Open Access Open Access  Restricted Access Subscription or Fee Access

Surface and Corner Defect Detection on Tile Images Using Gabor Features, Level Set Segmentation and Dot Product

F.S. Najafabadi, H. Pourghassem

Abstract


Quality inspection is one of the most important problems in industry. Digital image processing techniques are used, in order to be able to detect defects by using advanced systems and to prevent human faults during product categorization process based on quality. In this paper, an automatic surface and corner defect detection algorithm using Gabor feature, level set segmentation and dot product are proposed in tile images. This algorithm detects two groups of defects, surface defects such as pinhole, bulb, spot, crack, and chip corner defect, produced during the tile production process. In this algorithm, after pre-processing stage on images by using selective binary and Gaussian filtering regularized level set (SBGFRLS) method, the tile's image are segmented from its background with the lowest error rate and time and then filtering is used for analyzing random texture surface by a novel way of Gabor filters. At last the desired defect is detected by using a sensitive threshold to changes. The proposed algorithm is evaluated on a perfect set of tile images. The obtained results show effectiveness of our proposed algorithm in real and operational conditions.

Keywords


Surface and corner defect detection, tile image, Gabor filter, active contour.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.