List of Figures. List of Tables. Preface. Acknowledgments. 1: Overview. 1. Introduction. 2. Image Interpretation. 3. Literature Review. 4. Approaches. 5. Layout of the Monograph. 2: Background. 1. Introduction. 2. Markov Random Field Models. 3. Multiresolution. 3: MRF Framework For Image Interpretation. 1. MRF on a Graph. 4. Bayesian Net Approach To Interpretation. 1. Introduction. 2. MRF model leading to Bayesian Network Formulation. 3. Bayesian Networks and Probabilistic Inference. 4. Probability Updating in Bayesian Networks. 5. Bayesian Networks for Gibbsian Image Interpretation. 6. Experimental Results. 7. Conclusions. 5: Joint Segmentation And Image Interpretation. 1. Introduction. 2. Image Interpretation using Integration. 3. The Joint Segmentation and Image Interpretation Scheme. 4. Experimental Results. 5. Conclusions. 6: Conclusions. Appendices: Appendix A. Bayesian Reconstruction. Appendix B. Proof of Hammersley-Clifford Theorem. Appendix C. Simulated Annealing Algorithm - Selecting Toin practise. Appendix D. Custom Made Pyramids. Appendix E. Proof of Theorem 4.6. Appendix F. k-means clustering. Appendix G. Features used in Image Interpretation. Appendix H. Knowledge Acquisition. Appendix I. HMM for Clique Functions. References. Index.

Bayesian Approach to Image Interpretation will interest anyone working in image interpretation. It is complete in itself and includes background material. This makes it useful for a novice as well as for an expert. It reviews some of the existing probabilistic methods for image interpretation and presents some new results. Additionally, there is extensive bibliography covering references in varied areas.
For a researcher in this field, the material on synergistic integration of segmentation and interpretation modules and the Bayesian approach to image interpretation will be beneficial.
For a practicing engineer, the procedure for generating knowledge base, selecting initial temperature for the simulated annealing algorithm, and some implementation issues will be valuable.
New ideas introduced in the book include:

• New approach to image interpretation using synergism between the segmentation and the interpretation modules.
• A new segmentation algorithm based on multiresolution analysis.
• Novel use of the Bayesian networks (causal networks) for image interpretation.
• Emphasis on making the interpretation approach less dependent on the knowledge base and hence more reliable by modeling the knowledge base in a probabilistic framework.