Superpixels optimized by color and shape



Kurlin, V ORCID: 0000-0001-5328-5351 and Harvey, D
(2018) Superpixels optimized by color and shape. In: Energy Minimization Models in Computer Vision and Pattern Recognition, 2017-10-30 - 2017-11-1, Venice, Italy.

[img] Text
SOCS.pdf - Author Accepted Manuscript

Download (4MB)

Abstract

Image over-segmentation is formalized as the approximation problem when a large image is segmented into a small number of connected superpixels with best fitting colors. The approximation quality is measured by the energy whose main term is the sum of squared color deviations over all pixels and a regularizer encourages round shapes. The first novelty is the coarse initialization of a non-uniform superpixel mesh based on selecting most persistent edge segments. The second novelty is the scale-invariant regularizer based on the isoperimetric quotient. The third novelty is the improved coarse-to-fine optimization where local moves are organized according to their energy improvements. The algorithm beats the state-of-the-art on the objective reconstruction error and performs similarly to other superpixels on the benchmarks of BSD500. The only parameters are the number of superpixels and the shape coefficient for a trade-off between accuracy and shape of superpixels

Item Type: Conference or Workshop Item (Unspecified)
Depositing User: Symplectic Admin
Date Deposited: 02 Oct 2017 08:41
Last Modified: 19 Jan 2023 06:53
DOI: 10.1007/978-3-319-78199-0_20
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3009726