作者: Diego Reforgiato Recupero , Sebastiano Battiato , Alfredo Pulvirenti
DOI:
关键词:
摘要: This paper describes a new method for analysis/synthesis of textures using non-parametric multi-resolution approach able to reproduce efficiently the generative stochastic process wide class real texture images. is realized through data structure Antipole Tree and suitable research strategy outperform both classical linear full-search heuristic TSVQ (Tree Structure Vector Quantization) acceleration used in previous related works. Experimental results performed on an exhaustive set [VisTex] show effectiveness proposed approach.