From oscar Sat Jan 13 20:02:04 1996 Flags: 000000000001 Received: (from oscar@localhost) by DB.Stanford.EDU (8.7.1/8.7.1) id UAA22824 for gio; Sat, 13 Jan 1996 20:02:03 -0800 Date: Sat, 13 Jan 96 20:02:03 PST From: Oscar Firschein To: gio@DB.Stanford.EDU Subject: First class notes Message-ID: First lecture CS545I 1 - Why study image databases? Image databases are an increasingly important type of database as sources of images increase, methods of storage improve, and the Net offers the communication ability However, images have important unique characteristics The database designer must know and understand these characteristics 2- Goal of seminar To gain an appreciation of the special problems of image retrieval, to learn about some current systems, to learn about the indexing and database organization technqiues, and to get hands-on experience with one of the systems 3 - Some sources of images Medical imagery (x-ray ,NMR, ultrasonic, etc,) News and entertainment videos Art and photo collections Consumer and engineering catalogues Scientific images (astronomy, earth resources, etc.) Intelligence images Home photos/videos 4 - Types of user request There is a remarkable variety of user requests. Users may want combinations of the following requests: SIMILARITY: Find image that looks like this image (or parts of it look like part of this image) OBJECT: Find image that contains a cat OBJECT RELATIONSHIP: Find image that contains a cat near a dog MOOD: Find a sad/happy/... picture VIEW ANGLE: Find a picture of a crowd taken from an airplane TIME OF DAY/SEASON: Find a picture of Yosemite taken at day/night/sunset/winter COLOR: Find a picture with a red apple TEXTURE: Find picture with a brick texture SHAPE: Find picture with circular object GEOGRAPHIC: Find aerial image of the port of San Francisco 5 - Approach to image database design One could treat an image database as if it were a document database. Create a database in which each image is manually tagged with an index term Queries are combinations of index terms User reviews results and modifies qquery HOWEVER This approach does not take advantage of the special aspects of an image: People can analyze images very fast An image has many "meanings" depending on the interest or "point of view" of the viewer 6 - An Ideal image database system: allows user to review image "thumbnails" presents image in order of "closeness" uses a variety of description approaches, many of them automated also allows retrieval using conventional relational, etc. databases 7 - Capabilities needed Similarity metric must match human idea of similarity of images Search must be efficient enough to be interactive User must be able to specify needs without becoming an image or DB expert -- a good approach is for user to specify by providing examples close to what is desired Image descriptor-finding must be automated 8 - Problems How to normalize an image: scale, orientation Capturing aspects of content by using invariants or discriminants Can these invariants retain semantic info? Efficiency of invariants Can title or caption of image aid in finding invariants? 9 - Some existing systems IBM Ultimedia manager combines QBIC (Query by Image Content) color, shape, texture and traditional DB searching MIT Media lab Photobook that uses appearance, 2-D shape, and texture for interactive image browsing UC Berkeley Chabot system integrates relational DB and color analysis.