Abstract
Figure-ground image segmentation has been a challenging problem in computer vision. Apart from the difficulties in establishing an effective framework to divide the image pixels into meaningful groups, the notions of figure and ground often need to be properly defined by providing either user inputs or object models. In this paper, we propose a novel graph-based segmentation framework, called superpixel cut. The key idea is to formulate foreground segmentation as finding a subset of superpixels that partitions a graph over superpixels. The problem is formulated as Min-Cut. Therefore, we propose a novel cost function that simultaneously minimizes the inter-class similarity while maximizing the intra-class similarity. This cost function is optimized using parametric programming. After a small learning step, our approach is fully automatic and fully bottom-up, which requires no high-level knowledge such as shape priors and scene content. It recovers coherent components of images, providing a set of multiscale hypotheses for high-level reasoning. We evaluate our proposed framework by comparing it to other generic figure-ground segmentation approaches. Our method achieves improved performance on state-of-the-art benchmark databases.
Highlights
Despite a variety of segmentation techniques have been proposed, figure-ground image segmentation remains challenging for any single method to do segmentation successfully due to the diversity and ambiguity in an image
We propose a novel graph-based segmentation framework, called superpixel cut, which formulates foreground segmentation as finding a subset of superpixels that partitions a graph over superpixels
4.2.1 Qualitative results We provide a qualitative evaluation of our approach by testing it on images from the two datasets
Summary
Despite a variety of segmentation techniques have been proposed, figure-ground image segmentation remains challenging for any single method to do segmentation successfully due to the diversity and ambiguity in an image. In recent years an increasingly popular way to solve various image labeling problems like object segmentation, stereo and single view reconstruction is to formulate them using superpixels obtained from unsupervised segmentation algorithms (Li et al, 2004, Levinshtein et al, 2010, Brendel and Todorovic, 2010). They may belong to the same object or may have the same surface orientation. Our approach has the following two important characters, which distinguish our work from most of the others: First, it is fully automatic, efficient, and requires no user input; Second, it is fully bottom-up, which requires no high-level knowledge such as shape priors and scene content
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
