Mathematical Morphology and its applications in Image Processing

Department of Electronics & Communication Engineering
National Institute of Technology Karnataka, Surathkal,
Mangalore 575025 INDIA
&
Centre d'Imagerie BioMédicale (CIBM)
Genève, Switzerland
TEQIP II sponsored Short Course on
Mathematical Morphology and its applications in Image Processing
July 14 – 25, 2015
Objective
Resource person
The objective of the course is to provide valuable inputs on advanced techniques in image
processing to students and young researchers. In image analysis, it is important to be able to
extract features, describe shapes and recognize patterns. Such tasks refer to geometrical
concepts such as size, shape, and orientation. Mathematical morphology uses concepts from set
theory, geometry and topology to analyse geometrical structures in an image.
Linear Image Processing
Historically, image processing is based on signal theory and, is basically linear. The heritage from
linear systems is mathematical tools like convolution, correlation and Fourier analysis. Because of
the linearity of operators, the undo operation is always possible, for example, deconvolution.
Recent discoveries in neurology have shown that an image is not interpreted in our brain as a
bunch of pixels but rather as a set of objects. These objects are characterized by external
boundaries and inner textures. The problem associated with linear operation, such the
convolution is the blurring effect, a consequence of the weighted sum of pixels, which tend to
destroy the sharpness of edges.
Object based image processing
An object is defined as a connected set of pixels being either brighter or darker than their
surroundings. To detect such objects, many algorithms are available. Most of them belong to a
framework called Mathematical Morphology, invented in 1964 by two French scientists, Georges
Matheron and Jean Serra from the Ecole des Mines de Paris who worked on the automatic
analysis of images occurring in mineralogy and petrography. The word morphology stems from
the Greek words morfh and logos, meaning the study of forms. In the context of image processing
it is a specific methodology designed for the analysis of the geometrical structure in an image by
probing it with small patterns, called structuring elements, of varying size and shape and finds
application in medical diagnostics, histology, industrial inspection, computer vision, and character
recognition.
Course Outline
Types of images; Discrete geometry; Transforms; Erosion, Dilation, rank filtering; Opening,
Closing; Hit or Miss transform; Connected operations; Granulometry; Morphological filtering;
Segmentation
Structure of the course
Theory and simulation are interleaved during the lectures. Practical work is based on Matlab and
on the additional toolbox which can be found at: http://www.mmorph.com
Prof. Michel Kocher is
currently Professor of Signal
and Image Processing at the
University of Applied Science
HEIG-VD, Yverdon, Switzerland
and an affiliated Professor of
Centre for Biomedical Imaging
(CIBM), University Hospital of
Geneva. He received his MSc in
Electrical Engineering in 1979
and PhD in Signal processing in
1983 from EPFL Lausanne,
Switzerland. He has also
worked at ATT Bell Labs, CERAC
research institute, Charmilles
Technologies and University of
Applied Science HEPIA Geneva.
His research interests are in
Signal and Image Processing,
Biomedical image analysis and
mathematical modelling.
Participants
Interested students, researchers and faculty of NITK Surathkal with knowledge of basics of Signal & Image processing can
participate in the course. Participants are expected to attend all the lectures and the practical sessions. Interested
participants may register by submitting the completed registration form to the Course Coordinator on or before July 03,
2015. The maximum number of participants would be limited to 40. Registration is free.
In case you need any additional information please send an email to the Coordinator.
Prof. Sumam David S.
Email: [email protected] Phone: 3502 (O)
Department of Electronics & Communication Engineering
National Institute of Technology Karnataka, Surathkal, Mangalore 575025 INDIA
TEQIP II sponsored Short Course on
Mathematical Morphology and its applications in Image Processing
July 14 – 25, 2015
Registration Form
Name:
Program: BTech/ MTech/ MTech(R)/ PhD/ Faculty
Specialisation:
Roll No (for students):
Department:
Email address:
Contact phone number:
Signature:
Recommendation of Faculty Advisor/ Research Guide (for students)
Approval of Head of the Department