Fusion in Image Processing - Information Fusion in Signal and Image Processing - page 44

measurement, the reliability of an image for certain classes or structures, etc. From
a processing perspective, this hybrid aspect arises, for example, when a proposition
establishing that the recognition of a structure only depends on the local context leads
to an adequate modeling in a Markovian framework. Symbolic representations are also
used as a priori knowledge, or contextual or generic knowledge to guide the numeri-
cal process. They also serve as a structural medium, for example, when fusing images
and maps [MOI 95].
3.6. Bibliography
[MAI 91] M AÎTRE H., “Utilisation de l'imagerie aérienne et satellitaire pour l'aménagement
du territoire”, Cours du 8ème Congrès AFCET de Lyon , Tutorial 4, 1991.
[MAN 94] M ANGIN J.F., F ROUIN V. , B LOCH I., L OPEZ -K RAHE J., B ENDRIEM B., “Fast
Nonsupervised 3D Registration of PET and MR Images of the Brain”, Journal of Cerebral
Blood Flow and Metabolism , vol. 14, p. 749-762, 1994.
[MOI 95] M OISSINAC H., M AÎTRE H., B LOCH I., “Graph Based Urban Scene Analysis Using
Symbolic Data”, SPIE Integrating Photogrammetric Techniques with Scene Analysis and
Machine Vision II , vol. 2486, Orlando, Florida, p. 93-104, April 1995.
[SIM 89] S IMON J.C., From Pixels to Features , V-X, North Holland, Amsterdam, 1989.
[ZIT 03] Z ITOVA B., F LUSSER J., “Image registration methods: a survey”, Image and Vision
Computing , vol. 21, p. 977-1000, 2003.