Journal of Engineering and Applied Sciences
ISSN: Online 1818-7803ISSN: Print 1816-949x
Abstract
In industrial field, the automated visual inspection systems is applied effectively to identify the defects in various digital images. In this research work researchers have proposed a new defect detection algorithm based on local homogeneity and Discrete Cosine Transform (DCT) to eliminate the texture elements in the digital image by isolating the defected area. Firstly, the local homogeneity of each pixel is computed to construct a new Homogeneity image denoted as (H-image). Then a DCT transform in order to extract features energy is applied. After these energy are integrated by the Hotelling’s T2 statistic and the defect blocks can be determined by the multivariate statistical method. Finally, a simple thresholding method is applied to set a threshold for distinguishing between defective areas and uniform regions. Simulations on different textured images show good promising results. This new automatic defect detection method shows good performance in comparison with other existing algorithms.
How to cite this article:
Farhat Fnaeich, Sabeur Abid and Ali Rebhi. Defect Detection Algorithm for Gray Level Digital Images Using Local Homogeneity
and Discrete Cosine Transform.
DOI: https://doi.org/10.36478/jeasci.2014.43.49
URL: https://www.makhillpublications.co/view-article/1816-949x/jeasci.2014.43.49