The K-Space segmentation tool set
McGuinness, Kevin and O'Connor, Noel E. (2008) The K-Space segmentation tool set. In: SAMT 2008 - 3rd International Conference on Semantic and Multimedia Technologies, 3-5 December 2008, Koblenz, Germany.
Full text available as:
In this paper we describe two applications, created as part of the K-Space Network of Excellence, designed to allow researchers to use and experiment with state-of-the-art methods for spatial segmentation of images and video sequences. The first of these tools is an _Interactive Segmentation Tool_, developed to allow accurate human-guided segmentation of semantic objects from images using different segmentation algorithms. The tool is particularly useful for generating ground-truth segmentations, extracting objects for further processing, and as a general image processing application.The second tool we developed is designed for fully automatic spatial region segmentation of image and video. The tool is web-based; usage only requires a browser.
Both the automatic and interactive segmentation tools have been made available online; we anticipate they will be a valuable resource for other researchers.
Archive Staff Only: edit this record