Nonparametric Joint Shape and Feature Priors for Image Segmentation

Abstract

In many image segmentation problems involving limited and low-quality data, employing statistical prior information about the shapes of the objects to be segmented can significantly improve the segmentation result. However, defining probability densities in the space of shapes is an open and challenging problem, especially if the object to be segmented comes from a shape density involving multiple modes (classes). Existing techniques in the literature estimate the underlying shape distribution by extending Parzen density estimator to the space of shapes. In these methods, the evolving curve may converge to a shape from a wrong mode of the posterior density when the observed intensities provide very little information about the object boundaries. In such scenarios, employing both shape- and class-dependent discriminative feature priors can aid the segmentation process. Such features may involve, e.g., intensity-based, textural, or geometric information about the objects to be segmented. In this paper, we propose a segmentation algorithm that uses nonparametric joint shape and feature priors constructed by Parzen density estimation. We incorporate the learned joint shape and feature prior distribution into a maximum a posteriori estimation framework for segmentation. The resulting optimization problem is solved using active contours. We present experimental results on a variety of synthetic and real data sets from several fields involving multimodal shape densities. Experimental results demonstrate the potential of the proposed method.

A Dynamic-Shape-Prior Guided Snake Model With Application in Visually Tracking Dense Cell Populations

“…In fact, none of the aforementioned snake models are specifically targeted at the self-crossing problem. By using algorithms such as [4], [6], [8] with circular or elliptic priors, or snake models with more specific shape priors [18]- [20], the snake self-crossing problem can be side-stepped. However, these methods generally have strong shape priors that exclude them from tracking an object with flexible deformation, or multiple objects with a variety of shapes and sizes, such as dense cell populations.…”

Region-Based Nonparametric Model for Interactive Image Segmentation

“…Some algorithms consider appearance model parameters as extra variables in the optimizations which makes the problem NP-hard [15]. Nonparametric models have proved powerful in segmentation problems because they do not require any basic model to describe the appearance of the image [19]. Therefore, they can accept any unknown data distribution.…”

Semantic Image Segmentation with Deep Convolutional Neural Networks and Quick Shift

“…Quick shift [19] is a mode-seeking based clustering algorithm, which has a relatively good boundary adherence. It first initializes the segmentation using medoid shift [20], then moves each data point in the feature space to the nearest neighbor that increases the Parzen density estimation [21]. Simple Linear Iterative Clustering (SLIC) [22] adopts a k-means clustering approach with a distance metric that depends on both spatial and intensity differences to efficiently generate superpixels.…”