Subband coding has proven to be a powerful technique for medium bandwidth source encoding of speech. Recently, some promising results have been reported on the extension of this concept to the source coding of images. In this paper, a new two-dimensional subband coding technique is presented which is also applied to images. A frequency band decomposition of the image is carried out by means of ...

A colour quantization technique is presented which maps 24-bit colour images to 8bit colour, using Self-Organizing Neural Networks. The quantized image is superior to that produced by existing methods, and has useful continuity properties.

The object of this dissertation is to investigate rate-distortion optimization and to evaluate the prospects of adaptive vector quantization for digital video compression. Rate-distortion optimization aims to improve compression performance using discrete optimization algorithms. We first describe and classify algorithms that have been developed in the literature to date. One algorithms is exte...

A thorough description of trellis-coded quantization as a nearly-optimal source coding system is presented. Trelliscoded quantizers couple traditional quantization techniques with finite state machines to build effective high dimensional vector quantizers. In a trellis-coded quantizer, each transition of the related finite state machine is labeled, by means of a convolutional code, with one of ...

Efficient image compression technique especially for medical applications is presented. Dyadic wavelet decomposition by use of Antonini and Villasenor bank filters is followed by adaptive space-frequency quantization and zerotree-based entropy coding of wavelet coefficients. Threshold selection and uniform quantization is made on a base of spatial variance estimate built on the lowest frequency...

We consider sensor-based distributed source localization applications, where sensors transmit quantized data to a fusion node, which then produces an estimate of the source location. For this application, the goal is to minimize the amount of information that the sensor nodes have to exchange in order to attain a certain source localization accuracy. We propose a distributed encoding algorithm ...

Digital holography is an imaging technique that enables recovery of topographic 3D information about an object under investigation. In digital holography, an interference pattern is recorded on a digital camera. Therefore, quantization of the recorded hologram is an integral part of the imaging process. We study the influence of quantization error in the recorded holograms on the fidelity of bo...

In this paper, we workout a detailed mathematical analysis for a new learning algorithm termed Cascade Error ProJection (CEP) and a general learning frame work. This frame work can be used to obtain the cascade correlation learning algorithm by choosing a particular set of parameters. Furthermore, CEP learning algorithm is operated only on one layer, whereas the other set of weights can be calc...

In this article, we present a distributed variant of an adaptive stochastic gradient method for training deep neural networks in the parameter-server model. To reduce communication cost among workers and server, incorporate two types quantization schemes, i.e., weight quantization, into proposed Adam. addition, to bias introduced by operations, propose error-feedback technique compensate quanti...

We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making more efficient by running them using low-bit integer arithmetic therefore commonly adopted in industry. Recent work has shown that floating-point have been verified to be can become vulnerable adversarial attacks after quantization, certification represen...