A combined active contours method for segmentation using localization and multiresolution

Abstract

Image segmentation is a fundamental step in many image processing applications. To achieve high-quality segmentations active contours are commonly used. However, state of art strategies are not able to provide successful results in all the conditions. Additionally, the strategies that get the best overall results are computationally expensive and need to manually set some parameters, which decreases their usability.Here, we propose a novel active contours-based segmentation method that, through the combination of boundary-based and regionbased energies and a multiresolution analysis, provides very highquality results while significantly increasing both the computational efficiency and the usability of previous approaches.

Fast localised active contour for inhomogeneous image segmentation

“…Yanez et al [16] showed that using an adaptive radius drastically decreases the computational efficiency while only slightly increasing the quality of the results. For this reason, we use a fixed localisation radius (i.e.…”

Tool for Semiautomatic Labeling of Moving Objects in Video Sequences: TSLAB

“…Active contours are a very powerful tool for detecting contours, especially if we have an initial approximation of the contour that we want to reach. Therefore, to facilitate the labeling task, we have included in TSLAB the active contour-based segmentation strategy proposed in [ 33 ].…”