" Instructor and Course Schedule " BIL 717 ! Image Processing ! • Dr. Erkut ERDEM ! Feb. 19, 2014 ! • erkut@cs.hacettepe.edu.tr ! • Office: 114 ! • Tel: 297 7500 / 149 ! Erkut Erdem " Hacettepe University " • Lectures: Wednesday, 09:00-11:45 ! Dept. of Computer Engineering ! • Office Hour: By appointment. ! Introduction ! About BIL717 " Communication " • This course provides a comprehensive overview of • The course webpage will be updated regularly fundamental topics in image processing for graduate throughout the semester with lecture notes, students. ! programming and reading assignments and " important deadlines. • The goal of this course is to provide a deeper http://web.cs.hacettepe.edu.tr/~erkut/bil717.s14 ! understanding of the state-of-the-art methods in image processing literature and to study their connections. ! • All other communications will be carried out • The course makes the students gain knowledge and skills through Piazza. Please enroll it by following the link in key topics and provides them the ability to employ https://piazza.com/hacettepe.edu.tr/spring2014/bil717 ! them in their advanced-level studies. !
Prerequisites " Reading Material " • Programming skills " • Lecture notes and handouts ! (C/C++, Matlab) ! • Papers and journal articles ! • Good math background " (Calculus, Linear Algebra, Statistical Methods) ! • A prior, introductory-level course in image processing is recommended. ! Reference Books " Related Conferences " • Mathematical Problems in Image Processing: • International Conference on Scale Space and Variational Partial Differential Equations and the Calculus Methods in Computer Vision (SSVM) ! of Variations, G. Aubert and P . Kornprobst, " • Energy Minimization Methods in Computer Vision and Pattern 2nd Edition, Springer-Verlag, 2006 ! Recognition (EMMCVPR) ! • IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ! • Image Processing And Analysis: Variational, • Advances in Neural Information Processing Systems (NIPS) ! PDE, Wavelet, And Stochastic Methods, " T. Chan and J. Shen, Society for Industrial and • IEEE International Conference on Computer Vision (ICCV) ! Applied Mathematics, 2005 ! • European Conference on Computer Vision (ECCV) ! • IEEE International Conference on Pattern Recognition (ICPR) ! • IEEE International Conference on Image Processing (ICIP) ! • Markov Random Fields For Vision And Image • British Machine Vision Conference (BMVC) ! Processing, Edited by A. Blake, P . Kohli and " C. Rother, MIT Press, 2011 !
Related Journals " Grading Policy " • IEEE Transactions on Pattern Analysis and Machine • 20% Quizzes ! Intelligence (IEEE TPAMI) ! • 20% Programming Assignments ! • IEEE Transactions on Image Processing (IEEE TIP) ! • 20% Paper presentations/Class participation ! • Journal of Mathematical Imaging and Vision (JMIV) ! • 40% Project and final term paper ! • International Journal of Computer Vision (IJCV) ! • Computer Vision and Image Understanding (CVIU) ! • Image and Vision Computing (IMAVIS) ! • Pattern Recognition (PR) ! Programming Assignments " Paper presentations and Quizzes " • The students will be required to present at least one • There will be three assignments related to the topics research paper either of their choice or from the covered in the class. ! suggested reading list. ! • Each assignment will involve implementing an • These papers should be read by every student as the algorithm, carrying out a set of experiments to quizzes about the presented papers will be given on evaluate it, and writing up a report on the the weeks of the presentations. ! experimental results. ! • The schedule for the presentations will be finalized • All assignments have to be done individually, unless on 5th of March. ! stated otherwise. !
