SylabUZ

Generate PDF for this page

Image recognition - course description

General information
Course name Image recognition
Course ID 11.3--INFD-RozObr- Er
Faculty Faculty of Engineering and Technical Sciences
Field of study Computer Science
Education profile academic
Level of studies Second-cycle Erasmus programme
Beginning semester winter term 2023/2024
Course information
Semester 2
ECTS credits to win 6
Course type obligatory
Teaching language english
Author of syllabus
  • dr hab. inż. Marek Kowal, prof. UZ
Classes forms
The class form Hours per semester (full-time) Hours per week (full-time) Hours per semester (part-time) Hours per week (part-time) Form of assignment
Project 15 1 - - Credit with grade
Laboratory 30 2 - - Credit with grade
Lecture 15 1 - - Credit with grade

Aim of the course

To familiarize students with the techniques of image processing, segmentation, recognition and classification.

Prerequisites

Artificial intelligence

Scope

  1. Image processing: image loading and saving, image types, color spaces and histogram, cropping and affine operations, point operators, image intensity transformation, basic image filtering, morphological operations
  2. Image segmentation: line and edge detection, thresholding methods, watershed method, active contours, deep neural networks
  3. Feature extraction: contour and region descriptors, corner and center detection, SIFT descriptors, Convolutional Neural Networks
  4. Object detection and classification: application of descriptors, classifiers and deep neural networks to detect and classify objects in images

Teaching methods

conventional lecture, exercises, project

Learning outcomes and methods of theirs verification

Outcome description Outcome symbols Methods of verification The class form

Assignment conditions

lecture - obtaining a positive grade from the written test

laboratory - obtaining positive grades from laboratory exercises reports

project - obtaining a positive assessment of the completed project

final grade = 30% lecture + 40% laboratory + 30% project

 

Recommended reading

  1. Digital Image Processing /Rafael C. Gonzalez, Richard E. Woods/ Pearson, 2018.
  2. Computer Vision: Algorithms and Applications /Richard Szeliski / Springer, 2022.
  3. Hands-On Image Processing with Python /Sandipan Dey/ Packt Publishing, 2018.
  4. Deep Learning with Python /François Chollet/ Manning, 2017.
  5. Deep Learning Ian /Goodfellow, Yoshua Bengio, Aaron Courville/ MIT Press, 2016.

 


 

Further reading

  1. Computer Vision Projects with OpenCV and Python 3 /Matthew Rever/ Packt Publishing, 2018.

Notes


Modified by dr hab. inż. Marek Kowal, prof. UZ (last modification: 25-04-2023 18:01)