We propose a method to generate figure-ground segmentation by incorporating shape priors into the graph-cuts algorithm. Given an image, we first obtain a linear representation of an image and then apply directional chamfer matching to generate class-independent, nonparametric shape priors, which provide shape clues for the graph-cuts algorithm. We then enforce shape priors in a graph-cuts energy function to produce object segmentation. In contrast to previous segmentation methods, the proposed method shares shape knowledge for different semantic classes and does not require class-specific model training. Therefore, the approach obtains high-quality segmentation for objects. We experimentally validate that the proposed method outperforms previous approaches using the challenging PASCAL VOC 2010/2012 and Berkeley (BSD300) segmentation datasets.
"Figure-ground segmentation based on class-independent shape priors," Journal of Electronic Imaging 27(1), 013018 (14 February 2018). https://doi.org/10.1117/1.JEI.27.1.013018
. Submission: Received: 12 October 2017; Accepted: 16 January 2018
Received: 12 October 2017; Accepted: 16 January 2018; Published: 14 February 2018