Machine vision and image processing

Course guarantor:

Lecturer:

Tutor:

Supervisor:

Department of Applied Mathematics

Synopsis:

Camera systems are becoming a common part of life by being universally available. Related to this phenomenon is the need to process and evaluate image information. The course introduces students to different types of camera systems and a variety of methods for image and video processing. The course is focused on practical use of camera systems for solving problems of practice that the graduates may encounter.

Requirements:

https://courses.fit.cvut.cz/BI-SVZ/classification/index.html

Syllabus of lectures:

1. Machine Vision and Physical Principles

2. Types of Sensors and Optics

3. Camera System and Image Processing

4. Image as a Matrix

5. Perspective and Image Geometry

6. Image Preprocessing - Transformation and Correction

7. Image Preprocessing - Morphology and Shape Characteristics

8. Image Preprocessing - Spatial and Frequency Domain Filtering

9. Image Segmentation - Edge Detection

10. Image Segmentation - Hough Transform and Region-based Segmentation

11. Image Recognition, Object Detection, Modern Trends

12. Modern Trends in Image Recognition

Syllabus of tutorials:

1. Introduction to tools

2. Working with cameras and basics of image processing

3. Optics defects, camera calibration

4. Image segmentation

5. Utilizing lights

6. Perspective of images

7. Working with depth cameras

8. Line-scan cameras

9. Transformation techniques

10. Image perspective, 360° lenses

11. Basics of measurement with a thermal camera

12. Image classification, object detection

Study Objective:

The student is expected to gain the following from the course:

- The ability to respond to vaguely defined demands for machine vision in practice.

- Knowledge that allows them to understand problems from a machine vision perspective and design an appropriate imaging system, including the camera, lens, and lighting, with the aim of obtaining ideal image data for further processing.

- Theoretical knowledge about a range of algorithms that can be applied with minimal effort to the acquired ideal data to solve tasks.

- Practical skills in implementing these algorithms using Python on real-world data.

Study materials:

[1] McAndrew A., Computational Introduction to Digital Image Processing, CRC Press, 2. vydání, 2016

[2] Sundararajan D., Digital Image Processing: A Signal Processing and Algorithmic Approach, Springer, 2017

[3] Birchfield S., Image Processing and Analysis, Cengage Learning, 2016

[4] Acharya T., Ray A. K., Image Processing: Principles and Applications, Wiley, 2005

[5] Burger W., Burge M. J., Principles of Digital Image Processing: Fundamental Techniques, Springer-Verlag, 2009

Note:

Further information:

https://courses.fit.cvut.cz/BI-SVZ/

No time-table has been prepared for this course

The course is a part of the following study plans: