low discriminative power. To address the problem, we present a simple and effective method that fuse the VLAD vectors based on local gradient and color information. Also, in order(More)
Based on the wavelet shrinkage denoising theory proposed by D.L. Donoho, a new thresholding function is presented in this paper, which is rather similar to hard thresholding one. However it has infinite-order continuous derivative. Compared to soft thresholding function, it can reserve better image details due to its "hard" characteristic. Moreover, the new(More)
A new image denoising algorithm based on contourlet transform is presented in this paper. The new approach takes the correlations of inter-scale contourlet coefficients into account in the process of shrinkage, and assumes that the noise-free contourlet coefficients are correlated to their parent coefficients which locate at a different scale. By computing(More)
Gradient Pursuit (GP) algorithm is one kind of the Greedy Algorithms for signal reconstruction. It is a practical method as a result of less computational requirements and better performance for signal reconstruction. GP algorithm is based on the steepest descent method of optimization theory. It uses the steepest descent step-size for the iterative(More)
In this paper, we propose a robust collaborative tracking algorithm based on interest points detection and template matching in sparse representation framework. In the proposed tracker, the target dictionary and the candidate dictionary are constructed with the patches around interest points of the previous frame and the current frame, respectively. The(More)
  • 1