Skip to main content

Image Classification and Segmentation for Densely Packed Aggregates

  • Conference paper
Advances in Knowledge Discovery and Data Mining (PAKDD 2007)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 4426))

Included in the following conference series:

  • 1413 Accesses

Abstract

This paper presents a methodology for delineating densely packed aggregate particles based on aggregate image classification. There is no earlier work on segmentation of aggregate particles has exploited these two building blocks for making robust object delineation. The proposed method has been tested experimentally for different kinds of densely packed aggregate images, which are difficult to detect by a normal edge detector. As tested, the studied algorithm can be applied into other applications too.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Gallagher, E.: Optoelectronic coarse particle size analysis for industrial measurement and control. Ph.D. thesis, University of Queensland, Dept. of Mining and Metallurgical Engineering (1976)

    Google Scholar 

  2. Maerz, N.H., Palangio, T.W.: Post-Muckpile, Pre-Primary Crusher, Automated Optical Blast Fragmentation Sizing. Fragblast 8(2), 119–136 (2004)

    Article  Google Scholar 

  3. Schleifer, J., Tessier, B.: Aggregateation Assessment using the FragScan System: Quality of a Blast. Int. J. Fragblast 6(3-4), 321–331 (2002)

    Article  Google Scholar 

  4. Kemeny, J., et al.: Improvements in Blast Aggregateation Models Using Digital Image Processing. Int. J. Fragblast 6(3-4), 311–320 (2002)

    Article  Google Scholar 

  5. Wang, W.X., Fernlund, J.: Shape Analysis of Aggregates. KTH-BALLAST Report no. 2, KTH, Stockholm, Sweden (1994)

    Google Scholar 

  6. Pal, N.R., Pal, S.K.: A review of image segmentation techniques. Int. J. Pattern Recognition 26(9), 1277–1294 (1993)

    Article  Google Scholar 

  7. Wang, W.X.: Image analysis of aggregates. J. Computers & Geosciences 25, 71–81 (1999)

    Article  Google Scholar 

  8. Wang, W.X.: Binary image segmentation of aggregates based on polygonal approximation and classification of concavities. Int. J. Pattern Recognition 31(10), 1503–1524 (1998)

    Article  Google Scholar 

  9. Otsu, N.: A threshold selection method from gray-level histogram. IEEE Trans. Systems Man Cybernet. 9, 62–66 (1979)

    Article  Google Scholar 

  10. Suk, M., Chung, S.M.: A new image segmentation technique based on partition mode test. Int. J. Pattern Recognition 16(5), 469–480 (1983)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Zhi-Hua Zhou Hang Li Qiang Yang

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer Berlin Heidelberg

About this paper

Cite this paper

Wang, W. (2007). Image Classification and Segmentation for Densely Packed Aggregates. In: Zhou, ZH., Li, H., Yang, Q. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2007. Lecture Notes in Computer Science(), vol 4426. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71701-0_99

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-71701-0_99

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-71700-3

  • Online ISBN: 978-3-540-71701-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics