In this book, we develop the stochastic geometry framework for image analysis purposes.
New sensors currently provide very high resolution images. Civilian satellites have achieved resolutions of less than one meter, while microscopy is now in the micro-meters. At these resolutions, geometrical information is crucial for analyzing images. In addition, the stochastic framework has proved to be very efficient for analyzing lower resolution images. These models can be extended by considering the stochastic geometry framework.
The book reviews the different models, based on stochastic geometry, used to address image analysis problems. The authors consider the problems of modeling, optimization and parameter estimation. Practical examples are detailed. Numerous applications, covering remote sensing images, biological and medical imaging, are detailed. The two main frameworks considered in this book are the marked point process approach and random closed sets models.
1. Introduction, X. Descombes.
2. Marked Point Processes for Object Detection, X. Descombes.
3. Random Sets for Texture Analysis, C. Lantuéjoul and M. Schmitt.
4. Simulation and Optimization, F. Lafarge, X. Descombes, E. Zhizhina and R. Minlos.
5. Parametric Inference for Marked Point Processes in Image Analysis, R. Stoica, F. Chatelain and M. Sigelle.
6. How to Set Up a Point Process?, X. Descombes.
7. Population Counting, X. Descombes.
8. Structure Extraction, F. Lafarge and X. Descombes.
9. Shape Recognition, F. Lafarge and C. Mallet.
Xavier Descombes is currently research director at INRIA (French research institute dedicated to digital science and technology). His research interests include Markov random fields, stochastic geometry and stochastic modeling in image processing.