Advertisement

Neural Networks and Image Data Management

  • D. Z. Badal

Abstract

This paper describes the research prototype of a postrelational DBMS CHINOOK being implemented at the University of Colorado at Colorado Springs. CHINOOK is intended to manage ultra-large databases of digitized images and digitized one-dimensional data as well as text and tables. This paper discusses our neural network based approach to the image data management in CHINOOK. We report our initial results on neural network generated image signatures which are the basis of CHINOOK image search and retrieval mechanism. We expect the image signatures to support the retrieval of images by their content.

Keywords

Query Language Image Query Image Signature Composite Image Atomic Image 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [AGRA90]
    Agrawal, R., et al., “OdeView: The Graphical Interface to Ode,” Proc ACM SIGMOD90, June 1990.Google Scholar
  2. [BADA87]
    Badal, D. Z., “Visual Recall Query Language,” Hewlett-Packard Laboratories Tech Report, STL-87-12, June 1987.Google Scholar
  3. [BALD89]
    Baldi, P. and Hornik, K., “Neural Networks and Principal Component Analysis: Learning from Examples Without Local Minima,” Neural Networks, 2, 1989, pp. 53–58.CrossRefGoogle Scholar
  4. [BECK91]
    Becker, B., et al, “Spatial Priority Search: An Access Technique for Scaleless Maps,” Proc ACM SIGMOD91, Denver, May 1991.Google Scholar
  5. [BECK90]
    Beckmann, N., et al., “The R*-tree: An Efficient and Robust Access Method for Points and Rectangles,” Proc ACM SIGMOD90, June 1990.Google Scholar
  6. [BODO88]
    Bodorik, P., and Riordan, J. S., “Heuristic Algorithm for Distributed Query Processing,” Proc Int Symp on Databases in Parallel and Distributed Systems, Austin, TX, 1988.Google Scholar
  7. [BODO90]
    Bodorik, P., et al., “Correcting Execution of Distributed Queries,” Proc 2nd Int Symp on Databases in Parallel and Distributed Systems, Dublin, Ireland, 1990.Google Scholar
  8. [BROL89]
    Brolio, J., et al., “ISR: A Database for Symbolic Processing in Computer Vision,” COMPUTER, Vol. 22, No. 12, December 1989.Google Scholar
  9. [CARE86a]
    Carey, M. J., et al., “The Architecture of the EXODUS Extensible DBMS: A Preliminary Report,” Computer Science Tech Report No 644, University of Wisconsin at Madison, May 1986.Google Scholar
  10. [CARE86b]
    Carey, M. J., et al., ” Object and File Management in the EXODUS Extensible Database System,” Computer Science Tech Report No. 638, University of Wisconsin at Madison, March 1986.Google Scholar
  11. [CARE88]
    Carey, M. J., et al., “A Data Model and Query Language for EXODUS,” Proc ACM SIGMOD 88, June 1988.Google Scholar
  12. [CARE89]
    Carey, M. and Livny, M., “Parallelism and Concurrency Control Performance in Distributed Database Machines,” Proc ACM SIG-MOD89, June 1989.Google Scholar
  13. [CHAN80]
    Chang, N. S. and Fu, K. S., “Query-by-Pictorial-Example,” IEEE Transactions Software Engineering, Vol. 6, November 1980.Google Scholar
  14. [CHAN87]
    Chang, N. S., et al., “A Relational Database System for Pictures,” Proc IEEE Workshop on Picture Data Description and Management, CS Press, 1977.Google Scholar
  15. [CHAN89]
    Chang, W. W., and Schek, H. J., “A Signature Access Method for Starburst Database System,” Proc VLDB 89, August 1989.Google Scholar
