An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured Surfaces

Automated defect inspection has long been a challenging task especially in industrial applications, where collecting and labeling large amounts of defective samples are usually harsh and impracticable. In this paper, we propose an approach to detect and localize defects with only defect-free samples for model training. This approach is carried out by reconstructing image patches with convolutional denoising autoencoder networks at different Gaussian pyramid levels, and synthesizing detection results from these different resolution channels. Reconstruction residuals of the training patches are used as the indicator for direct pixelwise defect prediction, and the reconstruction residual map generated in each channel is combined to generate the final inspection result. This novel method has two prominent characteristics, which benefit the implementation of automatic defect inspection in practice. First, it is absolutely unsupervised that no human intervention is needed throughout the inspection process. Second, multimodal strategy is utilized in this method to synthesize results from multiple pyramid levels. This strategy is capable of improving the robustness and accuracy of the method. To evaluate this approach, experiments on convergence, noise immunity, and defect inspection accuracy are conducted. Furthermore, comparative tests with some excellent algorithms on actual and simulated data sets are performed. Experimental results demonstrated the effectiveness and superiority of the proposed method on homogeneous and nonregular textured surfaces.

I. Introduction

Textured surface inspection aims to identify regions that exhibit dissimilar properties with defect-free areas according to certain criteria such as texture patterns or structures. It commonly occurs in many industrial applications, such as textile inspection [1], wood inspection [2], and ceramic tile inspection [3]. Surface defects are generally inspected by experienced inspectors traditionally. Similar manual approaches are usually time consuming and highly subjective. Therefore, they are still insufficient to meet the needs of modern industrial production. Automated optical inspection uses machine vision techniques for industrial defect inspection and has drawn much attention in recent years, especially for textured surface inspection [4]–[6].