! BBM 413 ! Today Fundamentals of ! • Introduction Image Processing – About the class – Organization of this course • What is image processing? – What does it mean, to see? Erkut Erdem ! – Vision as a computational problem Dept. of Computer Engineering ! – Sample image processing problems and applications Hacettepe University ! Introduction Today About this course • This course is an advanced level undergraduate course • Introduction about the fundamentals of image processing. – About the class – Organization of this course • Requirements – Programming skills (C/C++, Matlab) • What is image processing? – Good math background (Calculus, Linear Algebra, Statistical Methods) – What does it mean, to see? – Little or no prior knowledge of image processing techniques – Vision as a computational problem – Sample image processing problems and applications • BBM 415 Introduction to Programming Practicum – The students will gain hand-on experience via a set of programming assignments.
! ! ! ! ! About this course (cont’d.) BBM 413-415 Team • Goals of the course: Instructor ) TA ) – to provide an introduction to students who wish to specialize in Erkut&ERDEM&& Aysun&KOCAK& interrelated disciplines like image processing, computer vision erkut@cs.hace1epe.edu.tr&& aysunkocak@cs.hace1epe.edu.tr& and computational photography Office:&114& Office:&Vision&Lab& • Skills to develop: – a foundational understanding and knowledge of concepts that underlie image processing • What is image processing? ! Office)hours:) to&be&announced!& – What does image processing deal with? – Computational analysis of low and mid-level vision Communication Textbooks and Reference Material • Computer Vision: Algorithms and Applications, Richard Szeliski, ! • The course webpage will be updated regularly throughout the Springer, 2010 semester with lecture notes, programming and reading • Digital Image Processing, R. C. Gonzalez, R. E. Woods, ! assignments and important deadlines. 3rd Edition, Prentice Hall, 2008 ! http://web.cs.hacettepe.edu.tr/~erkut/bbm413.f15 • Lecture notes and handouts • Papers and journal articles
Getting Help Course work and grading • Reading assignments (12%) • Office hours – Reading research papers and preparing their summaries – See webpage for the schedule • Quizzes (16%) • BBM 415 Image Processing Practicum – Pop-up quizzes during class – Course related recitations, practice with example codes, etc. • Midterm exam (32%) – Closed book and notes • Communication – In class on November 19 th – Announcements and course related discussions through • Final exam (40%) https://piazza.com/hacettepe.edu.tr/fall2015/bbm413 – Closed book and notes – To be scheduled by Registrar Course Overview BBM 415 Image Processing Practicum – Introduction (0.5 week) • Programming assignments (PAs) – What is image processing? (0.5 week) – Five programming assignments throughout the semester. – Image formation and the digital camera (1 week) – Each assignment has a well-defined goal such as solving a specific – Color perception and color spaces (1 week) problem. – You must work alone or a group of two on all assignments stated – Point operations (1 week) unless otherwise. – Spatial filtering (1 week) – Frequency Domain Techniques (2 weeks) • Important Dates (Tentative) Midterm&exam& – Image pyramids and wavelets (1 week) – PA 1: October 8 th – Gradients, edges, contours (1 week) – PA 2: October 22 nd – PA 3: November 12 th – Image segmentation (2 weeks) – PA 4: November 26 th – Image smoothing (1 week ) – PA 5: December 10 th
Policies Today • Work groups • Introduction – You must work alone or a group of two on all assignments stated – About the class unless otherwise – Organization of this course • Submission • What is image processing? – Assignments due at 23:59 on Friday evenings – Electronic submissions (no exceptions!) – What does it mean, to see? – Vision as a computational problem • Lateness penalties – Sample image processing problems – Get penalized 10% per day – No late submission later than 3 days after due date What does it mean, to see? Signal � Processing • “The plain man’s answer (and Aristotle’s, too) would be, to know Applied � Comp. � what is where by looking. In other words, vision is the process of Math Photography discovering from images what is present in the world, and where it is.” David Marr, Vision, 1982 Image&& Filtering Processing& • Our brain is able to use ! Computer � Statistics an image as an input, ! Vision and interpret it ! in terms of objects and ! scene structures. Machine � Graphics Learning P.&Milanfar& Credit: � Jason �
What does Salvador Dali’s Study for the Why does vision appear easy to Dream Sequence in Spellbound (1945) ! humans? say about our visual perception? • Our brains are specialized to do vision. We see a two dimensional image • Nearly half of the cortex in a human brain is devoted to doing But, we perceive depth information vision (cf. motor control ~20-30%, language ~10-20%) • “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” ! Steven Pinker, How the Mind Works, 1997 light reflected ! on the retina • Gestalt Theory ! (Laws of Visual ! Perception), ! converging lines shadows of the eye Max Wertheimer, 1912 Figures: Steven Pinker, How the Mind Works, 1997 Why does vision appear easy to Computer Vision humans? • “Vision is a process that produces from images of ! the external world a description that is useful to the viewer and not cluttered with irrelevant information” ~David Marr • The goal of Computer Vision: ! To develop artificial machine vision systems that make inferences related to the scene being viewed through the images acquired with digital cameras. Things that are easy for us are difficult for computers and viceversa ~ Marvin Minsky h1p://xkcd.com/1425/&
Origins of computer vision L. G. Roberts, Machine Perception of Three Dimensional Solids, Ph.D. thesis, MIT Department of Electrical Engineering, 1963. Slide credit: S. Lazebnik Vision: a very difficult computational Reading Assignment #1 problem, at several levels of understanding • D. Marr (1982). Vision: A Computational Investigation • Vision as an information processing task [David Marr, 1982] into the Human Representation and Processing of • Three levels of understanding: Visual Information. Chapter 1. 1. Computational theory • Due on 15 th of October. – What is computed? Why it is computed? • Submit a brief 1-2 pages summary ! 2. Representation and Algorithm (in English) electronically. – How it is computed? • Use LaTeX to prepare your reports ! – Input, Output, Transformation in pdf file format. 3. Physical Realization – Hardware
Visual Modules and the Information Flow Visual Modules and the Information Flow • Visual perception as a data-driven, bottom-up process ! • Vision modules can be categorized into three groups ! (traditional view since D. Marr) according to their functionality: • Unidirectional information flow – Low-level vision: filtering out irrelevant image data – Mid-level vision: grouping pixels or boundary fragments together • Simple low-level cues >> Complex abstract perceptual units – 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