Project " Project – Important Dates " • The aim of the project is to give the students some • Project proposals: 12 th of March ! experience on conducting research. ! • Project progress reports: 16 th of April ! • Students should work individually. ! • Project presentations: will be announced! ! • Project final reports: 4 th of June ! • This project may involve ! – design of a novel approach and its experimental analysis, ! – an extension to a recent study (published after 2008) of non-trivial complexity and its experimental analysis, ! – an in-depth empirical evaluation and analysis of two " • Late submissions will be penalized! ! or more related methods not covered in the class. ! Tentative Outline " Tentative Outline " • (1 week) Overview of Image Processing ! • (1 week) Graphical Models ! • (1 week) Linear Filtering, Edge Detection, ! • (1 week) Semantic Segmentation ! • (1 week) Nonlinear Filtering ! • (1 week) Visual Saliency ! • (1 week) Variational Segmentation Models ! • (1 week) What we’ve done, Where we’re going ! • (2 weeks) Modern Image Filtering ! • (1 week) Image deblurring ! • (1 week) Clustering-based Segmentation Models ! • (1 week) Sparse Coding !
Signal � Processing Applied � Comp. � Math Photography Image Processing " Image## Filtering Processing# Computer � Statistics Vision Machine � Graphics Learning P.#Milanfar# Credit: � Jason � What does Salvador Dali’s Study for the What does it mean, to see? " Dream Sequence in Spellbound (1945) ! say about our visual perception? " • “The plain man’s answer (and Aristotle’s, too) would be, to know We see a two dimensional image " what is where by looking. In other words, vision is the process of discovering from images what is present in the world, and where it But, we perceive depth information " is.” David Marr, Vision, 1982 ! ! • Our brain is able to use " an image as an input, " light reflected ! and interpret it " on the retina " in terms of objects and " scene structures. ! converging lines " shadows of the eye "
Why does vision appear easy to Computer Vision " humans? " • Our brains are specialized to do vision. ! • “Vision is a process that produces from images of " the external world a description that is useful to the • Nearly half of the cortex in a human brain is devoted to doing vision (cf. motor control ~20-30%, language ~10-20%) ! viewer and not cluttered with irrelevant information” ~David Marr ! • “Vision has evolved to convert the ill-posed problems into solvable ones by adding premises: assumptions about how the world we evolved in is, on average, put together” " • The goal of Computer Vision: " Steven Pinker, How the Mind Works, 1997 ! To develop artificial machine vision systems that make inferences related to the scene being viewed • Gestalt Theory " through the images acquired with digital cameras. ! (Laws of Visual " Perception), " Max Wertheimer, 1912 ! Figures: Steven Pinker, How the Mind Works, 1997 " Marr’s observation: Studying Visual Modules and the Information Flow " vision at 3 levels " • Vision as an information processing task [David Marr, 1982] ! • Three levels of understanding: ! 1. Computational theory ! – What is computed? Why it is computed? ! 2. Representation and Algorithm ! – How it is computed? ! • Visual perception as a data-driven, bottom-up process " – Input, Output, Transformation ! (traditional view since D. Marr) ! 3. Physical Realization ! • Unidirectional information flow ! – Hardware ! • Simple low-level cues >> ! Complex abstract perceptual units !
Visual Modules and the Information Flow " Visual Modules and the Information Flow " Subject(ma+er(of(this(course( • Vision modules can be categorized into three groups " • Vision modules can be categorized into three groups " • Vision modules can be categorized into three groups " according to their functionality: ! according to their functionality: ! according to their functionality: ! – Low-level vision: filtering out irrelevant image data ! – Low-level vision: filtering out irrelevant image data ! – Low-level vision: filtering out irrelevant image data " – Mid-level vision: grouping pixels or boundary fragments together ! – Mid-level vision: grouping pixels or boundary fragments – Mid-level vision: grouping pixels or boundary fragments together ! together " – High-level vision: complex cognitive processes ! – High-level vision: complex cognitive processes ! – High-level vision: complex cognitive processes ! Image Formation " Fundamentals of Image Processing " Image Formation ! Digital " Reality ! (Software - Hardware) ! Image ! Image Processing ! Three Dimensional " Two Dimensional " World ! Image Space ! • What is a digital image, how it is formed? ! Another " Information ! • How images are represented in computers? ! • What is measured in an image location? ! Digital Image ! • Why we process images? ! viewpoint ! • How we process images? ! – brightness ! illumination conditions ! << local geometry ! – color ! local material properties ! Figures: Francis Crick, The Astonishing Hypothesis, 1995 "
Recommend
More recommend