Announcements

  1. (Dec 4) Course page is online.
  2. (Jan 24) Course information is added.
  3. (Jan 24) Syllabus is available.
  4. (Jan 24) There is a waiting list at the CS Dept. (Secretary's office) for non-CS students who would like to register to this course.
  5. (Jan 29) Slides for introduction are available.
  6. (Feb 3) Slides for digital image fundamentals are available.
  7. (Feb 11) Slides for binary image analysis are available.
  8. (Feb 11) Slides for digital image fundamentals are updated with examples.
  9. (Feb 13) Homework assignment 1 is available.
  10. (Feb 13) Added Matlab code examples for processing images.
  11. (Feb 15) Added late submission policy and honor code for assignments to the syllabus.
  12. (Feb 19) Added Matlab code examples for binary image analysis.
  13. (Feb 19) First part of the slides for linear filtering is available.
  14. (Feb 24) Second part of the slides for linear filtering is available.
  15. (Feb 27) Slides for edge detection are available.
  16. (Feb 27) There will be no class on March 2, 2007.
  17. (Mar 12) Slides for edge detection are updated.
  18. (Mar 13) Slides for pattern recognition are available.
  19. (Mar 14) Homework assignment 2 is available.
  20. (Mar 18) Homework assignment 2 due date is postponed to March 29, 2007.
  21. (Mar 18) Added Matlab code examples for filtering.
  22. (Mar 20) Slides for local feature detectors are available.
  23. (Mar 23) Slides for color image processing are available.
  24. (Mar 28) Homework assignment 3 is available.
  25. (Apr 2) Slides for texture analysis are available.
  26. (Apr 7) Slides for image segmentation are available.
  27. (Apr 23) Homework assignment 4 is available.
  28. (Apr 23) Slides for representation and description are available.
  29. (May 7) Slides for image retrieval are available.
  30. (May 8) Project description is available.
  31. (May 11) Slides for image classification and object recognition are available.
  32. (May 21) Project presentations will be made at EA 502 during 10:00-12:00 on May 27th.

Personnel

Instructor: Selim Aksoy (Office: EA 423, Email: )
TA: Hüseyin Gökhan Akçay (Office: EA 522, Email: akcay[at]cs.bilkent.edu.tr)

Course Information

Schedule: Tue 11:40-12:30, Fri 8:40-10:30 (EB 103)
Office hours: Selim Aksoy (Fri 10:40-12:00)
Hüseyin Gökhan Akçay (TBD)
Catalog description: Image acquisition, sampling and quantization. Spatial domain processing. Image enhancement. Texture analysis. Edge detection. Frequency domain processing. Color image processing. Mathematical morphology. Image segmentation and region representations. Statistical and structural scene descriptions. Applications.
Course emphasis and goals: This course provides an introduction to image analysis and computer vision for undergraduates. We will start with low-level vision (early processing) techniques such as binary image analysis, filtering, edge detection and texture analysis. Then, we will cover mid-level vision topics such as image segmentation and feature extraction in detail. Finally, we will do case studies on several applications such as image retrieval and classification. The emphasis will be on feature extraction and image representations for recognition.
Prerequisites: Good programming background, data structures, linear algebra, vector calculus, basics of signal processing. No prior knowledge of image processing or computer vision is assumed.

Texts

Lecture Schedule

Chapters

Contents

Introduction

[ Slides: pps | pdf ]

(Jan 30)

Topics:
  • Overview
  • Example applications

Digital Image Fundamentals

[ Slides: pps | pdf ]

(Feb 2, 6)

Topics:
  • Acquisition, sampling, quantization
  • Image enhancement
  • Image formats
  • Linear algebra and MATLAB review
Readings:
  • GW Ch 1, 2, 3.1-3.4
  • SS Ch 1, 2
References:
Software:

Binary Image Analysis

[ Slides: pps | pdf ]

(Feb 9, 13, 16)

Topics:
  • Pixels and neighborhoods
  • Mathematical morphology
  • Connected components analysis
  • Automatic thresholding
Readings:
  • GW Ch 2.5, 9.1-9.5, 10.3
  • SS Ch 3.1-3.5, 3.8
Software:

