User-Friendly Interactive Image Segmentation Through Unified Combinatorial User Inputs

Abstract

One weakness in the existing interactive image segmentation algorithms is the lack of more intelligent ways to understand the intention of user inputs. In this paper, we advocate the use of multiple intuitive user inputs to better reflect a user's intention. In particular, we propose a constrained random walks algorithm that facilitates the use of three types of user inputs: 1) foreground and background seed input, 2) soft constraint input, and 3) hard constraint input, as well as their combinations. The foreground and background seed input allows a user to draw strokes to specify foreground and background seeds. The soft constraint input allows a user to draw strokes to indicate the region that the boundary should pass through. The hard constraint input allows a user to specify the pixels that the boundary must align with. Our proposed method supports all three types of user inputs in one coherent computational framework consisting of a constrained random walks and a local editing algorithm, which allows more precise contour refinement. Experimental results on two benchmark data sets show that the proposed framework is highly effective and can quickly and accurately segment a wide variety of natural images with ease.

Automatic atlas-guided constrained random Walker algorithm for 3D segmentation of muscles on water magnetic resonance images

“…The above system of equations can be extended by imposing additional constraints on the set of voxels located on the boundaries between different tissues (S H ) and the set of voxels located around these boundaries (S S ). The resulting constrained Random Walker algorithm computes the probability p crw i that vertex v i has label S F as [4]:…”

“…Vanishing the derivative of the above cost function with respect to p i yields the following system of equations that can be solved efficiently [4]:…”

“…In addition to the spatially varying regularization, our main contributions to the constrained Random Walker algorithm, in difference to the previous works [2], [4], are the ways of…”

“…This is due to the sensitivity of all RW-based algorithms to the number of labeled seeds [2]- [4], as the foreground seeds get reduced by having errors in the atlas-derived muscle probabilities.…”

“…However, this supervised segmentation approach demands user interaction to define labeled seeds for different classes and has difficulties in differentiating objects of similar intensities or textures. Moreover, its performance depends on the number and distribution of the defined seeds [2]- [4].…”