CoChat
Sign Up
Cited by 18Industrial Vision Systems and Defect DetectionNon-Destructive Testing TechniquesImage Retrieval and Classification Techniques

A Surface Inspection Machine Vision System that Includes Fractal Texture Analysis.

Open access
Blackledge, Jonathan·2009·Dublin Institute of Technology
DOI 10.21427/d7qs5j
Open this paper in CoChat — free accountOpen PDF

Abstract

The detection, recognition and classification of features in a digital image is an important component of quality control systems in production and process engineering and industrial systems monitoring, in general. In this paper, a new pattern recognition system is presented that has been designed for the specific task of monitoring the quality of sheet-steel production in a rolling mill. The system is based on using both the Euclidean and Fractal geometric properties of an imaged object to develop training data that is used in conjunction with a supervised learning procedure based on the application of a fuzzy inference engine. Thus, the classification method includes the application of a set of features which include fractal parameters such as the Lacunarity and Fractal Dimension and thereby incorporates the characterisation of an object in terms of texture that, in this application, has metallurgical significance.\nThe principal issues associated with object recognition are presented including a new segmentation algorithm. The selflearning procedure for designing a decision making engine using fuzzy logic and membership function theory is also presented and a new technique for the creation and extraction of information from a membership function considered.\nThe methods discussed, and the system developed, have a range of applications in ‘machine vision’ and automatic inspection. However, in this publication, we focus on the development and implementation of a surface inspection system designed specifically for monitoring surface quality in the manufacture of sheet-steel. For this publication, we include a demonstration version of the system which can be downloaded, installed and utilised by interested readers as discussed in Section VI.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

DataCite · 10.21427/d7qs5j

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • A Wiener filter has been used in a cold-rolled strip application with real-time suitability.

    “Interestingly, a Wiener filter, which requires processing in frequency domain with information on power spectrum of noise and un-degraded image, has been used in a cold-rolled strip application [76] with realtime suitability.”

    From Review of vision-based steel surface inspection systems (2014) · cites this paper as [76]

    The Background to the Case and Section V describe applying a Wiener filter to images of sheet-metal defects from a rolling-mill inspection system. But Section V specifies that the illustrated Wiener-filter application was performed off-line; its account of real-time data acquisition does not establish real-time suitability for the filter. The cited passages also do not specify that the strip was cold-rolled. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

  • First-order gradient filter followed by thresholding is more commonly used for edge localisation due to its noise immunity characteristics compared to Laplacian.

    “First-order gradient filter followed by thresholding is more commonly used for edge localisation [2,44,46,59,76] due to its noise immunity characteristics compared to Laplacian.”

    From Review of vision-based steel surface inspection systems (2014) · cites this paper as [76]

    In “Background to the Case” (page unavailable), the paper uses a Sobel edge detector to provide a rough location for defects, supporting the edge-localisation portion of the claim. Our copy does not say that gradient filtering is followed by thresholding, is more commonly used, or has better noise immunity than a Laplacian filter; searches for those terms found no such comparison. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

  • Spatial domain techniques are fast and easy to implement compared to wavelet-based methods, and they have been used in most papers where suitability for real-time operation has been reported.

    “Spatial domain techniques are fast and easy to implement compared to wavelet-based methods, and they have been used in most of the papers where suitability for real-time operation have also been reported [2,24,26,35,46,58,59,61,76].”

    From Review of vision-based steel surface inspection systems (2014) · cites this paper as [76]

    The “Speed of operation” section says this paper’s feature-based approach operates faster than existing schemes. The “Aditional Features” section discusses hardware requirements for a real-time system. Neither passage compares spatial-domain techniques with wavelet-based methods, says they are easier to implement, or establishes that most papers reporting real-time suitability used them; no page numbers are available in our copy. (LLM, conf=0.83)

    Experimental — accuracy not yet measured

  • Region growing has been employed, particularly after use of gradient operators, to identify RoIs.

    “Region growing has been employed [2,24,59,76], particularly after the use of gradient operators, to identify RoIs.”

    From Review of vision-based steel surface inspection systems (2014) · cites this paper as [76]

    Appendix I describes applying a Sobel edge detector before object-location and contour-tracing algorithms to locate defects and determine their boundaries. The Object Location Algorithm describes iterative, neighborhood-based pixel classification, but the copy does not identify that procedure as region growing; that specific method attribution is unsupported. (LLM, conf=0.81)

    Experimental — accuracy not yet measured

  • For detection of six types of defects in cold strip, [76] used a Wiener filter for noise reduction, then Sobel edge detector for rough locations, and finally a specially developed region growing method based on fuzzy logic object membership function of a pixel.

    “For detection of six types of defects in cold strip, [76] first used a Wiener filter for noise reduction. Then, rough locations of defects were extracted using Sobel edge detector. Finally, object locations were identified by a specially developed region growing method based on fuzzy logic object membership function of a pixel.”

    From Review of vision-based steel surface inspection systems (2014) · cites this paper as [76]

    The Introduction describes inspection of a moving steel strip, and Section V identifies six defect classes and says a Wiener filter removes noise before a Sobel detector locates defects. Section III(B), “Object Location Algorithm,” describes an iterative pixel-neighborhood method using fuzzy-logic membership functions, consistent with the claimed final step. Our copy does not specify that the strip was cold-rolled or call the method “region growing.” (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

No references could be resolved yet.

