A Study on the Surface Image Processing of the Mixed Mineralized Lining

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Background/Objectives: A method for qualitatively interpreting the special surface characteristics and the geometrical optics relationships, which are relatively important when intending to obtain the information of the objects from the contrast images, and for finally detecting the areas of the problems that look like the faults from the images (linings) of the solid bodies that are materialized with the mixed minerals is proposed.

    Methods/Statistical analysis: By extracting the interested areas on real time by using the background differential images and by dividing the interested areas by carrying out a principal component analysis and by calculating the vector relations, whether or not there is a lining fault is decided.

    Findings: This research proposes an image handling method that detects and classifies the problematic areas that look like the faults from the lining images which are materialized with the mixed minerals that were entered through the camera, and it shows the examples in which the method was actually applied.

    Improvements/Applications: The method being proposed will be applied for automatically detecting the cracked parts on the surface of the lining, for classifying the types, and measuring the extent of the fault.


  • Keywords

    Geometric optics, lining surface inspection, computer vision, background differential image,Plane homography.

  • References

      [1] Joaquim Salvi, Xavier Armangue, Joan Batlle (2002), A Comparative review of camera calibrating methods with accuracy evaluation,Pattern Recognition 35,1617-1635.

      [2] Mohamed Benallal and Jean Meunier (2002), Camera Calibration with a Viewfinder, The 15th InternationalConference on Vision Interface, May 27-29, Calgary, Canada.

      [3] Yong-Shen Chen, Sheng-Wen Shih, Yi-Ping Hung and Chiou-ShannFuh (2001), Simple and Efficient Method of Calibrating a Motorized Zoom Lens, Image and Vision Computing, Vol. 19, No. 14, 1099-1110.

      [4] M. Dare and C.S. Fraser (2000), Linear Infrastructure Mapping Using Airborne Video Imagery and Subsequent Integration into a GIS, Inprocessings of the IEEE International Geoscience and Remote Sensing Symposium.

      [5] R. S. Brid, (1997). Two Dimensional Pattern Matching. Information Processing Letters, Vol. 6, No. 5, Oct., 168-170.

      [6] J. Salvi, X. Armangue and J. Batle. (2002). A Comparative review of camera calibrating methods with accuracy evaluation. Pattern Recognition 35, 1617-1635.

      [7] Anthony G. Willey and Kam W. Wong. (1995). Geometric calibration of zoom lenses for computer vision metrology. PE&RS, vol. 61, No. 1, 69-74

      [8] C. Lawrence Zitnick, T. Kanade. (2000). A Cooperative algorithm for stereo matching and occlusion detection. IEEE Trans. Pattern Anal. Mach. Intell., Vol. 22, no 7, 675-684.

      [9] JuyangWeng, Paul cohen and Marc Herniou. (1992). Camera calibration with distortion models and accuracy evaluation. IEEE Pattern Analysis and Machine Intelligence, Vol. 14, No. 10, 674-684.

      [10] W. I. Grotsky and R. Jain. (1983). Optimal Quadtrees for Image Segments. IEEE Trans. PAMI, Vol.5, 77-83.




Article ID: 18008
DOI: 10.14419/ijet.v7i2.33.18008

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.