Hardware Architectures for Vector Quantization in Very Low Bit-Rate Image Coding

The paper describes a board-based hardware implementation of a neural algorithm performing vector quantization for very low bit-rate video compression. The Neural Gas model has been chosen for its remarkable properties in terms of both consistency (quality of the quantization process) and easy implementation. The Neuro-board interfaces to a PC through a standard ISA bus. The system architecture is composed of a 70ns RAM bank, an FPGA-based control logic and mathematical coprocessor, and a DSP device for numerical computations. The board supports both training (codevectors adjustment) and run-time operation. The main advantages of the implemented solution lie in its simplicity and easy control for HW tests and SW development.

Published

1996-10

Content type

Original Research

DOI

10.5594/M001241

ISBN

978-1-61482-947-8