Morphological Image Processing: Principles and Applications

Level: Introductory Length: 6.5 hours Format: Online Intended Audience: Scientists, engineers, technicians and managers who need to understand and/or apply the fundamental concepts and techniques of mathematical morphology for digital image processing are encouraged to take this course. Although no particular background is needed, some prior knowledge of set theory and lattice theory would be helpful. Description: This course is an introduction to the principles and basic concepts of Mathematical Morphology (MM) with applications to digital image processing and analysis. MM is a collection of non-linear operators related to the shape of geometrical structures in an image. It familiarizes the audience with the understanding, design, and implementation of algorithms in the various sub-areas of morphological image processing such as filtering, segmentation, measurements, texture analysis, shape recognition and scene interpretation. Many relevant DCS application examples using such morphological image processing methods (from different imaging modalities) will complement the technical descriptions. Learning Outcomes: This course will enable you to: have knowledge of the principles and basic concepts of Mathematical Morphology (MM) with applications of digital image processing and analysis. - explain the concepts and terminologies employed in MM: set theory, lattice algebra, ordering relations, discrete geometry - describe the fundamental notions of MM used to define the basic morphological operators: structuring element, dilation, erosion - explain the various operators used in MM for processing binary images: opening, closing, geodesic reconstruction, thinning, thickening, skeletonization - explain the extension of MM for processing gray-level, color and multispectral/hyperspectral images: sub-graph, structuring functions, level sets - demonstrate the performance of such morphological image processing methods for various DCS relevant applications: automatic target recognition in SAR imaging, road network extraction from satellite images, feature extraction in multispectral imaging, anomaly detection in hyperspectral imaging, optical inspection, target recognition in marine environments, road monitoring and obstacle detection, automatic mine detection, food quality analysis and control. Instructor(s): Johan Debayle is a Full Professor at MINES Saint-Etienne, France. He is actively engaged in research in adaptive image processing, mathematical morphology, pattern analysis and stochastic geometry. He has published over 120 papers in journals and conference proceedings. He is currently Associate Editor for the Journal of Electronic Imaging (SPIE), Image Analysis and Stereology (ISSIA) and Pattern Analysis and Applications (Springer). He is the Head of a Master of Science in Mathematical Imaging and Spatial Pattern Analysis (MISPA). He is a member of SPIE, IAPR, ISSIA and Senior Member of IEEE. SPIE online courses are on-demand and self-paced, with access for one year. For more information visit: spie.org/education/online-courses