A hardware design of a massive-parallel, modular NN-based vector quantizer for real-time video coding

Authors:
Agustin Ramirez-Agundis;Rafael Gadea-Girones;Ricardo Colom-Palero
Affiliations:
Department of Electronic Engineering, Instituto Tecnológico de Celaya, Av. Tecnologico s/n, 38010, Celaya, Gto., Mexico;Department of Electronic Engineering, Universidad Politecnica de Valencia, Camino de Vera s/n, 46020, Valencia, Spain;Department of Electronic Engineering, Universidad Politecnica de Valencia, Camino de Vera s/n, 46020, Valencia, Spain
Venue:
Microprocessors & Microsystems
Year:
2008

Citing 12
Cited 3

Vector quantization and signal compression

Vector quantization and signal compression
Speech recognition chip for monosyllables

Proceedings of the 2001 Asia and South Pacific Design Automation Conference
Intelligent Internet Search Applications Based on VLSI Associative Processors

SAINT '02 Proceedings of the 2002 Symposium on Applications and the Internet
Associative memory with fully parallel nearest-Manhattan-distance search for low-power real-time single-chip applications

Proceedings of the 2004 Asia and South Pacific Design Automation Conference
Hardware Accelerated Data Analysis

PARELEC '04 Proceedings of the international conference on Parallel Computing in Electrical Engineering
2005 Special issue: FPGA implementation of self organizing map with digital phase locked loops

Neural Networks - 2005 Special issue: IJCNN 2005
FPGA implementation of full-search vector quantization based on partial distance search

Microprocessors & Microsystems
VLSI architecture for motion vector quantization

IEEE Transactions on Consumer Electronics
Digital implementation of hierarchical vector quantization

IEEE Transactions on Neural Networks
IP core implementation of a self-organizing neural network

IEEE Transactions on Neural Networks
A massively parallel architecture for self-organizing feature maps

IEEE Transactions on Neural Networks
An image representation algorithm compatible with neural-associative-processor-based hardware recognition systems

IEEE Transactions on Neural Networks

Utilization of a fast MSE calculation approach to improve the image quality and accelerate the operation of a hardware K-SOM quantizer

Microprocessors & Microsystems
Techniques for power reduction in an SIMD implementation of the VQ/SOM algorithms

Neurocomputing
A reconfigurable neuroprocessor for self-organizing feature maps

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This report describes the design of a modular, massive-parallel, neural-network (NN)-based vector quantizer for real-time video coding. The NN is a self-organizing map (SOM) that works only in the training phase for codebook generation, only at the recall phase for real-time image coding, or in both phases for adaptive applications. The neural net can be learned using batch or adaptive training and is controlled by an inside circuit, finite-state machine-based hard controller. The SOM is described in VHDL and implemented on electrically (FPGA) and mask (standard-cell) programmable devices.