Contextual clustering for image segmentation

The unsupervised Pappas adaptive clustering (PAC) algorithm is a well-known Bayesian and contextual procedure for pixel labeling. It applies only to p iecewise constant or slowly varying intensity images that may be corrupted by an additive white Gaussian noise field independent of the scene. interes ting features of PAC include multiresolution implementation and adaptive es timation of spectral parameters in an iterative framework. Unfortunately, P AC removes from the scene any genuine but small region whatever the user-de fined smoothing parameter may be. As a consequence, PAC's application domai n is limited to providing sketches or caricatures of the original image. We present a modified PAC (MPAC) scheme centered on a novel class-conditional model, which employs local and global spectral estimates simultaneously. R esults show that MPAC is superior to contextual PAC and stochastic expectat ion-maximization as well as to noncontextual (pixel-wise) clustering algori thms in detecting image details, (C) 2000 Society of Photo-Optical Instrume ntation Engineers. [S0091-3286(00)02704-5].