CS484 Image Analysis (Spring 2017)

Instructor: Gokberk Cinbis (Room: EA-431)
Instructor office hour:  Mon 10:40-11:30
TA: Mert Bulent Sariyildiz (mert.sariyildiz [at] bilkent.edu.tr)
TA office hour:  Thu 09:00-10:00
Syllabus:  Please read the syllabus for course details.
The course is based on the structure and contents of the previous offerings by Assoc. Prof. Selim Aksoy.

Lectures

Topics

Contents

Introduction

Feb 8

[ ]

Topics:
  • Overview
  • Example applications
Demos:

Digital Image Fundamentals

Feb 13 & 15

[ Slides ]

Topics:
  • Acquisition, sampling, quantization
  • Image enhancement
  • Image formats
  • Linear algebra and MATLAB review
Readings:
  • SS Ch 1, 2
  • GW Ch 1, 2, 3.1-3.4
References:
  • R. C. Gonzales, R. E. Woods, "Review material and slides on linear algebra, probability, and linear systems," 2002.
Software:

Binary Image Analysis

Feb 15 & 20

[ Slides: | Part 2 ]

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

Filtering

[ Slides: | ]

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

Edge Detection

[ ]

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

Local Feature Detectors

[ ]

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

Color Image Processing

[ ]

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

Texture Analysis

[ ]

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

Image Segmentation

[ ]

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

Representation and Description

[ ]

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

Pattern Recognition Overview

[ Slides: Part 1 | Part 2 ]

Topics:
  • Brief introduction to pattern recognition
Readings:
  • SS Ch 4
  • GW Ch 12.1-12.2
References:
Software:

Case Studies

[ Slides: | Part 2 | Part 3 (with kind permission from Prof. Linda Shapiro) ]

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

Exams

In exams, only printouts of course slides are allowed.

  • Midterm I: March 22, 2017, 10:40-12:30, EB-204 (in class hours). Grades.
  • Midterm II: April 19, 2017, 10:40-12:30, EB-204 (in class hours).

Homework

  • Homework 1: Binary image analysis. Due: March, 15, 2017, 23:50.
  • Homework 2: Fourier transform and template matching. Due: April 7, 2017, 23:50.
  • Homework 3: Image segmentation. Due: April, 24, 2017, 23:50.

Online submission: For homework submissions, please use the corresponding unit in CS484 Moodle site.

Project

  • Project details will be announced later.
  • The final report (only pdf is accepted) and source code files (zip) are due 23:50 on May 22, 2017.
  • Please use the CS484 Moodle submission page. Email submissions (unless Moodle is down) and late submissions will not be accepted.
  • The reports should ideally be around 6-8 pages, and must be prepared using the IEEE two-column conference template. Using LaTeX (or LyX) is recommended.

Honor code

Please make sure you fully understand the honor code in the syllabus as well as the Bilkent University Policy on Academic Honesty (in Turkish) and the Rules and Regulations of the Higher Education Council (YOK) (in Turkish). Cheating and plagiarism on exams, quizzes, and assignments will be punished according to these regulations.

We reserve the right to make changes in the course content.