Image segmentation with superpixel-based covariance descriptors in low-rank representation
This work addresses image segmentation for computer vision applications, but it is incremental as it builds on existing superpixel and covariance descriptor methods.
The paper tackles image segmentation by enhancing superpixel covariance descriptors using Log-Euclidean distance with an RBF kernel and a low-rank representation extension, achieving competitive results on the Berkeley Segmentation Dataset.
This paper investigates the problem of image segmentation using superpixels. We propose two approaches to enhance the discriminative ability of the superpixel's covariance descriptors. In the first one, we employ the Log-Euclidean distance as the metric on the covariance manifolds, and then use the RBF kernel to measure the similarities between covariance descriptors. The second method is focused on extracting the subspace structure of the set of covariance descriptors by extending a low rank representation algorithm on to the covariance manifolds. Experiments are carried out with the Berkly Segmentation Dataset, and compared with the state-of-the-art segmentation algorithms, both methods are competitive.