Course Catalog 2009-2010 Basic Basic Pori International Postgraduate Open University |Degrees|     |Study blocks|     |Courses|

Person responsible

Serkan Kiranyaz, Moncef Gabbouj

Implementations

	Lecture times and places	Target group recommended to
Implementation 1	Per 4 : Thursday 12 - 14, TB110	Automaatiotekniikan koulutusohjelma International Students Jatko-opiskelijat Signaalinkäsittelyn ja tietoliikennetekniikan koulutusohjelma Sähkötekniikan koulutusohjelma Tietojohtamisen koulutusohjelma Tietotekniikan koulutusohjelma

Requirements

Attendance and completion of 60% Exercises Final Exam

Principles and baselines related to teaching and learning

Regular lecture-based teaching methods with a personal assignment to apply the knowledge.

Learning outcomes

The main topic is the current approaches for searching, browsing, and mining various types of multimedia data such as images, audio and video (audiovisual data). The focus is on applying methods from machine learning and computer vision to these problems. In this course, a broad range of techniques will be studied including multimedia features, video analysis and management, retrieval techniques, spatial indexing methods, long-term learning and Relevance Feedback, audio analysis and retrieval, semantic-based retrieval techniques.

Content

Content	Core content	Complementary knowledge	Specialist knowledge
1.	With the growth of the Internet and developments in imaging technology, very large digital image and video archives have been created and used in numerous applications. Together with the increase in the number of pictorial archives, demands are also growing for methodologies and techniques to store and retrieve audio-visual data. Therefore, understanding and thereby analysis of multimedia content at the semantic level is the only way towards realizing the full potential of emerging digital media technologies aimed at the delivery of compelling multimedia solutions. The integration of knowledge, semantics and low-level multimedia processing for the purpose of automatic semantics extraction from multimedia content is still the subject of active research in academia and industry.	Data mining	Multimedia formats

Evaluation criteria for the course

Assignments/Exercises : 30% Final Exam : 70% Project Work (optional) : 10%

Assessment scale:

Numerical evaluation scale (1-5) will be used on the course

Study material

Type	Name	Author	ISBN	URL	Edition, availability, ...	Examination material	Language
Book	Introduction to MPEG-7	B. S. Manjunath	0471 48678 7				English
Book	Multimedia Information Retrieval and Management	D. Feng et al.					English
Other literature					Relevant scientific papers and reference book material		English

Prerequisites

Correspondence of content

More precise information per implementation

	Description	Methods of instruction	Implementation
Implementation 1	Course Topic Current approaches for searching, browsing, and mining various types of multimedia data such as images, audio and video (audiovisual data). The focus is on applying methods from machine learning and computer vision on to these problems. In this course, a broad range of techniques will be studied including multimedia features, video analysis and management, retrieval techniques, spatial indexing methods, long-term learning and Relevance Feedback, audio analysis and retrieval, semantic-based retrieval techniques. Motivation and Scope With the growth of the Internet and developments in imaging technology, very large digital image and video archives have been created and used in numerous applications. Together with the increase in the number of pictorial archives, demands are also growing for methodologies and techniques to store and retrieve audio-visual data. Therefore, understanding and thereby analysis of multimedia content at the semantic level is the only way towards realizing the full potential of emerging digital media technologies aimed at the delivery of compelling multimedia solutions. The integration of knowledge, semantics and low-level multimedia processing for the purpose of automatic semantics extraction from multimedia content is still the subject of active research in academia and industry.