Information Theoretic Mean Shift Algorithm
- 1 September 2006
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2007 IEEE Workshop on Machine Learning for Signal Processing
- p. 155-160
- https://doi.org/10.1109/mlsp.2006.275540
Abstract
In this paper we introduce a new cost function called information theoretic mean shift algorithm to capture the "predominant structure" in the data. We formulate this problem with a cost function which minimizes the entropy of the data subject to the constraint that the Cauchy-Schwartz distance between the new and the original dataset is fixed to some constant value. We show that Gaussian mean shift and the Gaussian blurring mean shift are special cases of this generalized algorithm giving a whole new perspective to the idea of mean shift. Further this algorithm can also be used to capture the principal curve of the data making it ubiquitous for manifold learning.Keywords
This publication has 6 references indexed in Scilit:
- Real-time tracking of non-rigid objects using mean shiftPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Mean shift: a robust approach toward feature space analysisIeee Transactions On Pattern Analysis and Machine Intelligence, 2002
- Mode-finding for mixtures of Gaussian distributionsIeee Transactions On Pattern Analysis and Machine Intelligence, 2000
- Mean shift, mode seeking, and clusteringIeee Transactions On Pattern Analysis and Machine Intelligence, 1995
- Principal CurvesJournal of the American Statistical Association, 1989
- The estimation of the gradient of a density function, with applications in pattern recognitionIEEE Transactions on Information Theory, 1975