University of West Attica

Artificial Intelligence and Data Science

Computer vision

Course info:

Semester: 6

General Foundation

ECTS: 6

Hours per week: 3

Professor: T.B.D.

Teaching style: Face to face, usage of specialized software

Grading: Homework / projects (60%), final written exam (40%)

Activity Workload
Lectures 36
Class assignments 42
Independent study 72
Course total 150

Learning Results

Upon successful completion of the course, students will be able to:

  • Understand the theoretical and practical aspects of computing with images;
  • Describe the foundation of image formation, measurement, and analysis;
  • Develop common methods for robust image matching and alignment;
  • Comprehend the geometric relationships between 2D images and the 3D world;
  • Understand object and scene recognition and categorization from images;
  • Possess the practical skills necessary to build computer vision applications.

Skills acquired

  • Data and information retrieval, analysis and synthesis
  • Decision making
  • Individual work
  • Team work
  • New research ideas generation
  • Promotion of free, creative and inductive thinking
  • Introduction to Computer Vision
  • Spatial filtering
  • Frequency domain
  • Edge detection
  • Feature detection and matching
  • Image segmentation
  • Camera geometry
  • Camera calibration, stereo vision
  • Epipolar geometry, stereo disparity matching, RANSAC
  • Reconstruction and depth cameras
  • Recognition, bag of features, scene recognition
  • CNN architectures for computer vision: ResNets, R-CNNs, FCNs, U-nets
  • Tracking
  1. Computer Vision: Algorithms and Applications, R. Szeliski
  2. Concise Computer Vision, R. Klette

  3. Deep Learning, I. Goodfellow, Y. Bengio and A. Courville, MIT Press, 2016, http://www.deeplearningbook.org.

Related scientific journals:

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • International Journal of Computer Vision
  • Computer Vision and Image Understanding
  • Proceedings of CVPR and ICCV conferences
Learning Results - Skills acquired

Learning Results

Upon successful completion of the course, students will be able to:

  • Understand the theoretical and practical aspects of computing with images;
  • Describe the foundation of image formation, measurement, and analysis;
  • Develop common methods for robust image matching and alignment;
  • Comprehend the geometric relationships between 2D images and the 3D world;
  • Understand object and scene recognition and categorization from images;
  • Possess the practical skills necessary to build computer vision applications.

Skills acquired

  • Data and information retrieval, analysis and synthesis
  • Decision making
  • Individual work
  • Team work
  • New research ideas generation
  • Promotion of free, creative and inductive thinking
Course content
  • Introduction to Computer Vision
  • Spatial filtering
  • Frequency domain
  • Edge detection
  • Feature detection and matching
  • Image segmentation
  • Camera geometry
  • Camera calibration, stereo vision
  • Epipolar geometry, stereo disparity matching, RANSAC
  • Reconstruction and depth cameras
  • Recognition, bag of features, scene recognition
  • CNN architectures for computer vision: ResNets, R-CNNs, FCNs, U-nets
  • Tracking
Recommended bibliography
  1. Computer Vision: Algorithms and Applications, R. Szeliski
  2. Concise Computer Vision, R. Klette

  3. Deep Learning, I. Goodfellow, Y. Bengio and A. Courville, MIT Press, 2016, http://www.deeplearningbook.org.

Related scientific journals:

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • International Journal of Computer Vision
  • Computer Vision and Image Understanding
  • Proceedings of CVPR and ICCV conferences