BIL 717 - Image Processing (Spring 2015)

Lectures: Wed 13:00-15:50@D5

René Magritte's painting (Empire of Light II), 1950 Paul Signac's painting (Place des Lices), 1893

Instructor: Erkut Erdem

erkut-at-cs-hacettepe.edu.tr
114
+90 312 297 7500, 149

Course Description

This course provides a comprehensive overview of fundamental topics in image processing for graduate students. The goal is to give a deeper understanding of the state-of-the-art methods in image processing literature and to study their connections. In this context, the course makes the students gain knowledge and skills in key topics and provides them the ability to employ them in their advanced-level studies.

Prerequisites

Good math (calculus, linear algebra, statistics) and programming skills. A prior, introductory-level course in image processing is recommended.

Schedule (Tentative)

Week Date Topic Notes
1 Feb 18 Overview of Image Processing Slides: (pdf, 4pp)
Reading: D. Marr, Vision, The Philosophy and the Approach, 1982
2 Feb 25 Linear Filtering, Edge Detection Slides: (pdf, 4pp)
Notes: pdf
Reading: A. P. Witkin, Scale-space filtering: A New Approach to Multi-Scale Description, In Proc. IJCAI, 1983
Reading: D. Marr and E. Hildreth, Theory of Edge Detection, Proc. R. Soc. Lond. B, 1980
3 Mar 4 Nonlinear Filtering PA1 out: (pdf, code)
Paper selections due: (final schedule)
Slides: (pdf, 4pp)
Notes: pdf
Reading: P. Perona and J. Malik, Scale-Space and Edge Detection Using Anisotropic Diffusion, IEEE Trans. Pattern Anal. Mach. Intell., 1990
Reading: L. Rudin et al., Nonlinear Total Variation Based Noise Removal Algorithms, Phys. D., 1992
4 Mar 11 Snakes, Variational Segmentation Models Project proposals due
Slides: (pdf, 4pp)
Notes: pdf
Reading: M. Kass et al., Snakes: Active contour models, Int. Journal Comp. Vis., 1988
Reading: T. Chan and L. Vese, Active contours without edges, IEEE Trans. Image Processing, 2001
Reading: E. Erdem and S. Tari, Mumford-Shah Regularizer with Contextual Feedback, J. Math. Imaging and Vision, 2009
5 Mar 18 Modern Image Filtering Slides: (pdf, 4pp)
Reading: C. Tomasi and R. Manduchi, Bilateral Filtering for Gray and Color Images , In Proc. ICCV, 1998
Reading: A. Buades et al., A non-local algorithm for image denoising, In Proc. CVPR, 2005
Reading: H. Takeda et al., Kernel Regression for Image Processing and Reconstruction, IEEE Trans. Image Processing, 2007
Paper presentation: J. Weickert, Coherence-Enhancing Diffusion of Colour Images, Image and Vision Computing, 1999
6 Mar 25 Modern Image Filtering (cont’d.) PA1 due­
Slides: (pdf, 4pp)
Reading: L. Karacan et al., Structure Preserving Image Smoothing via Region Covariances, ACM Trans. Graph., 2013
Reading: Q. Zhang et al., Rolling Guidance Filter, In Proc. ECCV, 2014
Paper presentation: Xu et al., Structure extraction from texture via relative total variation, ACM Trans. Graph., 2012
7 Apr 1 Image Deblurring Slides: (pdf, 4pp)
Reading: R. Fergus et al., Removing camera shake from a single image, SIGGRAPH 2006
Reading: S. Cho and S. Lee, Fast motion deblurring, ACM Trans. Graph., 2009
Paper presentation: Q. Zhang et al., 100+ Times Faster Weighted Median Filter (WMF), In Proc. CVPR, 2014
8 Apr 8 Sparse Coding PA2 out: (pdf, code)
Slides: (pdf, 4pp)
Reading: M. Elad et al., On the Role of Sparse and Redundant Representations in Image Processing, IEEE Proceedings, 2010
Reading: M. Aharon et al., K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation, IEEE Trans. Signal Processing, 2006
Reading: L. Xu et al., Image Smoothing via L0 Gradient Minimization, ACM Trans. Graph., 2011
Paper presentation: T. Michaeli and M. Irani, Blind deblurring using internal patch recurrence, In Proc. ECCV, 2014
9 Apr 15 Image Segmentation Project progress reports due
Slides: (pdf, 4pp)
Reading: J. Shi and J. Malik, Normalized Cuts and Image Segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 2000
Reading: P. Arbelaez et al., Contour Detection and Hierarchical Image Segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 2011
Reading: J. J. Lim et al., Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection, In Proc. CVPR, 2013
Paper presentation: X. Ren and L. Bo, Discriminatively Trained Sparse Code Gradients for Contour Detection, In Proc. NIPS, 2012
10 Apr 22 Project Progress Presentations
11 Apr 29 Graphical Models PA2 due­­­­­­
PA3 out (pdf, code)
Slides: (pdf, 4pp)
Reading: A. Blake and P. Kohli, Introduction to Markov Random Fields, Markov Random Fields for Vision and Image Processing, The MIT Press, 2011.
Reading: C. Rother et al., GrabCut: Interactive foreground extraction using iterated graph cuts, ACM Trans. Graph., 2004.
Paper Presentation: P. Isola et al., Crisp Boundary Detection Using Pointwise Mutual Information, In Proc. ECCV, 2014
12 May 6 Semantic Segmentation Slides: (pdf, 4pp)
Reading: J. Shotton et al., TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context, Int. Journal Comp. Vis., 2007
Reading: C. Liu et al., Nonparametric Scene Parsing via Label Transfer, IEEE Trans. Pattern Anal. Mach. Intell., 2011
Paper Presentation: D. Kuettel and V. Ferrari, Figure-ground segmentation by transferring window masks, In Proc. CVPR, 2012
13 May 13 Visual Saliency Slides: (pdf, 4pp)
Reading:
Reading: L. Itti et al., A model of saliency-based visual attention for rapid scene analysis, IEEE Trans. Pattern Anal. Mach. Intell., 1998
Reading: E. Erdem and A. Erdem, Visual saliency estimation by nonlinearly integrating features using region covariances, Journal of Vision, 2013
Paper Presentation: R. Mottaghi et al., The Role of Context for Object Detection and Semantic Segmentation in the Wild, In Proc. CVPR, 2014
14 May 20 What we’ve done, Where we’re going PA3 due

