Special Topics in Signal and Image Processing and Analysis

Course ID
Optional (free)
Spring Semeter
Ώρες Θεωρίας
Ώρες Εργαστηρίου


Introduction. Advanced methods for feature extraction and segmentation of signals and images. Methods of optimization and applications in signal processing and analysis. Convolutional neural networks (CNNs). Generative Adversarial Networks (GANs). Recurrent Neural Networks (RNNs). Design and architecture of neural network architectures. Python programming. Machine learning tools (Tensorflow, Keras, Pytorch). Neural network applications (object recognition, image segmentation, image classification, image synthesis, audio signal (and other time-series) processing and analysis, biomedical applications).

Course objectives

The course aims to familiarize students with machine learning techniques applicable in signal and image processing and analysis. The students will be equipped with the related theoretical background in machine learning, as well as with the design, parameterization and implementation of algorithms in real problems of signal/image processing. Emphasis will be provided in deep learning architectures.

After successfully completing the course, the students will:

  • Have acquired knowledge on classical machine learning approaches (clustering. classification) and the means to apply such approaches in signal and image processing and analysis.
  • Have acquired an in-depth understanding of the structure and function of deep learning architectures (CNN, GAN, RNN), with emphasis in signal/image processing and analysis applications.
  • Be able to develop algorithms using Python and related tools (Keras, Pytorch, colab, Tensorflow).

Have a critical view on the current developments and trends at the intersection of machine learning with signal and image processing.


  • Ψηφιακή Επεξεργασία και Ανάλυση Εικόνας, Παπαμάρκος Ν., Εκδόσεις Ν. Παπαμάρκου, 3η/2013, Αθήνα.
  • Ψηφιακή Επεξεργασία Σήματος, Hayes Monson H., Εκδόσεις Α. Τζιόλα & Υιοι, 1η έκδ./2000, Θες/νίκη.
  • Αναγνώριση Προτύπων, Θεοδωρίδης Σ., Κουτρουμπάς Κ., Εκδόσεις: Πασχαλίδης, 2011, Αθήνα.
  • Deep Learning, Goodfellow I., Bengio Y., Courville A., MIT Press (free online), 2016.

Assessment method

 Written examinations at the end of the semester.

Course material

Lectures in the classroom using multimedia tools (ppt presentations, video, live-stream lectures) Consolidation exercises during the lectures Material in e-class (lectures power-point, suggested exercises) Additional recommended readings

Skip to content