Pattern recognition and image analysis

• Low level image processing, linear/non linear filtering, morphomathematics.
• Image segmentation.
• Object feature extraction from digital images.
• Supervised and unsupervised classification methods.
• Image processing techniques applied to industrial and biomedical problems.

• The lecture recalls the basics in digital image processing and analysis, ranging from principles of image acquisition to object recognition.
• Several automatic segmentation techniques are explained and compared with respect to practical implementation issues.
• Morphomathematic methods are introduced, in particular the watershed technique. Image feature descriptors are defined (texture, shape, color,...) and serve as the input to recognition systems.
• Classical machine learning methods are explained and analysed in terms of their application conditions for pattern recognition.
• The objective of the course is to give to the students notions of the analytic approach to image segmentation and pattern recognition problems through both theory and application motivated examples.

Required and Corequired knowledge and skills

INFO-H-500 Image acquisition and processing or equivalent

lectures and practical works

Contribution to the teaching profile

This teaching unit contributes to the following competences:

• Gérer, explorer et analyser les données médicales (dossier médical, imagerie, génomique, statistiques)

• Communiquer en anglais dans le domaine de l’ingénierie

References, bibliography, and recommended reading

 
Handbook of Image & Video Processing Alan C. Bovik (Editor)
Digital Image Processing: Concepts, Algorithms, and Scientific Applications Bernd Jahne (Author)
Digital Image Processing Rafael C. Gonzalez (Author), Richard E. Woods (Author)
Image Processing, Analysis, and Machine Vision Milan Sonka (Author), Vaclav Hlavac (Author), Roger Boyle (Author)
A Wavelet Tour of Signal Processing, Second Edition (Wavelet Analysis & Its Applications).. Stephane Mallat (Author)
The Image Processing Handbook, Second Edition John C. Russ (Author)
Handbook of Medical Imaging: Processing and Analysis Management (Biomedical Engineering) Isaac Bankman (Editor)
Handbook of Medical Imaging, Volume 2. Medical Image Processing and Analysis J.Michael Fitzpatrick (Author), Milan Sonka (Author)
Active Contours: The Application of Techniques from Graphics, Vision, Control Theory and Statistics to Visual Tracking of Shapes in Motion Andrew Blake (Author), Michael Isard (Author)
Handbook of Computer Vision and Applications, Three-Volume Set Bernd Jahne (Editor), Horst Haussecker (Editor), Peter Geissler (Editor)
Mathematical Methods and Algorithms for Signal Processing Todd K. Moon (Author), Wynn C. Stirling (Author)
Pattern Recognition Engineering Morton Nadler (Author), Eric P. Smith (Author)
Mathematical Morphology in Image Processing (Optical Science and Engineering) [Hardcover] Edward Dougherty (Author)
Digital Image Processing Methods (Optical Science and Engineering) Dougherty (Author)
Duda, Hart et Stork, Pattern classification, John Wiley et Sons.
Theodoridis S, Koutroumbas K: Pattern recognition, Academic Press (on-line acces from the ULB network)
 

Course notes

• Université virtuelle
• Podcast

Contacts

Olivier.Debeir@ulb.be , Christine.Decaestecker@ulb.be

Campus

Solbosch

Method(s) of evaluation

• Oral examination
• Written report

Oral examination

Written report

• Questions are asked for each of the two parts of the course.
• There is a preparation period, without notes.
• Depending on the circumstances, the exam can be done remotely using Teams.

Mark calculation method (including weighting of intermediary marks)

The grade is constructed according to a mean (identical weighting for the two parts of the course).

Language(s) of evaluation

• english
• french