Open AccessSUPERPIXEL CUT FOR FIGURE-GROUND IMAGE SEGMENTATION
Author(s) -
Michael Ying Yang,
Bodo Rosenhahn
Publication year - 2016
Publication title -
isprs annals of the photogrammetry, remote sensing and spatial information sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.356
H-Index - 38
eISSN - 2194-9042
pISSN - 2196-6346
DOI - 10.5194/isprsannals-iii-3-387-2016
Subject(s) - segmentation , cut , artificial intelligence , computer science , figure–ground , ground truth , pixel , benchmark (surveying) , pattern recognition (psychology) , image segmentation , segmentation based object categorization , parametric statistics , graph , scale space segmentation , similarity (geometry) , prior probability , image (mathematics) , computer vision , mathematics , theoretical computer science , bayesian probability , statistics , geodesy , neuroscience , perception , biology , geography
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