EE-451 / 4 credits

Teacher(s): Bozorgtabar Seyedbehzad, Thiran Jean-Philippe

Language: English


Summary

This course gives an introduction to the main methods of image analysis and pattern recognition.

Content

Introduction

Digital image acquisition and properties.

Pre-processing: geometric transforms, linear filtering, image restoration.

Introduction to Mathematical Morphology

Examples and applications

Segmentation and object extraction

Thresholding, edge detection, region detection.

Segmentation by active contours. Applications in medical image segmentation.

Shape representation and description

Contour-based representation, region-based representation. Morphological skeletons

Shape recognition

Statistical shape recognition, Bayesian classification, linear and non-linear classifiers, perceptrons, neural networks and unsupervised classifiers.

Applications.

Practical works and mini-project on computers

 

Keywords

image processing, image analysis, image segmentation, feature extraction, introduction to machine learning, pattern recognition.

Learning Outcomes

By the end of the course, the student must be able to:

  • Use Image Pre-processing methods
  • Use Image segmentation methods
  • Choose shape description methods appropriate to a problem
  • Use classification methods appropriate to a problem

Transversal skills

  • Use a work methodology appropriate to the task.
  • Assess one's own level of skill acquisition, and plan their on-going learning goals.
  • Identify the different roles that are involved in well-functioning teams and assume different roles, including leadership roles.
  • Make an oral presentation.
  • Summarize an article or a technical report.

Teaching methods

Ex cathedra and practical work and oral presentation by the students

Assessment methods

Continuous control : oral exam during the semester + graded reports and mini-poject

Prerequisite for

Semester project, Master project, doctoral thesis

In the programs

  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Exam form: During the semester (summer session)
  • Subject examined: Image analysis and pattern recognition
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Practical work: 2 Hour(s) per week x 14 weeks
  • Type: optional

Reference week

Related courses

Results from graphsearch.epfl.ch.