Defect Detection on Texture using Statistical Approach
Abstract
In this paper we present several techniques for detecting simple defect on the texture. The simple defect means, that the defect can be detected via image histogram or via wavelet of the image histogram. Hill estimator is one of the techniques that we suggest to use to solve this problem, since it does not need estimate parameters for estimating the image densityMetrics
References
.Haindl, M., Texture Synthesis, CWI Quaterly,1991,pp. 305-331.
.Cavalin, P., Oliveira, L. S., Koerich, A. L., and Britto Jr, A.S., Wood Defect Detection using Grayscale Images and an Optimized Feature Set. IEEE Industrial Electronics, IECON 2006 -32nd Annual conferenceProceeding, Paris 2006.
.Wand, M.P and Jones, M.C; Kernel Smoothing, Chapman & Hall, 1995.New Jersey: Pearson Prentice Hall. 2005
.Moahseri, B. B. M, Azadinia, S. and Mehbodniya, A New Voting Approach to Texture Defect Detection Based on Multiresolutional Decomposition, World Academy of Science, Engineering and Technology, 65, 2010, pp. 887-891.
Timm, F. and Barth, E., Non-parametric Texture Defect Detection using Weibull Features. Image Processing: Machine Vision Applications IV, 7877, Proceeding of SPIE. SPIE-IS& T. San Francisco, USA 2011.
Franke, J., and Halim, S., Wild Bootstrap Tests: Regression Models for Comparing Signal and Images, IEEE Signal Processing Magazine, July 2007, pp. 31-37
Franke, J., and Halim, S., A Bootstrap Test for Comparing Images in Surface Inspection, presented at DFG-Priority Program 1114 Technical Report 150.
Nason, G.P., Wavelet Methods in Statistics, Springer, New York, 2008
Wand, M.P and Jones, M.C; Kernel Smoothing, Chapman & Hall, 1995
Otsu, N., A Threshold Selection Method from Gray-Level Histogram. IEEE Transaction on System Man Cybernet, SMC-9(1), 1979,pp.62-66
Hill, B. M., A Simple General Approach to Inference about the Tail of Distribution. Annals of Statistics, 3, 1975, pp. 1063-1174.
Ng Hui Fang, Automatic Thresholding for defect detection, Pattern Recog¬nition Letters, 27(14), 2006,pp.1644-1649.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Â