Spectral Segmentation via Midlevel Cues Integrating Geodesic and Intensity
- 20 March 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 43 (6) , 2170-2178
Abstract
Image segmentation still remains as a challenge in image processing and pattern recognition when involving complex natural scenes. In this paper, we present a new affinity model for spectral segmentation based on midlevel cues. In contrast to most existing methods that operate directly on low-level cues, we first oversegment the image into superpixel images and then integrate the geodesic line edge and intensity cue to form the similarity matrix W so that it more accurately describes the similarity between data. The geodesic line edge could avoid strong boundary and represent the true boundary between two superpixels while the mean red green blue vector could describe the intensity of superpixels better. As far as we know, this is a totally new kind of affinity model to represent superpixels. Based on this model, we use the spectral clustering in the superpixel level and then achieve the image segmentation in the pixel level. The experimental results show that the proposed method performs steadily and well on various natural images. The evaluation comparisons also prove that our method achieves comparable accuracy and significantly performs better than most state-of-the-art algorithms.Keywords
This publication has 35 references indexed in Scilit:
- Adaptive image segmentation for region-based object retrieval using generalized Hough transformPattern Recognition, 2010
- Unsupervised segmentation of natural images via lossy data compressionComputer Vision and Image Understanding, 2008
- O(N) implementation of the fast marching algorithmJournal of Computational Physics, 2006
- Learning to detect natural image boundaries using local brightness, color, and texture cuesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Mean shift: a robust approach toward feature space analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Color image segmentation: advances and prospectsPattern Recognition, 2001
- Normalized cuts and image segmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- New geodosic distance transforms for gray-scale imagesPattern Recognition Letters, 1996
- Fronts propagating with curvature-dependent speed: Algorithms based on Hamilton-Jacobi formulationsJournal of Computational Physics, 1988
- Distance transformations in digital imagesComputer Vision, Graphics, and Image Processing, 1986