United States Patent 5,696,964
United States Patent 5,696,964
Cox, et. al. Dec. 9, 1997

Multimedia database retrieval system which maintains a posterior probability distribution that each item in the database is a target of a search
Inventors: Cox; Ingemar J. (Lawrenceville, NJ); Miller; Matthew L. (Vilnius, LT); Omohundro; Stephen M. (Monmouth Junction, NJ); Yianilos; Peter N. (Princeton, NJ).
Assignee: NEC Research Institute, Inc. (Princeton, NJ).
Appl. No.: 634,313
Filed: Apr. 16, 1996
Intl. Cl. : G06F 17/30
Current U.S. Cl.: 395/605; 395/326; 395/615
Field of Search: 395/601, 602, 603, 604, 605, 615, 326, 968

References Cited

U.S. Patent Documents
5,579,471Nov., 1996Barber et al. 395/326

Other References

Ingemar J. Cox et al., "Target Testing and the Pic Hunter Bayesian Multimedia Retrieval System," Proc. of the 3d Forum on Research and Technology Advances in Digital Libraries, ADL '96 , IEEE, pp. 66-75.

Ingemar J. Cox et al., "PicHunter: Bayesian Relevance Feedback for Image Retrieval," Proc. of the ICPR '96, IEEE, pp. 361-369.

"Jacob Methodology" @, date unknown.

Denis Lee et al., "Query by Image Content Using Multiple Objects and Multiple Features: User Interface Issues," 1994 Int'l Conf. on Image Processing, IEEE, pp. 76-80.

Atsushi Ono et al., "A Flexible Content-Based Image Retrieval System with Combined Scene Description Keyword," Proc. of Multimedia '96, IEEE, pp. 201-208.

P.M. Kelly, et al. "Candid Comparison Algorithm for Navigating Digital Image Databases", Proceedings 7(^th) International Working Conference on Scientific and Statistical Database Management, pp. 252-258, 1994.

Barros, et al. "Indexing Multispectral Images for Content-Based Retrieval", Proc. 23(^rd) AIPR Workshop on Image and Information Retrieval, Proc. 23(^rd) Workshop, Washington, DC, Oct. 1994, pp. 25-36.

Flickner, et al. "Query by Image and Video Content, the QBIC System", IEEE Computer 28(9); 23-32, 1995.

Hirata, et al. "Query by Visual Example, Content Based Image Retrieval" Advance in Database Technology-EDBT '92, Springer-Verlag, Berlin 1992, pp. 56-71.

Primary Examiner: Kulik; Paul V.
Attorney, Agent or Firm: Brosemer; Jeffery J.


A queryless, multimedia database search method incorporating a Bayesian inference engine that refines its answer with each user response. The set of user responses includes of a series of displays and user actions, and is defined by a relatively simple user interface.

21 Claims, 13 Drawing Figures