It started withimageprocessing inthesixties. Back then, it took ages to digitize a Landsat image and then process it with a mainframe computer. P- cessing was inspired on theachievements of signal processing and was still very much oriented towards programming. In the seventies, image analysis spun off combining image measurement with statistical pattern recognition. Slowly, computational methods detached themselves from the sensor and the goal to become more generally applicable. In theeighties, model-drivencomputervision originated when arti?cial- telligence and geometric modelling came together with image analysis com- nents. The emphasis was on precise analysiswithlittleorno interaction, still very much an art evaluated by visual appeal. The main bottleneck was in the amount of data using an average of 5 to 50 pictures to illustrate the point. At the beginning of the nineties, vision became available to many with the advent of suf?ciently fast PCs. The Internet revealed the interest of the g- eral public im images, eventually introducingcontent-basedimageretrieval. Combining independent (informal) archives, as the web is, urges for inter- tive evaluation of approximate results andhence weak algorithms and their combination in weak classi?ers.

"The goal of this book is to address the use of several important machine learning techniques into computer vision applications. An innovative combination of computer vision and machine learning techniques has the promise of advancing the field of computer vision, which contributes to better understanding of complex real-world applications. The effective usage of machine learning technology in real-world computer vision problems requires understanding the domain of application, abstraction of a learning problem from a given computer vision task, and the selection of appropriate representations for the learnable (input) and learned (internal) entities of the system.In this book, we address all these important aspects from a new perspective: that the key element in the current computer revolution is the use of machine learning to capture the variations in visual appearance, rather than having the designer of the model accomplish this. As a bonus, models learned from large datasets are likely to be more robust and more realistic than the brittle all-design models. TOC:Foreword.- Preface.- 1. Introduction.- 2. Theory: Probabilistic Classifiers.- 3. Theory: Generalization Bounds.- 4. Theory: Semi-Supervised Learning.- 5. Algorithm: Maximum Likelihood Minimum Entropy HMM.- 6. Algorithm: Margin Distribution Optimization.- 7. Algorithm: Learning The Structure Of Bayesian Network Classifiers.- 8. Application: Office Activity Recognition.- 9. Application: Multimodal Event Detection.- 10. Application: Facial Expression Recognition.- 11. Application: Bayesian Network Classifiers For Face Detection.- References.- Index."

Theory: Probabilistic Classifiers.- Theory: Generalization Bounds.- Theory: Semi-Supervised Learning.- Algorithm: Maximum Likelihood Minimum Entropy HMM.- Algorithm: Margin Distribution Optimization.- Algorithm: Learning the Structure of Bayesian Network Classifiers.- Application: Office Activity Recognition.- Application: Multimodal Event Detection.- Application: Facial Expression Recognition.- Application: Bayesian Network Classifiers for Face Detection.