The K-Space segmentation tool set

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.

[1]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Raúl Rojas,et al.  SIOX: simple interactive object extraction in still images , 2005, Seventh IEEE International Symposium on Multimedia (ISM'05).

[3]  Yiannis Kompatsiaris,et al.  Knowledge-Assisted Image Analysis Based on Context and Spatial Optimization , 2006, Int. J. Semantic Web Inf. Syst..

[4]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[5]  Tomasz Adamek,et al.  Using contour information and segmentation for object registration, modeling and retrieval , 2006 .

[6]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.