Neural net classification of states in finite state vector quantization

Author

Zhigang Zhang, New Jersey Institute of Technology

Document Type

Thesis

Date of Award

9-30-1990

Degree Name

Master of Science in Electrical Engineering - (M.S.)

Department

Electrical and Computer Engineering

First Advisor

Constantine N. Manikopoulos

Second Advisor

Irving Y. Wang

Third Advisor

MengChu Zhou

Abstract

In this thesis, a new image coding technique based on Neural Network Finite State Vector Quantization(NNFSVQ) is presented. The new design takes advantage of the high interblock spatial correlation of pixels in typical grey-level images, in addition to intrablock correlation already exploited by vector quantization (VQ). Although many FSVQ require large memory space for the storage of the numerous state codebooks, the memory space requirement of NNFSVQ can be reduced by a very large factor (about 10²-10³) to manageable size without impairing image quality. Simulation experiments have shown that by using NNFSVQ the bit rate can be reduced from 0.5 to 0.2 bits/pixel at about 30dB peak SNR for the image LENA. The pictorial quality of the image remains very high. This compares well to similar performance levels resulting from the application of Kim's algorithm, a high performance FSVQ technique. By contrast, the memory requirement for NNFSVQ is reduced by a factor of 256.

Recommended Citation

Zhang, Zhigang, "Neural net classification of states in finite state vector quantization" (1990). Theses. 3025.
https://digitalcommons.njit.edu/theses/3025