ABSTRACT
We present a novel probabilistic model for the hierarchal structure of an image and its regions. We call this model spatial random tree grammars (SRTGs). We develop algorithms for exact computation of likelihoods and MAP estimates and exact EM updates for model-parameter estimation. We collectively call these algorithms the center-surround algorithm. We use the center-surround algorithm to automatically estimate the ML parameters of SRTGs, classify images based on their likelihood and based on the MAP estimate of the associated hierarchal structure. We apply our method to the task of classifying natural images and demonstrate that the addition of hierarchal structure significantly improves upon the performance of a baseline model that lacks such structure.
Subject(s)
Algorithms , Artificial Intelligence , Image Enhancement/methods , Image Interpretation, Computer-Assisted/methods , Models, Statistical , Pattern Recognition, Automated/methods , Subtraction Technique , Computer Simulation , Reproducibility of Results , Sensitivity and SpecificityABSTRACT
We introduce a family of first-order multidimensional ordinary differential equations (ODEs) with discontinuous right-hand sides and demonstrate their applicability in image processing. An equation belonging to this family is an inverse diffusion everywhere except at local extrema, where some stabilization is introduced. For this reason, we call these equations "stabilized inverse diffusion equations" (SIDEs). Existence and uniqueness of solutions, as well as stability, are proven for SIDEs. A SIDE in one spatial dimension may be interpreted as a limiting case of a semi-discretized Perona-Malik equation. In an experiment, SIDE's are shown to suppress noise while sharpening edges present in the input signal. Their application to image segmentation is also demonstrated.
ABSTRACT
Techniques were developed for automated detection and characterization of dermatoscopic structures, including the pigment network and brown globules. These techniques incorporate algorithms for grayscale shape extraction based on differential geometry developed by Steger, a snake algorithm, and a modification of the region competition strategy of Zhu and Yuille. A novel approach was developed for global segmentation of pigmented lesions, based on stabilized inverse diffusion equations. Procedures for detection of air bubbles and hairs in dermatoscopic images are also reported.
