Title :
A new initialization technique for generalized Lloyd iteration
Author :
Katsavounidis, Ioannis ; Jay Kuo, C.-C. ; Zhang, Zhen
Author_Institution :
Signal & Image Process. Inst., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
The generalized Lloyd algorithm plays an important role in the design of vector quantizers (VQ) and in feature clustering for pattern recognition. In the VQ context, this algorithm provides a procedure to iteratively improve a codebook and results in a local minimum that minimizes the average distortion function. We propose an efficient method to obtain a good initial codebook that can accelerate the convergence of the generalized Lloyd algorithm and achieve a better local minimum as well.<>
Keywords :
convergence of numerical methods; image coding; iterative methods; pattern recognition; vector quantisation; VQ; average distortion function; codebook; convergence; feature clustering; generalized Lloyd algorithm; generalized Lloyd iteration; image sequences; initialization technique; local minimum; pattern recognition; vector quantizers; Acceleration; Algorithm design and analysis; Convergence; Distortion measurement; Image coding; Iterative algorithms; Partitioning algorithms; Pattern recognition; Product codes; Signal processing algorithms;
Journal_Title :
Signal Processing Letters, IEEE
