Detection of Surface Defects in Ceramic Tiles With Complex Texture

Huailiang Zhang,Sheng Yu,Ling Peng,Wei Qu

doi:10.1109/access.2021.3093090

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.

Highlights

Ceramic tiles are important building and decorative materials
Hanzaei et al extracted the characteristics of ceramic tile surface defects via a morphological operation using the rotation-invariant measure of a local variance operator and classified the defects using fuzzy recognition theory and a multiclass support vector machine (SVM) [8]
This study investigates complex-textured ceramic tiles that can result in false defect detection [25],[26]

Summary

INTRODUCTION

Ceramic tiles are important building and decorative materials. As the surface quality directly affects the appearance, performance, and service life of a tile, an accurate and efficient detection method for this property is crucial. Quan et al proposed a defect detection algorithm for ceramic tile surfaces based on local variance-weighted information entropy [10]. Casagrande et al proposed a feature extraction method comprising segmentation-based fractal texture analysis and discrete wavelet transform [11] This method accurately detects defects on single-color brick surfaces; its performance degrades in the case of textured tiles. Hocenski et al developed a set of machinevision-based detection systems for detecting defects on ceramic tile surfaces [12] Their method, programmed in C++, achieved good results on monochromatic tiles. Li et al proposed a surface detection algorithm for printing rollers based on visual saliency under complex surface conditions and high precision and high efficiency requirements [22] He et al developed a regression- and classification-based framework for generic industrial defect detection [23]. The evaluation results confirmed that in addition to improving the detection accuracy and reducing the false detection rate of defects in ceramic tile surfaces, the proposed method provides a theoretical reference for surface defect detection in related industries like steel, fabric and glass

IMAGE ACQUISITION AND PREPROCESSING

IMAGE PREPROCESSING

DEFECT DETECTION

EXPERIMENTAL RESULTS AND ANALYSIS

CONCLUSION