Far East Journal of Experimental and Theoretical Artificial Intelligence
Volume 1, Issue 1, Pages 61 - 69
(February 2008)
|
|
PERFORMANCE ANALYSIS OF VECTOR QUANTIZER USING MODIFIED GENERALIZED LLOYD ALGORITHM
V. S. Jayanthi (India), S. Ashwin (India) and A. Shanmugam (India)
|
Abstract:
In this paper, we propose a new Vector Quantization method that generates codebook using Generalized Lloyd Algorithm. Our algorithm known as MGLA is derived from Generalized Lloyd Algorithm to overcome empty cell problem. Huffman coding of the indices generated by the encoder is used in the proposed algorithm. Our tests on several training and test images demonstrate that the proposed scheme can produce the reconstructed images of good quality in terms of Peak Signal to Noise Ratio. A gain of 0.2dB to 1.9dB in the PSNR has been obtained through MGLA in our tests, by adding only a few iteration steps. |
| Keywords and phrases: vector quantization, generalized Lloyd algorithm, empty cell problem, Huffman coding, peak signal to noise ratio. |
| Communicated by K. W. Chau |
| Number of Downloads: 163 | Number of Views: 435 |
|
