Image vector quantization using an annealed Hopfield neural network

Jzau-Sheng Lin

doi:10.1117/1.602073

1 April 1999 Image vector quantization using an annealed Hopfield neural network

Jzau-Sheng Lin

Optical Engineering, Vol. 38, Issue 4, (April 1999). https://doi.org/10.1117/1.602073

We show an unsupervised parallel approach called the annealed Hopfield neural network (AHNN) with a new cooling schedule for vector quantization in image compression. The main purpose is to combine the characteristics of neural networks and annealing strategy so that online learning and hardware implementation for vector quantization are feasible. The idea is to cast a clustering problem as a minimization problem where the criterion for the optimum vector quantization is chosen as the minimization of the average distortion between training vectors and codevectors. Although the simulated annealing method can yield the global minimum, it is very time consuming with asymptotical iterations. In addition, to resolve the optimal problem using Hopfield or simulated annealing neural networks, the designer must determine the weighting factors to combine the penalty terms. The quality of the final result is very sensitive to these weighting factors, and feasible values for them are difficult to find. Using the AHNN for vector quantization eliminates the need for finding weighting factors in the energy function, which is formulated and based on a basic concept of the ‘‘within-class scatter matrix’’ principle. In addition, the rate of convergence is much faster than that of simulated annealing. The experimental results show that better and more promising solutions can be obtained using the AHNN than the LBG in image vector quantization. The convergence rate with various cooling schedules is discussed.

Citation Download Citation

Jzau-Sheng Lin "Image vector quantization using an annealed Hopfield neural network," Optical Engineering 38(4), (1 April 1999). https://doi.org/10.1117/1.602073

Published: 1 April 1999

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available