Feature points for image correspondence are often selected according to subjective criteria (e.g. edge density, nostrils). In this paper, we present a general, nonsubjective criterion for selecting informative feature points, based on the correspondence model itself. We describe the approach within the framework of the Bayesian Markov random field (MRF) model, where the degree of feature point information is encoded by the entropy of the likelihood term. We propose that feature selection according to minimum entropy-of-likelihood (EOL) is less likely to lead to correspondence ambiguity, thus improving the optimization process in terms of speed and quality of solution. Experimental results demonstrate the criterion's ability to select optimal features points in a wide variety of image contexts (e.g. objects, faces). Comparison with the automatic Kanade-Lucas-Tomasi feature selection criterion shows correspondence to be significantly faster with feature points selected according to minimum EOL in difficult correspondence problems.
Entropy-of-likelihood feature selection for image correspondence
Proceedings Ninth IEEE International Conference on Computer Vision ; 1041-1047 vol.2
2003-01-01
767849 byte
Conference paper
Electronic Resource
English
Entropy-of-likelihood Feature Selection for Image Correspondence
British Library Conference Proceedings | 2003
|Joint feature distributions for image correspondence
IEEE | 2001
|Joint Feature Distributions for Image Correspondence
British Library Conference Proceedings | 2001
|Global image feature correspondence under a multi-image network
British Library Online Contents | 1999
|CORRESPONDENCE - Maximum Likelihood Registration for Multiple Dissimilar Sensors
Online Contents | 2003
|