This paper presents a novel technique for image restoration based on nonlinear interpolative vector quantization (NLIVQ). The algorithm performs nonlinear restoration of diffraction-limited images concurrently with quantization. It is trained on image pairs consisting of an original image and its diffraction-limited counterpart. The discrete cosine transform is used in the codebook design proce...

Discrete cosine transform (DCT) is a widely compression technique for converting an image into elementary frequency components. However, level of quality and compression is desired, scalar multiples of the JPEG standard quantization may be used. In this paper, DCT method was applied to compress image under various level of quality. Different quantization matrices of DCT’s coefficients are used ...

AbshzctThe statistical analysis of coefficient quantization n o k io digital filters is a useful technique because it gives theoretid and practical results without resorting to lengthy case-by-case trials. The realization problem of digital filters can thus be simplified a n a l f i d y by statistical approaches. Furthermore, statistical approaches have an advantage of supplying unified tools f...

This paper presents an MPEG-2 compatible adaptive quantization algorithm that leads to the optimal encoding of I-frames in the sense of maximizing PSNR. It integrates three key features into a single Lagrangian optimization model: adaptive quantization including quantizer-change overhead consideration, coefficient thresholding, and a new coefficient amplitude reduction technique. Our results sh...

In this paper we consider a feature extraction approach for recognition of handwritten electrical symbols. The symbols are represented as a sequence of points. We apply a feature extraction technique to extract the most important features and then feed them for recognition to a Neural Network. We utilize a Learning Vector Quantization (LVQ) network and show its capability to recognize the symbo...

In vector quantization the number of vectors used to construct the codebook is always an undefined problem, there is always a compromise between the number of vectors and the quantity of information lost during the compression. In this text we present a minimum of Entropy principle that gives solution to this compromise and represents an Entropy point of view of signal compression in general. A...

This paper presents a hybrid technique for compression using Wavelet and Vector Quantization (VQ). Wavelet is a technique for representing the image into various degrees of resolution. The input image of size 256 *256 pixels is divided into 4 sub-bands named LL, HL, LH, HH by applying Discrete Wavelet Transform. Vector Quantization is then applied for the lower sub band (LL). The size of lower ...

-Mean-normalised Vector Quantization (M-NVQ) has been demonstrated to be the preferred technique for lossless compression of hyperspectral data. In this paper, a jointly optimised spatial M-NVQ/spectral DCT technique is shown to produce compression ratios significantly better than those obtained by the optimised spatial M-NVQ technique alone.

Motivated by the problem of effectively executing clustering algorithms on very large data sets, we address a model for large scale distributed clustering methods. To this end, we briefly recall some standards on the quantization problem and some results on the almost sure convergence of the competitive learning vector quantization (CLVQ) procedure. A general model for linear distributed asynch...

In this work we study the topic of high-resolution adaptive sampling of a given deterministic signal and establish a clear connection to classic analyses of high-rate quantization. More specifically, we formulate solutions to the task of optimal high-resolution sampling of one-dimensional signals, which are shown as the counterparts of well-known results for high-rate scalar quantization. Our r...