Alignment by maximization of mutual information

作者: P. Viola , W.M. Wells

DOI: 10.1109/ICCV.1995.466930

关键词: Artificial intelligenceReal imageImage processingObject modelMaximizationComputer scienceComputer visionMutual informationRobustness (computer science)

摘要: A new information-theoretic approach is presented for finding the pose of an object in an image. The technique does not require information about the surface properties of the object, besides its shape, and is robust with respect to variations of illumination. In our derivation, few assumptions are made about the nature of the imaging process. As a result, the algorithms are quite general and can foreseeably be used in a wide variety of imaging situations. Experiments are presented that demonstrate the approach in registering …

参考文章(30)
William Mercer Wells, Statistical Object Recognition Massachusetts Institute of Technology. ,(1993) , 10.21236/ADA270887
R. Linsker, From basic network principles to neural architecture Proc. National Academy of Science, USA 83. ,vol. 7508, pp. 8779- 8783 ,(1986)
B. WIDROW, M. E. HOFF, Adaptive switching circuits Neurocomputing: foundations of research. pp. 123- 134 ,(1988) , 10.21236/AD0241531
Lennart Ljung, Torsten Söderström, Theory and Practice of Recursive Identification ,(1983)
J. P. Mellor, Realtime Camera Calibration for Enhanced Reality Visualization international conference on computer vision. pp. 471- 475 ,(1995) , 10.1007/978-3-540-49197-2_62
André Collignon, Dirk Vandermeulen, Paul Suetens, Guy Marchal, 3D Multi-Modality Medical Image Registration Using Feature Space Clustering international conference on computer vision. ,vol. 905, pp. 195- 204 ,(1995) , 10.1007/978-3-540-49197-2_22
Herbert Robbins, Sutton Monro, A Stochastic Approximation Method Annals of Mathematical Statistics. ,vol. 22, pp. 400- 407 ,(1951) , 10.1214/AOMS/1177729586