Co-Sparse Textural Similarity for Interactive Segmentation^*

Claudia Nieuwenhuis¹, Simon Hawe², Martin Kleinsteuber², and Daniel Cremers²

¹UC Berkeley, USA

²Technische Universität München, Germany

Abstract. We propose an algorithm for segmenting natural images based on texture and color information, which leverages the co-sparse analysis model for image segmentation. As a key ingredient of this method, we introduce a novel textural similarity measure, which builds upon the co-sparse representation of image patches. We propose a statistical MAP inference approach to merge textural similarity with information about color and location. Combined with recently developed convex multilabel optimization methods this leads to an efficient algorithm for interactive segmentation, which is easily parallelized on graphics hardware. The provided approach outperforms state-of-the-art interactive segmentation methods on the Graz Benchmark.

^*This work was supported by the German Academic Exchange Service (DAAD) and the ERC Starting Grant ’Convex Vision’.

LNCS 8694, p. 285 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer International Publishing Switzerland 2014