Logo

Defect Detection on Texture using Statistical Approach

Halim, Siana (2015) Defect Detection on Texture using Statistical Approach. Jurnal Teknik Industri, 17 (2). pp. 89-96. ISSN 1411-2485

[img] PDF
Download (843Kb)
    [img]
    Preview
    PDF (cek plagiasi)
    Download (650Kb) | Preview
      [img]
      Preview
      PDF (peerreview)
      Download (640Kb) | Preview

        Abstract

        In this paper we present several techniques for detecting a simple defect on the texture. The simple defect is the defect that can be detected directly via image histogram or via image histogram of the transformed original image in the wavelet space. In this proposed methods we used kernel density estimate instead of histogram for presenting the distribution of the image gray levels. The simple defects can be detected as the area in the tail of the image gray level distribution. Therefore a threshold in the left or right (or both) side(s) of the gray level distribution is needed. This threshold will indicate the defect area to the non defect area in the image distribution. In this paper, we used three techniques to determine the threshold poin. The first one, we used the concept of significance level in statistical hypotheses, we assume that the probability of the defect gray level lies in that level, e.g. alpha = 5%, the threshold poin in this approach is the poin in the gray level (x-axis of the distribution) that makes the propobability of the gray level equal to alpha. The second approach, we used the modified Otsu method, and the last one we use the Hill estimator. These approaches will produce a rectilinear which cover the defect area. The smallest the rectilinear can detect the defected area the better the performance of the proposed method. In this way of measurement, Hill estimator performs better than the other two proposed methods.

        Item Type: Article
        Uncontrolled Keywords: Hill estimator, kernel density estimate, image histogram, wavelet, texture, defect.
        Subjects: H Social Sciences > HA Statistics
        Divisions: Faculty of Industrial Technology > Industrial Engineering Department
        Depositing User: Admin
        Date Deposited: 09 Jan 2016 16:00
        Last Modified: 16 Jan 2019 10:12
        URI: https://repository.petra.ac.id/id/eprint/17231

        Actions (login required)

        View Item