Equilibrium and dissipative structures role on images
Pattern Recognition Letters
Efficient Facial Feature Detection Using Entropy and SVM
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing
Robust Facial Feature Location on Gray Intensity Face
PSIVT '09 Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology
The spiral method applied to the study of the microcalcifications in mammograms
ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
| Hi-index | 0.00 |
Feature points for image correspondence are often selectedaccording to subjective criteria (e.g. edge density,nostrils). In this paper, we present a general, non-subjectivecriterion for selecting informative feature points, based onthe correspondence model itself. We describe the approachwithin the framework of the Bayesian Markov random field(MRF) model, where the degree of feature point informationis encoded by the entropy of the likelihood term. We proposethat feature selection according to minimum entropy-of-likelihood (EOL) is less likely to lead to correspondence ambiguity, thus improving the optimization process in termsof speed and quality of solution. Experimental resultsdemonstrate the criterion's ability to select optimal featurespoints in a wide variety of image contexts (e.g. objects,faces). Comparison with the automatic Kanade-Lucas-Tomasifeature selection criterion shows correspondence tobe significantly faster with feature points selected accordingto minimum EOL in difficult correspondence problems.