Author: P.V. Kalinin, A.А. Sirota (Voronezh State University, Voronezh, Russia)
COMPUTER VISION AND IMAGE UNDERSTANDING Vol. 130, pp. 80-86 (JAN 2015)
DOI: https://doi.org/10.1016/j.cviu.2014.09.007
Abstract
The problem of image segmentation is formulated in terms of recursive partitioning of segments into subsegments by optimizing the proposed objective function via graph cuts. Our approach uses a special normalization of the objective function, which enables the production of a hierarchy of regular superpixels that adhere to image boundaries. To enforce compactness and visual homogeneity of segments a regularization strategy is proposed. Experiments on the Berkeley dataset show that the proposed algorithm is comparable in its performance to the state-of-the-art superpixel methods.
Keywords
Segmentation; Superpixels; Graph cuts
Full text