  16. [COPE88]
    Copeland, G., et al., “Data Placement in Bubba,” Proc ACM SIGMOD88, June 88.Google Scholar
  17. [COTT87]
    Cottrell, G. W., Munro, P. and Zisper, D, “Image Compression by Back Propagation: An Example of Extensional Programming,” University of California at San Diego, Institute for Cognitive Science Report 8702, February 1987.Google Scholar
  18. [COTT88]
    Cottrell, G. W., “Analysis of Image Compression by Back Propagation,” Workshop on Neural Architectures for Computer Vision, AAAI 1988.Google Scholar
  19. [COTT88a]
    Cottrell, G. W. and Munro, P., “Principal Component Analysis via Back Propagation,” Proc SPIE, Vol. 1001, Visual Communication and Image Analysis, 1988, pp. 1070-1077.Google Scholar
  20. [COTT90]
    Cottrel, G. W. and Fleming, M., “Face Recognition Using Unsupervised Feature Extraction,” Proceedings of the International Joint Conference on Neural Networks, June 1990, v. I.Google Scholar
  21. [CREA89]
    Creasy, P., “ENIAM: A More Complete Conceptual Schema Language,” Proc VLDB89, August 1989.Google Scholar
  22. [DEWI90]
    DeWitt, D. and Gray, J., “Parallel Database Systems: the Future of Database Processing or a Passing Fad,” ACM SIGMOD Record, Vol. 19, No. 4, 1990.Google Scholar
  23. [DOUG89]
    Dougherly, E. R., “A Homogeneous Unification of Image Algebra”, Journal of Imaging Science, Vol. 33, No. 4, July/August 1989, pp. 136–144.Google Scholar
  24. [FAHL90]
    Fahlman, S. E., and Lebiere, C. “The Cascade-Correlation Learning Algorithm,” CMU Technical Report, CMU-CS-90-100, February 1990.Google Scholar
  25. [FALO87]
    Faloutsos, C., et al., “Analysis of Object Oriented Spatial Access Methods,” Proc ACM SIGMOD 87, 1987.Google Scholar
  26. [FALO87a]
    Faloutsos, C., et al., “Optimal Signature Extraction and Information Loss,” ACM TODS, Vol. 12, No. 3, September 1987.Google Scholar
  27. [FALO88]
    Faloutsos, C. and Chan, R., “Fast Text Access Methods for Optical and Large Magnetic Disks: Design and Performance Comparison,” Proc VLDB 88, Sept 1988.Google Scholar
  28. [GOOD89]
    Goodman, A., et al., “Knowledge-Based Computer Vision — Integrated Programming Language and Data Management System Design,” COMPUTER, Vol. 22, No. 12, December 1989.Google Scholar
  29. [GRAE90]
    Graefe, G., “Encapsulation of Parallelism in the Volcano Query Processing System,” Proc ACM SIGMOD90, May 1990.Google Scholar
  30. [GUTM84]
    Guttman, A., “R-Trees: A Dynamic Index Structure for Spatial Searching,” Proc ACM SIGMOD 84, 1984.Google Scholar
  31. [GYSS90]
    Gyssens, M., et al., “A Graph-Oriented Object Model for Database End-User Interfaces,” Proc ACM SIGMOD90, June 1990.Google Scholar
  32. [HECH90]
    Hecht-Nielsen, R., “Neurocomputing,” Addison-Wesley, 1990.Google Scholar
  33. [HUTF88]
    Hutflesz, A., et al., ” Twin Grid Files: Space Optimizing Access Schemes”, Proc ACM SIGMOD 88, June 1988.Google Scholar
  34. [JAGA89]
    Jagadish, H. V. and O’Gorman, L., “An Object Model for Image Recognition,” COMPUTER, Vol. 22, No. 12, December 1989.Google Scholar
  35. [JAGA90]
    Jagadish, H. V., “Linear Clustering of Objects with Multiple Attributes,” Proc ACM SIGMOD90, June 1990.Google Scholar
  36. [JOSE88]
    Joseph, T. and Cardenas, A., “Picquery: A High Level Query Language for Pictorial Database Management,” IEEE Transactions Software Engineering, Vol. 14, May 1988.Google Scholar
