BBM 413 - Fundamentals of Image Processing (Fall 2012)

Lectures: Tuesday 13:00-15:45 @D9

Salvador Dali’s Study for the Dream Sequence in Spellbound (1945)


Instructor:   

Erkut Erdem

erkut-at-cs.hacettepe.edu.tr

Office: 114, Tel: 297 7500 / 149

Office Hours: Wednesday 10:00-11:00


Lectures: 

Tuesday, 13:00-15:45 @ D9 

Monday 


TAs:

Levent Karacan

karacan-at-cs.hacettepe.edu.tr

Office Hours: To be announced!      


Course Description:

The subject matter of this advanced undergraduate course is about the fundamentals of image processing. The course is structured around key topics in image processing, including image formation, point operations and histogram processing, spatial filtering techniques, frequency domain approaches, image smoothing, edge detection and image segmentation. The main aim of this course is to provide an introduction to students who wish to specialize in interrelated disciplines like image processing, computer vision and computational photography. The students are expected to develop a foundational understanding and knowledge of concepts that underly image processing and related fields. The students will also be expected to gain hand-on experience via a set of programming assignments supplied in the complementary BBM 415 Image Processing Practicum. Hence, the students are strongly advised to register both BBM 413 and BBM 415 classes.


Prerequisites:

Good math (calculus, linear algebra, statistics) and programming skills. Students are not expected to have any prior knowledge of image processing techniques.


Textbooks:


Grading Policy:

Grading for BBM 413 will be based on a set of written assignments (15%), a midterm exam (35%) and a final exam (45%). Participation in class discussions will also be an important factor for the grade (5%). In BBM 415, the grading will be based on at least 4 programming assignments which will be done individually.


Important Dates:

Programming Assignment 1   

10 October 2012

Programming Assignment 2   

31 October 2012

Programming Assignment 3   

21 November 2012

Programming Assignment 4   

19 December 2012

Midterm exam

20 November 2012

Final exam

To be announced later.


Detailed Schedule:


Week

Date  

Topic

From the book

Additional Readings

Assignments


1

10/2

Introduction [pdf]

S1

D. Marr, Vision. Chapter 1   

2

10/9

Image formation and the digital camera [pdf]  

S2.1-2.3.1

PA 1 out
code, images

3

10/16

Color perception and color spaces [pdf]

S2.3.2

Beau Lotto's TED Talk: Optical illusions show how we see   

4

10/23

Point operations [pdf]  

S3.1, GW3.1-3.3

PA1 due

5

10/30

Spatial filtering [pdf]  

S3.2-3.3

PA2 out

6

11/6

Frequency Domain Techniques [pdf]  

S3.4, GW4.1-4.10  

7

11/13

Image pyramids and wavelets [pdf]  

S3.5, GW7.1

A. Oliva, A. Torralba, P.G. Schyns, Hybrid Images
ACM Transactions on Graphics, ACM SIGGRAPH, 25-3, 527-530, 2006   

PA2 due

8

11/20

Midterm exam

PA 3 out
images

9

11/27

Gradients, edges, contours [pdf]  

S4.2,4.3.1-4.3.2

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

10

12/4

Image smoothing [pdf]  

S3.2

PA3 due

11

12/11

Image segmentation I [pdf]  

S5.1-S5.2

E. Borenstein and S. Ullman, Class-Specific, Top-down Segmentation
ECCV 2002, LNCS 2351, pp. 109-122, 2002   

12

12/18

Image segmentation II [pdf]  

S5.3-5.5

PA4 out

13

12/25

Advanced topics

14

1/1

No class (New Year’s Day)

PA4 due



Additional Resources:


Communication:

The course webpage will be updated regularly throughout the semester with lecture notes, programming and 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/fall2012/bbm413


Policies:

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.