Course contents at a glance

These notes are intended for teaching and learning in digital image processing and computer vision courses.The notes are still under construction. The content is not without typos, and the authors have done their best to present quality information. If you see areas for improvement, please let us know or submit a pull request with your fixes to our GitHub repository. You may explore them in a linear fashion (this page), or use the ISPeL system (second item on the menu bar above) for nonlinear, personalized learning.

The ISPeL system is still under development. It is founded on topic-based authoring, which focuses on authoring small, modular, and reusable components with minimal dependencies. The intent is to provide each learner with quality content, examples and practice problems in an environment designed to encourage inclusive pedagogy and a personalized learning experience within a non-course-centric curriculum.

We welcome your collaboration toward the goal of making ISPeL system and content a valuable learning resource.

The linear style exploration of the course is divided into several parts. Each part addresses a cohesive list of interrelated topics.

Problem-Based Learning (PBL) Activities

This course uses Problem-Based Learning (PBL). It is a student-centered pedagogy which enables acquiring a deeper knowledge through active exploration of authentic projects. PBL projects are shown to promote the development of problem-solving abilities, critical thinking skills, communication skills, team work, and life-long learning. PBL projects also provide context for learning and help achieve a deeper understanding of course content and long-term retention.

Explore PBL projects here.

Image formation and acquisition

  1. Human and computer vision

  2. Image modalities

  3. Sampling and quantization

  4. Image geometry and interpolation

Spatial domain processing

  1. Pixel intensity transformation functions

  2. Pixel intensity transformations through histogram equalization

  3. Pixel intensity transformations through histogram matching

  4. Spatial filtering

Frequency domain filtering

  1. Discrete Fourier transform \((1D)\)

  2. Discrete Fourier transform \((2D)\)

  3. Image smoothing

  4. Image sharpening

Image restoration

  1. Noise models

  2. Estimating degradation functions

  3. Restoration filters

Image segmentation

  1. Edge detection

  2. Thresholding

  3. Region-based segmentation

Color image processing

  1. Color models

  2. Color transformations

  3. Smoothing and sharpening

  4. Segmentation based on color

Morphological image processing

  1. Morphological operations

  2. Morphological algorithms

  3. Grayscale morphology

Image compression

  1. Compression models

  2. Compression methods

Deep learning approaches

  1. Convolutional neural networks

  2. Object detection

  3. Image classification

  4. Image generation