Image Segmentation Using Weak Shape Priors

TL;DR

This paper presents a novel image segmentation method that uses weak shape priors to improve segmentation accuracy under challenging conditions like occlusion and noise, requiring less training data than traditional methods.

Contribution

The paper introduces a weak shape prior approach for segmentation that minimally influences the process while effectively regularizing it, reducing training data needs compared to PCA-based methods.

Findings

Effective segmentation under occlusion and noise

Requires smaller training sets than PCA-based methods

Provides regularization without dominating data forces

Abstract

The problem of image segmentation is known to become particularly challenging in the case of partial occlusion of the object(s) of interest, background clutter, and the presence of strong noise. To overcome this problem, the present paper introduces a novel approach segmentation through the use of "weak" shape priors. Specifically, in the proposed method, an segmenting active contour is constrained to converge to a configuration at which its geometric parameters attain their empirical probability densities closely matching the corresponding model densities that are learned based on training samples. It is shown through numerical experiments that the proposed shape modeling can be regarded as "weak" in the sense that it minimally influences the segmentation, which is allowed to be dominated by data-related forces. On the other hand, the priors provide sufficient constraints to regularize the convergence of segmentation, while requiring substantially smaller training sets to yield less biased results as compared to the case of PCA-based regularization methods. The main advantages of the proposed technique over some existing alternatives is demonstrated in a series of experiments.