BIL 717 - Image Processing, Spring 2013

BIL 717 - Image Processing (Spring 2013)

Lectures: Tuesday 09:30-12:15@D5

A detail from Joan Miró's Peinture (Étoile Bleue), 1927

Instructor: Erkut Erdem

e-mail: erkut-at-cs.hacettepe.edu.tr

Office: 114

Tel: 297 7500 / 149

Office hours: By appointment.

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.

Reading Assignments:

Each week a number of research papers will be assigned as reading assignments. Students are expected to write a brief review of any of the assigned papers (less than a page) for half of the papers. Each review should summarize the paper in 4-5 sentences. The review should clearly identify the main contribution of the paper and describe the strengths and weaknesses of the paper. The reviews should be emailed to the instructor before class (by 09:00 on Tuesdays). Each student has 3 late days for the entire semester, but beyond that limit his/her submission will not be accepted.

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

Grading Policy:

Class participation

5%

Reading Assignments

12%

Programming Assignments

18%

Project

30%

Final Exam

35%

Course Schedule:

Week

Date

Topic

Additional Readings

Assignments

1

2/26

Introduction [slides],
Image Processing Basics [notes]

Vision. Chapter 1, D. Marr, 1982.

2

3/5

Linear Filtering [slides], [notes]
Edge Detection [slides]

A. P. Witkin, Scale-space filtering: A New Approach to Multi-Scale Description, In Proc. IJCAI, 1983

D. Marr and E. Hildreth, Theory of Edge Detection, Proc. R. Soc. Lond. B, 1980



3

3/12

Nonlinear Filtering [slides], [notes]

J. Weickert, Coherence-enhancing diffusion of colour images, Image and Vision Computing, 1999

T. Brox et al., Nonlinear structure tensors, Image and Vision Computing, 2006

G. Steidl and T. Teuber, Diffusion Tensors for Processing Sheared and Rotated Rectangles, IEEE Trans. Image Processing, 2009

PA1 out
code, images

4

3/19

Variational Segmentation Models [slides], [notes]

E. Erdem and S. Tari, Mumford-Shah Regularizer with Contextual Feedback, J. Math. Imaging and Vision, 2009

X. Bresson et al., Fast global minimization of the active contour/snake model, J. Math. Imaging and Vision, 2007

C. Xu and J. L. Prince, Snakes, Shapes, and Gradient Vector Flow, IEEE Trans. Image Processing, 1998

5

3/26

Modern Image Filtering [slides]

S. Paris and F. Durand, A Fast Approximation of the Bilateral Filter using a Signal Processing Approach, In Proc. ECCV, 2006

K. He et al., Guided Image Filtering, In Proc. ECCV, 2010

L. Pizarro et al., Generalised Nonlocal Image Smoothing, Int. Journal Comp. Vis., 2010

PA1 due

6

4/2

Modern Image Filtering (cont’d.) [slides]

K. Dabov et al., Image denoising by sparse 3-D transform-domain collaborative filtering, IEEE Trans. Image Processing, 2007

Farbman et al., Edge-preserving decompositions for multi-scale tone and detail manipulation, ACM Trans. Graph., 2008

Subr et al., Edge-preserving multiscale image decomposition based on local extrema, ACM Trans. Graph., 2009

7

4/9

Clustering-based Segmentation Models [slides]

Y. J. Lee and K. Grauman, Collect-Cut: Segmentation with Top-Down Cues Discovered in Multi-Object Images, In Proc. CVPR, 2010

P. Arbelaez et al., Contour Detection and Hierarchical Image Segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 2011

R. Achanta et al., SLIC Superpixels Compared to State-of-the-art Superpixel Methods, IEEE Trans. Pattern Anal. Mach. Intell., 2012

8

4/16

Markov Random Fields [slides]

C. Rother et al., Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs, In Proc. CVPR, 2006

V. Lempitsky et al., Image Segmentation by Branch-and-Mincut, In Proc. ECCV, 2008

J. Carreira and C. Sminchisescu, Constrained Parametric Min-Cuts for Automatic Object Segmentation, In Proc. CVPR, 2010

PA2 out
code

9

4/23

No class (The Republic Day)

10

4/30

Sparse Coding [slides]

