CS 545I - Advanced Image Databases, W 95/96

Friday, 13 Jan 1996. 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 and CR, NMR, ultrasonic, etc,)
  • News and entertainment videos
  • Art and photo collections
  • Consumer and engineering catalogues
  • Scientific images (astronomy, earth resources, etc.) Home photos/videos

    4 - Types of user request

    There is a remarkable variety of user requests. Users may want combinations of the following requests:
  • SIMILALARITY: 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 query

    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:

    1. allows user to review image "thumbnails"
    2. presents image in order of "closeness"
    3. uses a variety of description approaches, many of them automated
    4. also allows retrieval using conventional relational, etc. databases

    7 - Capabilities needed

    1. Similarity metric must match human idea of similarity of images
    2. Search must be efficient enough to be interactive
    3. 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
    4. 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.