Grading

Paper presentations and Quizzes

The students will be required to present at least one research paper either of their choice or from the suggested reading list. These papers should be read by every student as the quizzes about the presented papers will be given on the weeks of the presentations.

Programming Assignments

There will be three assignments related to the topics covered in the class. Each assignment will involve implementing an algorithm, carrying out a set of experiments to evaluate it, and writing up a report on the experimental results. All assignments have to be done individually, unless stated otherwise.

Project

The students will be required to do a project in image processing which should be done in individually. For a detailed description of the course project and the related schedule, follow this link. In preparing your progress and final project reports, you should use the provided template and submit them electronically in PDF format.

Reference Books

Resources

Communication:

The course webpage will be updated regularly throughout the semester with lecture notes, programming and reading assignments and important deadlines. All other course related communications will be carried out through Piazza. Please enroll it by following the link https://piazza.com/hacettepe.edu.tr/spring2015/bil717

Policies:

Attendance to lectures is required. You are responsible for all material presented in lecture.

All work on assignments must be done individually unless stated otherwise. You are encouraged to discuss with your classmates about the given assignments, but these discussions should be carried out in an abstract way. That is, discussions related to a particular solution to a specific problem (either in actual code or in the pseudocode) will not be tolerated.

In short, turning in someone else’s work, in whole or in part, as your own will be considered as a violation of academic integrity. Please note that the former condition also holds for the material found on the web as everything on the web has been written by someone else.

© 2015 Hacettepe University