M. Elad and M. Aharan, Image denoising via learned dictionaries and sparse representation, In Proc. CVPR, 2006

J. Yang et al., Image super-resolution as sparse representation of raw image patches, In Proc. CVPR, 2008

J. Mairal et al., Non-Local Sparse Models for Image Restoration, In Proc. ICCV, 2009

PA2 due

11

5/7

Low-rank Matrix Approximations [slides]

J. Wright et al., Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization, , In Proc. NIPS, 2009

Y. Peng et al., RASL: Robust Alignment by Sparse and Low-rank Decomposition for Linearly Correlated Images, , In Proc. CVPR, 2010

X. Liang et al., , Repairing Sparse Low-Rank Texture, In Proc. ECCV, 2012

PA3 out
code

12

5/14

Visual Saliency [slides]

A. Borji and L. Itti, Exploiting Local and Global Patch Rarities for Saliency Detection, , In Proc. CVPR, 2012

J. Yang and M-H. Yang, Top-Down Visual Saliency via Joint CRF and Dictionary Learning, , In Proc. CVPR, 2012

E. Erdem and A. Aykut, Visual saliency estimation by nonlinearly integrating features using region covariances, , Journal of Vision, 2013

13

5/21

Semantic Segmentation [slides]

P. Kohli et al., Robust Higher Order Potentials for Enforcing Label Consistency, In Proc. CVPR, 2008

D. Eigen and R. Fergus, Nonparametric Image Parsing using Adaptive Neighbor Sets, In Proc. CVPR, 2012

M. Rubinstein et al., Annotation Propagation in Large Image Databases via Dense Image Correspondence, In Proc. ECCV, 2012

PA3 due

14

5/28

Project Presentations

Resources:

Reference Books:

Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, 2010 (draft available online)

Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations, G. Aubert and P. Kornprobst, 2nd Edition, Springer-Verlag, 2006.

Markov Random Fields for Vision and Image Processing, Andrew Blake, Pushmeet Kohli, Carsten Rother, The MIT Press, 2011.

Related Conferences:

IEEE International Conference on Computer Vision (ICCV)

European Conference on Computer Vision (ECCV)

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

IEEE International Conference on Pattern Recognition (ICPR)

British Machine Vision Conference (BMVC)

Advances in Neural Information Processing Systems (NIPS)

Related Journals:

International Journal of Computer Vision (IJCV)

IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI)

Computer Vision and Image Understanding (CVIU)

Pattern Recognition (PR)

Journal of Mathematical Imaging and Vision (JMIV)

Image and Vision Computing (IMAVIS)

MATLAB Resources:

Introduction to MATLAB, by Danilo Šćepanović

MATLAB Tutorial, by Stefan Roth

MATLAB Primer, by MathWorks

Code Vectorization Guide, by MathWorks

Writing Fast MATLAB code, by Pascal Getreuer

MATLAB array manipulation tips and tricks, by Peter J. Acklam

Linear Algebra:

A Geometric Review of Linear Algebra, by Eero Simoncelli

An Introduction to Linear Algebra in Parallel Distributed Processing, by M.I. Jordan

Resources for scientific writing and talks:

Notes on writing, by Fredo Durand

How to write a great research paper, by Simon Peyton Jones (video)

Small Guide To Giving Presentations, by Markus Püschel

Giving an effective presentation: Using Powerpoint and structuring a scientific talk, by Susan McConnell (video)

Writing papers and giving talks, by Bill Freeman (notes)

Communication:

The course webpage will be updated regularly throughout the semester with reading assignments and important deadlines. All other communications will be carried out through Piazza. Please enroll it by following the link https://piazza.com/hacettepe.edu.tr/spring2013/bil717

Class participation	5%
Reading Assignments	12%
Programming Assignments	18%
Project	30%
Final Exam	35%


