Detection of Surface Defects in Ceramic Tiles With Complex Texture

Abstract

To solve the problem of false defect detection owing to the interference of the texture attribute of ceramic tiles, a method for detecting surface defects in complex-textured ceramic tiles is proposed. Based on the visual detection principle of ceramic tile surfaces, an image acquisition system is established to obtain the ceramic tile image. After image segmentation and correction, the surface defects are preliminarily detected using a saliency detection method. Then, the image sub-block containing the defect area is cut out for secondary detection. The false defects are eliminated, and the final detection of the ceramic tile surface defects is completed using the defect determination method. The feasibility and effectiveness of the defect detection method are studied via comparative experiments. Experimental results show that the maximum accuracy rate of the proposed defect detection method is 98.75%, which satisfies the actual detection requirements and confirms the practical significance of the proposed method.INDEX TERMS Complex-textured ceramic tiles, defect determination, image acquisition, image sub-block, saliency detection HUAILIANG ZHANG received his Ph.D.

Deep LBP-Enriched Real-time Segmentation for Hair Defect Detection

“…This method can efficiently detect defects with special designed rules in the scope of search. Zhan et al [10] proposed the distribution variance of color space and the color area-spot weight feature to get the defect significance map, which has been successfully applied to detect surface defects of complex texture ceramic tiles. On the basis of the Local Binary Pattern (LBP), Li et al [11] proposed a texture description model for birch board crack.…”

Surface Defect Detection in Sanitary Ceramics Based on Lightweight Object Detection Network

“…The method achieves 8% missed detection rate in test data by performing object matching in a multi-level image pyramid. Zhang et al [2] proposed a surface defect detection method for complex texture ceramic tiles based on traditional image processing methods, using canny edge detection and defect saliency detection, and support vector machines for defect classification. Chen et al [3] proposed a ceramic decals defect detection method also based on traditional image processing methods.…”

A method for multi-view surface defect detection of Si3N4 ceramic bearing balls integrating features enhanced by the Gabor salient domain

“…Guo et al [9] performed edge detection of ceramic bowl surface defects by combining the Kirsch operator with the Canny operator. Zhang et al [10] in order to solve the problem of ceramic bearing ball blurring and missing edge information and missing edge information in captured images, an improved single scale retinex algorithm is used to enhance the image and suppress the redundant information in the image. In the problem of texture processing and feature information blurring, the methods commonly used by researchers are Roberts algorithm, Canny algorithm, Laplace algorithm.…”