Jedes Modul umfasst 3 ECTS. Sie wählen insgesamt 10 Module/30 ECTS in den folgenden Modulkategorien:
- 12-15 ECTS in Technisch-wissenschaftlichen Modulen (TSM)
TSM-Module vermitteln Ihnen profilspezifische Fachkompetenz und ergänzen die dezentralen Vertiefungsmodule. - 9-12 ECTS in Erweiterten theoretischen Grundlagen (FTP)
FTP-Module behandeln theoretische Grundlagen wie die höhere Mathematik, Physik, Informationstheorie, Chemie usw. Sie erweitern Ihre abstrakte, wissenschaftliche Tiefe und tragen dazu bei, den für die Innovation wichtigen Bogen zwischen Abstraktion und Anwendung spannen zu können. - 6-9 ECTS in Kontextmodulen (CM)
CM-Module vermitteln Ihnen Zusatzkompetenzen aus Bereichen wie Technologiemanagement, Betriebswirtschaft, Kommunikation, Projektmanagement, Patentrecht, Vertragsrecht usw.
In der Modulbeschreibung (siehe: Herunterladen der vollständigen Modulbeschreibung) finden Sie die kompletten Sprachangaben je Modul, unterteilt in die folgenden Kategorien:
- Unterricht
- Dokumentation
- Prüfung
Analyzing images is a very complex task that has many important real-world applications. This module presents powerful techniques to extract information from images and 3D data, based on machine learning and deep learning methods. These methods are mostly used as “black boxes” and their inner workings are not discussed in much detail. The module provides an overview of many image analysis applications such as document analysis, medical imaging and autonomous driving; examples of advanced uses of deep learning on images (generative networks for image synthesis, adversarial networks, neural style transfer) are also discussed.
Eintrittskompetenzen
Prerequisites:
- Basic knowledge of machine learning (e.g. Andrew Ng’s ML course on Coursera)
- Good command of an imperative programming language, basic knowledge of Python (the module will use Python 3).
- www.scipy-lectures.org/index.html Sections 1.1, 1.2, 1.3, 3.6.1, 3.6.2
- Basic knowledge of probability, statistics, linear algebra (vectors, matrices)
- Students are expected to take their laptops for the Lab activities
Lernziele
- Students know how images and 3D data are represented and manipulated by software
- Students know the most important problems related to image analysis: e.g. image classification, segmentation and object detection and tracking
- Students can apply machine learning and deep learning techniques to solve image-related problems, and deal with practical issues arising in the field (dataset engineering, data augmentation, data normalization)
- Students have seen different examples of image analysis problems and common solution techniques, and are able to acquire additional expert knowledge from the scientific literature and online resources
Modulinhalt
- Introduction
- Basic image processing methods applied to document processing: binarization; segmentation of text into lines, words and characters; connected component analysis.
- Image classification
- applications to OCR: handcrafted features; convolutional neural networks.
- Image classification with small datasets: data augmentation techniques; one-shot learning; transfer learning and pre-trained models.
- Segmentation
- applications to medical images (2D, 3D)
- fully convolutional networks for semantic segmentation.
- Object detection
- face detection with cascading classifiers
- pedestrian detection for autonomous driving
- object tracking in videos.
- Generative models and Image Synthesis
- Applications to Image Inpainting;
- Generative Adversarial Networks;
- Neural style transfer.
Lehr- und Lernmethoden
Classroom teaching; programming exercises using python and frameworks in python
Bibliografie
- Computer Vision: Algorithms and Applications, Richard Szeliski, 2010
- Deep Learning with Python, Francois Chollet, early 2018, Sections 5, 8.3, 8.5
Vollständige Modulbeschreibung herunterladen
Zurück