High-Order Models in Semantic Image Segmentation reviews recent developments in optimization-based methods for image segmentation, presenting several geometric and mathematical models that underlie a broad class of recent segmentation techniques. Focusing on impactful algorithms in the computer vision community in the last 10 years, the book includes sections on graph-theoretic and continuous relaxation techniques, which can compute globally optimal solutions for many problems. The book provides a practical and accessible introduction to these state-of -the-art segmentation techniques that is ideal for academics, industry researchers, and graduate students in computer vision, machine learning and medical imaging.
1. General introduction - p. vii 2. Chapter 1. Markov random fields - p. 1 3. Chapter 2. Graph cuts - p. 17 4. Chapter 3. Mean-field inference - p. 31 5. Chapter 4. Regularized model fitting - p. 45 6. Chapter 5. Regularized mutual information - p. 59 7. Chapter 6. Examples of high-order functionals - p. 69 8. Chapter 7. Pseudo-bound optimization - p. 85 9. Chapter 8. Trust-region optimization - p. 111 10. Chapter 9. Random field losses for deep networks - p. 123 11. Chapter 10. Constrained deep networks - p. 145 12. Index - p. 161
High-Order Models in Semantic Image Segmentation reviews recent developments in optimization-based methods for image segmentation, presenting several geometric and mathematical models that underlie a broad class of recent segmentation techniques. Focusing on impactful algorithms in the computer vision community in the last 10 years, the book includes sections on graph-theoretic and continuous relaxation techniques, which can compute globally optimal solutions for many problems. The book provides a practical and accessible introduction to these state-of -the-art segmentation techniques that is ideal for academics, industry researchers, and graduate students in computer vision, machine learning and medical imaging.
1. General introduction - p. vii 2. Chapter 1. Markov random fields - p. 1 3. Chapter 2. Graph cuts - p. 17 4. Chapter 3. Mean-field inference - p. 31 5. Chapter 4. Regularized model fitting - p. 45 6. Chapter 5. Regularized mutual information - p. 59 7. Chapter 6. Examples of high-order functionals - p. 69 8. Chapter 7. Pseudo-bound optimization - p. 85 9. Chapter 8. Trust-region optimization - p. 111 10. Chapter 9. Random field losses for deep networks - p. 123 11. Chapter 10. Constrained deep networks - p. 145 12. Index - p. 161
