htw saar Piktogramm QR-encoded URL
Back to Main Page Choose Module Version:
XML-Code

flag flag

Image Processing and Pattern Recognition


Module name (EN):
Name of module in study programme. It should be precise and clear.
Image Processing and Pattern Recognition
Degree programme:
Study Programme with validity of corresponding study regulations containing this module.
Applied Informatics, Master, regulation 01.10.2026
Module code: PIM-BM
SAP-Submodule-No.:
The exam administration creates a SAP-Submodule-No for every exam type in every module. The SAP-Submodule-No is equal for the same module in different study programs.
P211-0137, P211-0138
Hours per semester week / Teaching method:
The count of hours per week is a combination of lecture (V for German Vorlesung), exercise (U for Übung), practice (P) oder project (PA). For example a course of the form 2V+2U has 2 hours of lecture and 2 hours of exercise per week.
2V+2P (4 hours per week)
ECTS credits:
European Credit Transfer System. Points for successful completion of a course. Each ECTS point represents a workload of 30 hours.
5
Semester: 3
Mandatory course: no
Language of instruction:
German
Assessment:
Oral examination (75%,), project work (25%)

[updated 29.10.2026]
Applicability / Curricular relevance:
All study programs (with year of the version of study regulations) containing the course.

DFMEES-211 (P610-0685, P610-0686) Electrical Engineering - Renewable Energy and System Technology, Master, regulation 01.10.2019 , semester 2, mandatory course, technical
E2802 (P211-0137, P211-0138) Electrical Engineering and Information Technology, Master, regulation 01.04.2019 , semester 1, mandatory course, technical
KIM-BM (P211-0137, P211-0138) Computer Science and Communication Systems, Master, regulation 01.10.2019 , optional course, informatics specific
MP.E2802 (P211-0137, P211-0138) Medical Physics, Master, regulation 01.04.2019 , semester 1, mandatory course
MP3105.BUM Medical Physics, Master, regulation 01.10.2025 , semester 1, mandatory course
PIM-BM (P211-0137, P211-0138) Applied Informatics, Master, regulation 01.10.2017 , optional course, informatics specific
PIM-BM (P211-0137, P211-0138) Applied Informatics, Master, regulation 01.10.2026 , semester 3, optional course, informatics specific
TIM-BM Technical Computer Science, Master, regulation 01.10.2026 , optional course, informatics specific

Suitable for exchange students (learning agreement)
Workload:
Workload of student for successfully completing the course. Each ECTS credit represents 30 working hours. These are the combined effort of face-to-face time, post-processing the subject of the lecture, exercises and preparation for the exam.

The total workload is distributed on the semester (01.04.-30.09. during the summer term, 01.10.-31.03. during the winter term).
60 class hours (= 45 clock hours) over a 15-week period.
The total student study time is 150 hours (equivalent to 5 ECTS credits).
There are therefore 105 hours available for class preparation and follow-up work and exam preparation.
Recommended prerequisites (modules):
PIM-DE Data Engineering
PIM-DS Data Science


[updated 30.04.2026]
Recommended as prerequisite for:
Module coordinator:
Prof. Dr.-Ing. Ahmad Osman
Lecturer: Prof. Dr.-Ing. Ahmad Osman

[updated 19.02.2020]
Learning outcomes:
- After successfully completing this course, students will be able to evaluate the interaction of hardware and software components for image processing systems.
- They will be able to select specific methods of image processing and pattern recognition for practical tasks and plan suitable methods for obtaining relevant image data.
- Students will be able to independently design tailor-made image analysis process chains for simple image analysis tasks, implement the algorithms in Matlab and evaluate the results.
- They will be able to describe and categorize algorithms in the field of image processing and machine learning.
 
During the tutorials we will demonstrate the methods and procedures presented in this lecture by way of simple exercises.

[updated 29.10.2026]
Module content:
Data acquisition techniques, algorithms for image filtering, image transformation and segmentation, standards, optimization methods, classification techniques, logistic regression, feature mappings, Bayes classifiers, support vector machines (SVM), neural networks, performance of machine classification methods

[updated 29.10.2026]
Teaching methods/Media:
Lecture notes, transparencies, projector, notes

[updated 29.10.2026]
Recommended or required reading:
Bishop, Christopher M.: Pattern recognition and machine learning, Springer, 10. Aufl., ISBN 978-0-387-31073-2
Burger, Wilhelm; Burge, Mark James: Digitale Bildverarbeitung: eine Einführung mit Java und ImageJ, Springer Vieweg, (akt. Aufl.)
Duda, Richard O.; Hart, Peter E.; Stock, David G.: Pattern Classification, Wiley, 2001, 2. Aufl., ISBN 978-0471056690
Gonzalez, Rafael C.; Woods, Richard E.: Digital Image Processing, Pearson, (akt. Aufl.)
Hastie, Trevor; Tinshirani, Robert; Friedman, Jerome H.: The elements of statistical learning: data mining, inference, and prediction, Springer, (akt. Aufl.)

[updated 29.10.2026]
 
[Sat Oct 31 16:09:24 CET 2026, CKEY=emE2802, BKEY=pim3, CID=PIM-BM, LANGUAGE=en, DATE=31.10.2026]