6. Introducing spatial information into the merge
Spatial information is fundamental to image processing. Its introduction into fusion methods is crucial, and often requires specific developments to adapt methods from other fields. One of the most frequent objectives is to guarantee that the decision is spatially coherent. In multisource classification, for example, we try to avoid isolated points in a different class.
6.1 At the modeling level
The introduction of spatial information at the modeling level is more or less implicit, depending on the level of representation used. If we reason at pixel level, the information contained in a pixel does not contain any spatial information, and this must therefore be introduced explicitly. The spatial context considered is usually the local neighborhood of each point....
The Ultimate Scientific and Technical Reference
This article is included in
Signal processing and its applications
This offer includes:
Knowledge Base
Updated and enriched with articles validated by our scientific committees
Services
A set of exclusive tools to complement the resources
Practical Path
Operational and didactic, to guarantee the acquisition of transversal skills
Doc & Quiz
Interactive articles with quizzes, for constructive reading
Introducing spatial information into the merge
Conclusion
Bibliography
The Ultimate Scientific and Technical Reference
