Outline • Syllabus • Introduction • Computational Paradigms for Vision – Appearance-based computer vision – Physics-based computer vision Textbooks • Textbooks – I will use chapters from different books and papers from the literature – Most of the books were used in other classes – The book “2D Object Detection and Recognition” is available May 29, 2016 Computer Vision 2 The Goal of This Class • The focus of this class is not the formality – I will go through the basic concepts in the first few weeks – Then we will focus on important research topics one by one using one or few key papers • After discussing each of the key papers, we need to be crystal clear about the problems and the approaches so that we will understand whenever we see them again May 29, 2016 Computer Vision 3 Vision • Vision – The process of acquiring knowledge about the environmental objects and events by extracting information from the light they emit or reflect – Vision is a very complicated process, involving different processes such as memory – Vision is the most useful source for information as about 50% of the human brain is devoted to visual processing May 29, 2016 Computer Vision 4 Vision – cont. • Vision has been studied from many different perspectives – Computational vision • Emphasis on approaches that are biologically plausible – Computer vision • Emphasis on algorithms to solve particular problems – Statistical vision • Emphasis on developing and analyzing mathematical and statistical models May 29, 2016 Computer Vision 5 What is the Truth? • In the context of learning, what is the truth? – Statistical / mathematical frameworks or – Effective and efficient algorithms? May 29, 2016 Computer Vision 6 Transduction Inference A principle advocated by Vladimir Vapnik “If you are limited to a restricted amount of information, do not solve the particular problem you need by solving a more general problem” May 29, 2016 Computer Vision 7