skip to main content
10.1145/1167253.1167343acmconferencesArticle/Chapter ViewAbstractPublication Pagesacm-seConference Proceedingsconference-collections
Article

On the convergence of image compression and object recognition

Published: 18 March 2005 Publication History

Abstract

Over the past four decades, image compression and object recognition have evolved from pixel-level to region-level processing, and thence to feature-based resolution. For example, compression has progressed from entropy coding of a bit or pixel stream, to transform coding applied to rectangular encoding blocks, to feature-based compression that employs segmentation of isospectral or isotextural regions. Similarly, object recognition has progressed from operations on individual pixel intensities or spectral signatures, to region- or feature-based processing employing segmentation. Recent progress in image compression indicates that significantly decreased bit rate (thus, significantly increased compression ratio) can be obtained by isolating or segmenting, then compressing scene objects, which is called object-based compression or OBC.In this paper, the relationship between object segmentation and compression is presented theoretically, then exemplified in terms of current research in OBC. The relationship between object compression and recognition is also discussed theoretically. Recent work in object recognition is shown to be closely related theoretically to OBC. Two recently-developed paradigms, Muñoz et al.'s region growing algorithm and Campbell et al.'s Quick-Sketch, which support very efficient compression and accurate recognition/retrieval of image objects, are summarized. Additionally. a performance model is given for OBC that isolates space complexity bottlenecks for future enhancement and implementation.

References

[1]
Schmalz, M. S. "Overview of Image Compression", in Encyclopedia of Electro-Optics. Ed. Ron Driggers (2001) New York: Marcel Dekker.
[2]
Muñoz, X., Marti, J., Cufi, X., and Feixenet, J. Unsupervised active regions for multiresoltuion image segmentation. Proceedings IAPR International Conference on Pattern Recognition (2002).
[3]
Gibson, D. P., Campbell, N. W., and Thomas, B. T. Very low bit rate semantic compression of natural outdoor images, Proc. Picture Coding Symp. '99 (Oregon State Univ., USA, April 1999), pp. 231--234.
[4]
Schmalz, M. S. Object-based image compression. Proceedings SPIE4793 (2002) 13--23.
[5]
Schmalz, M. S. and Ritter, G. X. Techniques for region coding in object-based image compression, Proceedings SPIE5208 (2004), 11--21.
[6]
Ritter, G. X and Wilson, J. N. Handbook of Computer Vision Algorithms in Image Algebra, Second Edition, Boca Raton, FL: CRC Press (2001).
[7]
Schmalz, M. S. and Ritter, G. X. Boundary representation techniques for object-based image compression. Proceedings SPIE5208 (2004), 22--33.
[8]
Rao, A. R. and Lohse, G. L. Identifying high level features of texture perception. Computer Vision, Graphics, and Image Processing: Graphical Models and Image Processing55(3): (1993), 218--233.
[9]
Sriram, R., Francos, J. M., and Pearlman, W. A. Tex-ture coding using a Wold decomposition based model. IEEE Trans. Image Processing5 (1996), 1382--1386.
[10]
Drimbarean, A. and Whelan, P. Experiments in color texture analysis. Patt. Rec. Lett.22 (2001), 1161--1167.
[11]
Van de Wouwer, G., Scheunders, P., Livens, S. Van Dyck, D. Wavelet correlation signatures for color texture characterization, Pattern Recognition32 (1999), 443--451.
[12]
Carson, C., Belongie, S., Greenspan, H., and Malik, J. Blobword: Color and texture-based image sementation using EM and its application to content-based image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence24 (2002), 1026--1038.
[13]
Mirmehdi, M. and Petrou, M. Segmentation of color textures, IEEE Transactions on Pattern Analysis and Machine Intelligence22 (2000), 142--159.
[14]
Muñoz, X., Freixenet, J., Cufi, X., and Marti, J. Strategies for image segmentation combining region and boundary information. Pattern Recognition Letters24 (2003), 375--392.
[15]
Khotanzad, A. and Chen, J. Unsupervised segmentation of texture images by edge detection in multidimensional features, IEEE Trans. Pattern Analysis and Machine Intelligence11 (2003), 414--421.
[16]
Comaniciu, D. and Meer, P. Mean shift: A robust approach toward feature space analysis. IEEE Trans. Patt. Anal. and Machine Intelligence24 (2002), 1--18.
[17]
Salembier, P. Overview of the MPEG-7 standard and of future challenges for visual information analysis. Eurasip Journal on Appl. Signal Processing2002(4) (2002), 343--353.
[18]
Schmalz, M. S. and Ritter, G. X. Region segmentation techniques for object based compression - a review. Proceedings SPIE5561 (in press).
[19]
Campbell, N. W., Mackeown, P. J., Thomas, B. T., and Troscianko, T. Interpreting image databases by region classification", Pattern Recogn30(4): (1997). 555--563.

Cited By

View all
  • (2010)Data compression of multispectral images for FY-2C geostationary meteorological satellite2010 IEEE International Conference on Progress in Informatics and Computing10.1109/PIC.2010.5687425(118-121)Online publication date: Dec-2010

Index Terms

  1. On the convergence of image compression and object recognition

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    ACMSE '05 vol 2: Proceedings of the 43rd annual ACM Southeast Conference - Volume 2
    March 2005
    430 pages
    ISBN:1595930590
    DOI:10.1145/1167253
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 18 March 2005

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. object recognition
    2. object-oriented image compression
    3. performance analysis
    4. segmentation

    Qualifiers

    • Article

    Conference

    ACM SE05
    Sponsor:
    ACM SE05: ACM Southeast Regional Conference 2005
    March 18 - 20, 2005
    Georgia, Kennesaw

    Acceptance Rates

    Overall Acceptance Rate 502 of 1,023 submissions, 49%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)0
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 20 Jan 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2010)Data compression of multispectral images for FY-2C geostationary meteorological satellite2010 IEEE International Conference on Progress in Informatics and Computing10.1109/PIC.2010.5687425(118-121)Online publication date: Dec-2010

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media