Institut TELECOM / TELECOM SudParis / ARTEMIS : Teaching

	IMA4509	Visual content analysis
	Coordination	Nicolas ROUGON
	Duration	45h
	ECTS	4
	Prerequisite	None
	Objectives	To master the core techniques for low-level visual content (2D/3D still images and videos) analysis, as a preliminary structuring step towards interpretation and content-based access. To understand the related technological and economical challenges, and to gain insight into emerging application issues.
	Content	Visual content analysis: economical and industrial issues, technological challenges and new services in the Information and Communication Society 2D/3D modelling: - Low-level and high-level attributes - Geometric, deterministic, stochastic and fuzzy approaches Still image segmentation: - Global approaches: histogram techniques, frequential filtering - Differential approaches: edge and singularity detection - Mathematical morphology - Contour-based variational approaches: active contours and surfaces, level set methods - Region-based variational approaches: the Mumford-Shah model, region competition - Bayesian methods, Markov Random Fields Texture analysis and synthesis Video sequence analysis: motion estimation, dynamic segmentation and object tracking Hybrid approaches for multimedia data segmentation
	Bibliography	L.G. Shapiro, G.C. Stockman Computer Vision Prentice Hall, 2001 A. Bovik (Ed.) Handbook of Image & Video Processing Academic Press, 2000
	Assignment pattern	Continuous evaluation via personal supervised coursework (45h) comprising 3 short presentations (15h) and a 2-4 student group project (30h).