MICRO-511 / 3 credits

Teacher(s): Unser Michaël, Van De Ville Dimitri Nestor Alice

Language: English


Summary

Introduction to the basic techniques of image processing. Introduction to the development of image-processing software and to prototyping using Jupyter notebooks. Application to real-world examples in industrial vision and biomedical imaging.

Content

  • Introduction. Image processing versus image analysis. Applications. System components.
  • Characterization of continuous images. Image classes. 2D Fourier transform. Shift-invariant systems.
  • Image acquisition. Sampling theory. Acquisition systems. Histogram and simple statistics. Max-Lloyd quantization (K-means).
  • Characterization of discrete images and linear filtering. z-transform. Convolution. Separability. FIR and IIR filters.
  • Morphological operators. Binary morphology (opening, closing, etc.). Gray-level morphology.
  • Image-processing tasks. Preprocessing. Matching and detection. Feature extraction. Segmentation.
  • Convolutional neural networks. Basic components. Operator-based formalism. CNN in practice: denoising and segmentation.

Learning Prerequisites

Required courses

Signals and Systems I & II (or equivalent)

 

Important concepts to start the course

1-D signal processing: convolution, Fourier transform, z-transform

 

Learning Outcomes

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

  • Exploit the multidimensional Fourier transform
  • Select appropriately Hilbert spaces and inner-products
  • Optimize 2-D sampling to avoid aliasing
  • Formalize convolution and optical systems
  • Design digital filters in 2-D
  • Analyze multidimensional linear shift-invariant systems
  • Apply image-analysis techniques
  • Construct image-processing software
  • Elaborate morphological filters
  • Exploit the multidimensional Fourier transform
  • Select appropriately Hilbert spaces and inner-products
  • Optimize 2-D sampling to avoid aliasing
  • Formalize convolution and optical systems
  • Design digital filters in 2-D
  • Analyze multidimensional linear shift-invariant systems
  • Apply image-analysis techniques
  • Construct image-processing software

Transversal skills

  • Use a work methodology appropriate to the task.
  • Manage priorities.
  • Use both general and domain specific IT resources and tools

Assessment methods

  • 70% final exam
  • 30% IP labs during semester

Resources

Moodle Link

In the programs

  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Fall
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional
  • Exam form: Written (winter session)
  • Subject examined: Image processing I
  • Lecture: 3 Hour(s) per week x 14 weeks
  • Type: optional

Reference week

Thursday, 10h - 13h: Lecture CO4
CO2

Related courses

Results from graphsearch.epfl.ch.