Earth Mover Distance on superpixels
Authors:
- 1 September 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 4597-4600
Abstract
Earth Mover Distance (EMD) is a popular distance to compute distances between Probability Density Functions (PDFs). It has been successfully applied in a wide selection of problems of image processing. This success comes from two reasons, a physical one, since it computes a physical cost to transport an element of mass between two images or two histograms, and a statistical one, since it is a cross-bin metric (as opposed to a bin-wise metric). In computer vision, these features are useful since small variation of illuminance can shift the histogram. However, histograms are not a sufficient statistic to discriminate images since they ignore all geometric correlations. In addition, transport also called flow of an histogram loose the information of geometric flow to warp one image on to an other. This paper proposes a new construction of EMD between images. This construction approximates the EMD between two images, by computing a pixel-wise transport at the complexity cost of computing an EMD between 1-D Histograms and preserves the geometrical and topological structure of the image. This construction simply relies on a segmentation of the image (also called superpixelization of the image). Results on matching on images shows the stability of the method even when the superpixelizations are highly inconsistent across images.Keywords
This publication has 8 references indexed in Scilit:
- Fast and robust Earth Mover's Distances2009
- Video object segmentation by tracking regions2009
- Coresets and Approximate Clustering for Bregman Divergences2009
- Histogram Based Segmentation Using Wasserstein Distances2007
- Optimal Mass Transport for Registration and WarpingInternational Journal of Computer Vision, 2004
- Statistical region mergingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- The Earth Mover's Distance as a Metric for Image RetrievalInternational Journal of Computer Vision, 2000
- Region correspondence for image matching via EMD flow2000