Linear Filtering

[ Slides: Part 1 (pps | pdf) | Part 2 (pps | pdf) ]

(Feb 20, 23)

Topics:
  • Spatial domain filtering
  • Frequency domain filtering
  • Image enhancement
Readings:
  • GW Ch 3.5-3.8, 4
  • SS Ch 5.1-5.5, 5.10-5.11
Software:

Edge Detection

[ Slides: pps | pdf ]

(Feb 27, Mar 6, 9)

Topics:
  • Edges, lines, arcs
  • Hough transform
Readings:
  • GW Ch 10.1-10.2
  • SS Ch 5.6-5.8, 10.3-10.4
References:
Software:

Pattern Recognition Overview

[ Slides: Part 1 | Part 2 | Part 3 ]

(Mar 13)

Topics:
  • Brief introduction to pattern recognition
  • K-means and hierarchical clustering
Readings:
  • GW Ch 12.1-12.2
  • SS Ch 4
References:
Software:

Local Feature Detectors

[ Slides: pps | pdf ]

(Mar 16, 20)

Topics:
  • Corners and other interest points
  • Invariants
References:
Software:

Color Image Processing

[ Slides: pps | pdf ]

(Mar 23)

Topics:
  • Color spaces and conversions
Readings:
  • GW Ch 6
  • SS Ch 6.1-6.5

Texture Analysis

[ Slides: pps | pdf ]

(Mar 27, 30)

Topics:
  • Statistical approaches
  • Structural approaches
Readings:
  • GW Sec 11.3.3
  • SS Ch 7

Image Segmentation

[ Slides: pps | pdf ]

(Apr 3, 6)

Topics:
  • Histogram-based approaches
  • Clustering-based approaches
  • Region growing
  • Split-and-merge
  • Morphological approaches
  • Graph-based approaches
Readings:
  • GW Ch 10.4-10.5
  • SS Ch 10.1
References:
Software:

Spring Break

(Apr 9-13)

No class

Representation and Description

[ Slides: pps | pdf ]

(Apr 17, 20, 24)

Topics:
  • Image representations and descriptors
  • Region representations and descriptors
Readings:
  • GW Ch 11
  • SS Ch 10.2, 3.7
References:

Case Studies

[ Slides: Part 1 (pps | pdf) | Part 2 (pps | pdf) ]

(Apr 27, May 1, 4, 8, 11)

Topics:
  • Pattern recognition
  • Image retrieval
  • Image classification
  • Object recognition
References:

Exams

Homework

  1. Homework assignment 1: description | data (Due: February 27, 2007 as online submission)
  2. Homework assignment 2: description | data | software (Due: March 29, 2007 as online submission)
  3. Homework assignment 3: description | data | software (Due: April 13, 2007 as online submission)
  4. Homework assignment 4: description | data | software (Due: May 7, 2007 as online submission)

Please make sure you fully understand the late submission policy and the honor code for assignments in the syllabus. Cheating and plagiarism on homework assignments will be punished according to the regulations of the University as described in the Bilkent University Policy on Academic Honesty / Öğrenci Disiplin İlke ve Kuralları.

Project

The goal of the project is to develop a content-based image retrieval system that supports queries by example. The similarity between the query and an image in the database will be computed based on global image features, individual region features, and combinations of regions.

Project teams:

  1. Gokberk Cinbis, Volkan Dinc
  2. Yasar Kemal Alp, Ibrahim Emir Atalay, Gorkem Saygili
  3. Ates Akaydin, Baris Koc
  4. Alp Artar, Bahadir Erkan, Mustafa Emre Kazdagli
  5. Eren Algan, Abdullah Bulbul, Onur Kucuktunc
  6. Yunus Emre Barun, Emre Candan, Ilker Onur Kaya
  7. Dogus Ertemur, Efe Karasabun, Seyhun Sariyildiz
  8. Bahadir Kemaloglu
  9. Ali Sengul

Grading Policy

Homework:40%
Quiz:10%
Exam:20%
Project:25%
Class participation:5%

Related Links