CS 545I - Advanced Image Databases

Backup for archive on dbseminar/Archive/WinterY2001/WinterY2001.html.

Winter quarter, 2001
Fridays, 3:15 - 4:30
Gates building, Room 100

Oscar Firschein (oscar@db.stanford.edu) use for queries,

sponsored by Gio Wiederhold (gio@cs.stanford.edu).

Some References; see new URLs.

The first five seminars deal with the basics of image characterization; the next three presentations describe image and video retrieval systems. In the final seminar(s), registered students will present 15-20 minute reviews of papers in the literature.

An image matching system by James Ze Wang is based on a wavelet approach

Planned schedule for CS545I (click for class summaries)

Material from prior years Winter 1996-1997, Winter 1995-1996,


Today or soon.

Seminar abstract

CS545I is a reading and projects seminar devoted to advanced image and video databases, a topic of increasing interest due to large image and video databases soon to be available on the Web. The emphasis will be on combining image-derived descriptors and text descriptors to retrieve local and online images. There are many challenges in storing high-dimensional feature vectors for fast retrieval, and developing metrics of closeness between query and stored vectors. Applications including art collections, sales catalogs, aerial photographs, and medical images will be surveyed to illustrate the strengths or weaknesses of specific techniques. Retrieval from video databases is also an active area of research. We will be interested in how to automatically construct an inverse story-board (a visual summary) from video, and how to use the audio track to extract frames of interest.

Credit for the seminar only and a presentation will be 1 unit. Additional units (3 normally) under CS-395 will be available for students who wish to execute a project of their own choosing this or successor quarters. Check with Prof. Wiederhold for acceptable projects.

Students should pick out a presentation paper by the THIRD meeting of the quarter. Papers can be of your own choosing with approval of instructors, or from the following list (** denotes available from Oscar Firschein):


Students should have a background in database concepts of at least CS145.


Oscar Firschein (oscar@db.stanford.edu) recently retired from the Artificial Intelligence Center, SRI International and a four-year assignment to ARPA, where he was Program Manager for Image Understanding (IU). He has performed research and supervised many advanced projects in image processing.