  37. [KAST89]
    Kasturi, R., et al., “Map Data Processing in Geographic Information System,” COMPUTER, Vol. 22, No. 12, December 1989.Google Scholar
  38. [KIM88 ]
    Kim, W., et al., “Integrating an Object-Oriented Programming System with a Database System,” Proc OOPSLA 88 Conference, May 1988.Google Scholar
  39. [KIM89]
    Kim, W., et al., “Composite Objects Revisited,” Proc ACM SIGMOD 89, June 1989.Google Scholar
  40. [KING89]
    King, R. and Novak, M., “FaceKit: A Database Interface Design Toolkit,” Proc VLDB89, August 1989.Google Scholar
  41. [KOLO91]
    Kolovson, C. P. and Stonebraker, M., ” Dynamic Indexing Technique for Multi-Dimensioanl Interval Data,” Proc ACM SIGMOD91, Denver, May 1991.Google Scholar
  42. [KUNT89]
    Kuntz, M. and Melchert, R., “Pasta-3’s Graphical Query Language: Direct Manipulation, Cooperative Queries, Full Expressive Power,” Proc VLDB89, August 1989.Google Scholar
  43. [LEHM89]
    Lehman, T. J., and Lindsay, B., “The Starburst Long Field Manager,” Proc VLDB89, August 1989.Google Scholar
  44. [LINS88]
    Linsker, R., “Self-Organization in a Perceptual Network,” IEEE Computer, 21, March 1988, pp. 105-117.Google Scholar
  45. [NEUG91]
    Neugebauer, L., “Optimization and Evaluation of Database Queries Including Embedded Interpolation Procedures,” Proc ACM SIGMOD91, Denver, May 1991.Google Scholar
  46. [OREN90]
    Orenstein, J,. “A Comparison of Spatial Query Processing Techniques for Native and Parameter Spaces,” Proc ACM SIGMOD90, June 1990.Google Scholar
  47. [PIRA90]
    Pirahesh, H., et al., “Parallelism in Relational Data Base Systems: Architectural Issues and Design Approaches,” Proc 2nd Int Symp on Databases in Parallel and Distributed Systems, Dublin, Ireland, July 1990.Google Scholar
  48. [PIZA89]
    Pizano, A., et al., “Specification of Spatial Integrity Constraints in Pictorial Databases,” COMPUTER, Vol. 22, No. 12, December 1989.Google Scholar
  49. [ROSS88]
    Rossoupoulos, N., et al., “An Efficient Pictorial Database System for PSQL,” IEEE Transactions Software Engineering, Vol. 14, May 1988.Google Scholar
  50. [SEEG88]
    Seeger, B. and Kriegel, H. P., “Techniques for Design and Implementation of Efficient Spatial Access Methods,” Proc VLDB 88, Sept 1988.Google Scholar
  51. [SELL86]
    Sellis, T. K., “Global Query Optimization,” Proc ACM SIG-MOD86, Washington D. C., June 1986.Google Scholar
  52. [SHEK90]
    Shekita, E. and Carey, M., “A Performance Evaluation of Pointer-Based Joins,” Proc ACM SIGMOD90, June 1990.Google Scholar
  53. [STON88]
    Stonebraker, M. and Rowe, L. (editors), “The Postgres Papers,” University of California at Berkeley, Memorandum No. UCB/ERL M86/85, June 1987.Google Scholar
  54. [STON90]
    Stonebraker, M., et al., “On Rules, Procedures, Caching and Views in Data Base Systems,” Proc ACM SIGMOD90, June 1990.Google Scholar
  55. [STON91]
    Stonebraker, M., “Managing Persistent Objects in Multi-level Store,” Proc ACM SIGMOD91, May 1991.Google Scholar
  56. [VAND91]
    Vandenberg, S. and DeWitt, D., “An Algebra for Complex Objects with Arrays and Identity,” Proc ACM SIGMOD91, May 1991.Google Scholar

Copyright information

© Springer-Verlag/Wien 1992

Authors and Affiliations

  • D. Z. Badal
    • 1
  1. 1.Computer Science DepartmentUniversity of ColoradoColorado SpringsUSA

Personalised recommendations