Digital Image Processing and Analysis
COURSE: Digital Image Processing and Analysis
Code: ФЕИТ05023
ECTS points: 6 ECTS
Number of classes per week: 3+0+0+3
Lecturer: Assoc. prof. Zoran Ivanovski
Subject of the course content:
The digitized image and its properties. Data structures for image analysis. Image pre-processing: Luminance transformations; Geometric transformations; Local pre-processing; Image restoration. Advanced segmentation techniques: Thresholding; Edge-based segmentation; Region-based seg mentation. Advanced optimal border and surface detection approaches. Shape representation and description: Region identification; Contour-based shape representation and description; Region-based shape representation and description; Shape classes. Object recognition: Knowledge representation; Statistical and syntactic pattern recognition; Recognition as graph matching; Optimization techniques in recognition. Mathematical morphology: Basic concepts and morphological transformations; Topological processing. Texture: Statistical texture description; Syntactic texture description methods; Hybrid texture description methods; Texture recognition method applications. Image understanding: Image understanding control strategies; Active contour models and point distribution models; Pattern recognition methods in image understanding; Scene labeling and constraint propagation; Semantic image segmentation and understanding. Motion analysis: Differential motion analysis methods; Optical flow; Analysis based on correspondence of interest points; Kalman filters. 3d vision: 3d vision tasks; Geometry for 3d vision; Radiometry and 3d vision.
Literature:
- Milan Sonka, Vaclav Hlavac, Roger Boyle, “Image Processing, Analysis and Machine Vision”, Chapman & Hall, 3rd ed., 2008.
- Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing”, Prentice Hall, 3rd ed., 2007.
- Richard Hrtley, Andrew Zisserman, “Multiple View Geometry in Computer Vision”, Cambridge University Press, 2nd ed., 2003.