Research works printed but not linked: 27

  1. M. J. Turner, J. M. Blackledge and P. R. Andrews, Fractal Geometry in Digital Imaging, Academic Press, London, 1998.
  2. J. M. Blackledge, Digital Signal Processing, 2 nd Edition, Horwood Publishing, 2006.
  3. E. R. Davies, Machine Vision: Theory, Algorithms, Practicalities, Aca- demic press, London, 1997.
  4. H. Freeman, Machine vision. Algorithms, Architectures, and Systems, Academic press, London, 1988.
  5. W. E. Snyder and H. Qi, Machine Vision, Cambridge University Press, England, 2004.
  6. D. Marr, On the Theory of Edge Detection, Proceedings of the Royal Society, London, B 207: 127-217, 1980
  7. V. S. Nalwa and T. O. Binford, On Detecting Edges, IEEE Trans. Pattern Analysis and Machine Intelligence, PAMI-8, 699-714, 1986.
  8. V. B. Rao and H. V. Rao, C++ Neural Networks and Fuzzy Logic, MIS Press, 1993.
  9. N. K. Kasabov, Foundations of Neural Networks, Fuzzy Systems and Knowledge Engineering, MIT Press, 1996.
  10. J. M. Blackledge, On the Synthesis and Processing of Fractal Signal and Images, Applications of Fractals and Chaos, Springer, 81-100, 1993
  11. J. M. Blackledge and D. A. Dubovitskiy, Object Detection and Classification with Applications to Skin Cancer Screening, ISAST Transactions of Intelligent Systems, Vol 1, No 1, 34-45, 2008 - http://www.isastorganization.org/ISAST IS 2 2008.pdf
  12. H. M. Singer, I. Singer-Loginova, J. H. Bilgram and G. Amberg, Morphology Diagram of Thermal Dendritic Solidification by Means of Phase-fold Models in Two and Three Dimensions, Journal of Crystal Growth 296, 2006, 58-68.
  13. T. Mehran, A. D. C. Chan, A. Miri and R. M. Dansereau, Fractal Analy- sis of Surface Electromyography Signals: A Novel Power Spectrum- Based Method, Journal of Electromyography and Kinesiology, Elsevier, 2008 (accepted for publication: www.elsevier.com/locate/jelekin)
  14. D. Sanyal, P. Ramachandrarao and O. P. Gupta, A Fast Strategy for Simulation of Phase Change Phenomena at Multiple Length Scale, Computation Materials Science 37, 166-177, Elsevier, 2006.
  15. D. Sanyal, P. Ramachandrarao and O. P. Gupta, A Fractal Description of Transport Phenomena in Dendritic Porous Network, Chemical Engi- neering Science, 61, 307-315, Elsevier, 2006.
  16. M. F. Barnsley, R. L. Dalvaney, B. B. Mandelbrot, H. O. Peitgen, D. Saupe and R. F. Mandelbrot, The Science of Fractal Images, Springer, 1988.
  17. M. F. Barnsley, Fractals Everywhere, Academic Press, 1988.
  18. W. E. L. Grimson, Object Recognition by Computer: The Role of Geometric Constraints, MIT Press, 1990.
  19. B. D. Ripley, Pattern Recognition and Neural Networks, Academic Press, Oxford, 1996.
  20. R. B. Macy and A. S.Pandya, Pattern Recognition with Neural Networks in C++, IEEE Press, Florida Atlantic University, 1995.
  21. E. L. Hall, Computer Image Processing and Recognition, Academic press, London, 1979.
  22. C. T. Leondes, Image Processing and Pattern Recognition, Academic Press, London, 1998.
  23. T. Pavlidis, Algorithms for Graphics and Image Processing, Computer Science Press, USA, 1982.
  24. L. A. Zadeh, Fuzzy Sets and their Applications to Cognitive and Decision Processes, Academic Press, New York, 1975.
  25. N. Vadiee, Fuzzy Rule Based Expert System-I, Prentice Hall, Englewood, 1993.
  26. J. M. Blackledge, Diffusion and Fractional Diffusion based Mod- els for Multiple Light Scattering, ISAST Transactions on Elec- tronics and Signal Processing, Vol 1, No. 1, 38-60, 2007 - http://www.isastorganization.org/ISAST ES 1 2007.pdf
  27. J. M. Blackledge, Application of the Fractal Market Hypothesis for Macroeconomic Time Series Analysis, ISAST Transactions on Electronics and Signal Processing, Vol 1, No. 2, 56-80, 2008 - http://www.isastorganization.org/ISAST ES 2 2008.pdf

Cited by

Sorted by citations

Authors
Blackledge, J.
Corresponding author
Blackledge, Jonathan
ORCID
Blackledge, Jonathan
Venue
Dublin Institute of Technology
Publisher
Dublin Institute of Technology
Published
2009
DOI
10.21427/d7qs5j
OpenAlex
W1505935108
Cited by
18
References
0
Citations by year
2023: 1 · 2022: 2 · 2021: 1 · 2020: 1 · 2019: 2 · 2018: 1 · 2017: 4 · 2016: 2 · 2014: 2 · 2013: 1 · 2012: 1
FWCI
0.96
Type
journal article
Language
en
Open access
Locations
  • Arrow - TU Dublin (Technological University Dublin) (submittedVersion)
  • Arrow@dit (Dublin Institute of Technology) (submittedVersion, cc-by-nc-sa)
  • Arrow - TU Dublin (Technological University Dublin)
Topics
  • Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
  • Physical Sciences › Engineering › Mechanical Engineering › Non-Destructive Testing Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
Keywords
machine vision, surface inspection, fractal texture analysis, rolling mill, lacunarity, fractal dimension, fuzzy inference, membership functions, image segmentation, quality classification

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review