Schedule:
Mondays 7:25 PM - 9:55 PM
Building: TUTTLEMAN LEARNING CENTER 302
OBJECTIVE:
Content-based image and video retrieval is concerned with retrieving images and video sequences on the basis of automatically derived features, e.g. color, texture and shape information that is present in the images. The need for efficient storage and especially retrieval is a consequence of the increase of the number and size of digital image collections found in many application domains like journalism, advertising, weather forecasting, vision-based robot navigation, medicine etc. The emergence of content-based image/video-retrieval has brought together a number of disciplines, such as object recognition, feature extraction, information visualization, database indexing.
The course will mainly concentrate on topics of computer vision connected to databases. It will give an introduction to techniques of feature comparison in different domains, such as the frequency and the spatial domain.
The course will emphasize image-retrieval techniques based on shape recognition, comparing different techniques used in industrial and multimedia applications,it will cover video retrieval techniques, such as motion and key frame detection, typically needed for video surveillance systems, finally it will introduce searching techniques in image databases, such as indexing multimedia data in SQL, clustering etc.
For an example of an application please visit my online-internet-image database at
http://knight.cis.temple.edu/~shape
PREREQUISITES:
The course will be self-contained, all necessary concepts will be introduced, programming skills in JAVA and C++ are necessary, an introduction to MATLAB-programming will be given. Permission of the instructor is required.
TEXTBOOK:
- R. Veltkamp, H. Burkhardt, and H.-P. Kriegel (eds.): State-of-the-Art in Content-Based Image and Video Retrieval, Kluwer Academic Publishers, Boston, 2001.
- Different Research Articles
COURSE TOPICS:
- Introduction+Fundamentals of Image-Processing in MATLAB (/ JAVA / C++)
- Image Retrieval
o Color, Texture and Shape Based Techniques
o Object Recognition Based On Shape Comparison, Applications in Multimedia and Robotics
- Video Retrieval and applications:Motion Detection, Keyframe Detection,...
- Image+Multimedia Databases
GRADING:
Grades will be based on seminar presentations, projects and an exam.