Week	Date	Topic	Additional Readings	Assignments

1	2/26	Introduction [slides], Image Processing Basics [notes]	Vision. Chapter 1, D. Marr, 1982.
2	3/5	Linear Filtering [slides], [notes] Edge Detection [slides]	A. P. Witkin, Scale-space filtering: A New Approach to Multi-Scale Description, In Proc. IJCAI, 1983 D. Marr and E. Hildreth, Theory of Edge Detection, Proc. R. Soc. Lond. B, 1980
3	3/12	Nonlinear Filtering [slides], [notes]	J. Weickert, Coherence-enhancing diffusion of colour images, Image and Vision Computing, 1999 T. Brox et al., Nonlinear structure tensors, Image and Vision Computing, 2006 G. Steidl and T. Teuber, Diffusion Tensors for Processing Sheared and Rotated Rectangles, IEEE Trans. Image Processing, 2009	PA1 out code, images
4	3/19	Variational Segmentation Models [slides], [notes]	E. Erdem and S. Tari, Mumford-Shah Regularizer with Contextual Feedback, J. Math. Imaging and Vision, 2009 X. Bresson et al., Fast global minimization of the active contour/snake model, J. Math. Imaging and Vision, 2007 C. Xu and J. L. Prince, Snakes, Shapes, and Gradient Vector Flow, IEEE Trans. Image Processing, 1998
5	3/26	Modern Image Filtering [slides]	S. Paris and F. Durand, A Fast Approximation of the Bilateral Filter using a Signal Processing Approach, In Proc. ECCV, 2006 K. He et al., Guided Image Filtering, In Proc. ECCV, 2010 L. Pizarro et al., Generalised Nonlocal Image Smoothing, Int. Journal Comp. Vis., 2010	PA1 due
6	4/2	Modern Image Filtering (cont’d.) [slides]	K. Dabov et al., Image denoising by sparse 3-D transform-domain collaborative filtering, IEEE Trans. Image Processing, 2007 Farbman et al., Edge-preserving decompositions for multi-scale tone and detail manipulation, ACM Trans. Graph., 2008 Subr et al., Edge-preserving multiscale image decomposition based on local extrema, ACM Trans. Graph., 2009
7	4/9	Clustering-based Segmentation Models [slides]	Y. J. Lee and K. Grauman, Collect-Cut: Segmentation with Top-Down Cues Discovered in Multi-Object Images, In Proc. CVPR, 2010 P. Arbelaez et al., Contour Detection and Hierarchical Image Segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 2011 R. Achanta et al., SLIC Superpixels Compared to State-of-the-art Superpixel Methods, IEEE Trans. Pattern Anal. Mach. Intell., 2012
8	4/16	Markov Random Fields [slides]	C. Rother et al., Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs, In Proc. CVPR, 2006 V. Lempitsky et al., Image Segmentation by Branch-and-Mincut, In Proc. ECCV, 2008 J. Carreira and C. Sminchisescu, Constrained Parametric Min-Cuts for Automatic Object Segmentation, In Proc. CVPR, 2010	PA2 out code
9	4/23	No class (The Republic Day)
10	4/30	Sparse Coding [slides]	M. Elad and M. Aharan, Image denoising via learned dictionaries and sparse representation, In Proc. CVPR, 2006 J. Yang et al., Image super-resolution as sparse representation of raw image patches, In Proc. CVPR, 2008 J. Mairal et al., Non-Local Sparse Models for Image Restoration, In Proc. ICCV, 2009	PA2 due
11	5/7	Low-rank Matrix Approximations [slides]	J. Wright et al., Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization, , In Proc. NIPS, 2009 Y. Peng et al., RASL: Robust Alignment by Sparse and Low-rank Decomposition for Linearly Correlated Images, , In Proc. CVPR, 2010 X. Liang et al., , Repairing Sparse Low-Rank Texture, In Proc. ECCV, 2012	PA3 out code
12	5/14	Visual Saliency [slides]	A. Borji and L. Itti, Exploiting Local and Global Patch Rarities for Saliency Detection, , In Proc. CVPR, 2012 J. Yang and M-H. Yang, Top-Down Visual Saliency via Joint CRF and Dictionary Learning, , In Proc. CVPR, 2012 E. Erdem and A. Aykut, Visual saliency estimation by nonlinearly integrating features using region covariances, , Journal of Vision, 2013
13	5/21	Semantic Segmentation [slides]	P. Kohli et al., Robust Higher Order Potentials for Enforcing Label Consistency, In Proc. CVPR, 2008 D. Eigen and R. Fergus, Nonparametric Image Parsing using Adaptive Neighbor Sets, In Proc. CVPR, 2012 M. Rubinstein et al., Annotation Propagation in Large Image Databases via Dense Image Correspondence, In Proc. ECCV, 2012	PA3 due
14	5/28	Project Presentations