Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials

Abstract

The computer-vision-based surface defect detection of metal planar materials is a research hotspot in the field of metallurgical industry. The high standard of planar surface quality in the metal manufacturing industry requires that the performance of an automated visual inspection system and its algorithms are constantly improved. This paper attempts to present a comprehensive survey on both two-dimensional and three-dimensional surface defect detection technologies based on reviewing over 160 publications for some typical metal planar material products of steel, aluminum, copper plates and strips. According to the algorithm properties as well as the image features, the existing two-dimensional methodologies are categorized into four groups: statistical, spectral, model, and machine learning-based methods. On the basis of three-dimensional data acquisition, the three-dimensional technologies are divided into stereoscopic vision, photometric stereo, laser scanner, and structured light measurement methods. These classical algorithms and emerging methods are introduced, analyzed, and compared in this review. Finally, the remaining challenges and future research trends of visual defect detection are discussed and forecasted at an abstract level.

Photometric Stereo-Based Defect Detection System for Steel Components Manufacturing Using a Deep Segmentation Network

“…However, the best approach for obtaining useful images of specular surfaces is to have a reliable acquisition system that avoids surface reflections. Photometric stereo systems have been very suitable for acquiring these kind of images [13,14]. This technique estimates the object surface normals by imaging it under different lighting conditions [15].…”

A Survey on Unsupervised Industrial Anomaly Detection Algorithms

“…Some studies focus only on anomaly detection on a particular material. A thorough survey [1] is provided of both two-dimensional and three-dimensional surface defect detection systems for various common metal planar material products such as steel, aluminum, copper plates, and strips. The review [79] presents a detailed overview of histogram-based approaches, color-based approaches, image segmentation-based approaches, frequency domain operations, texturebased defect detection, sparse feature based operations, image morphology operations for fabric defect detection.…”

“…This transparent and efficient information-based production process can minimize production costs and also avoid wasting raw materials. In the long run, smart manufacturing mode based on artificial intelligence technology [1] can reduce the requirements on human quality, such as dependence on technical experts and other special talents, by mining and depositing relevant knowledge, so that the original labor force can be saved, thus reducing the dependence on human quality.…”

“…Material anomaly extensively exists in industrial production [1][2][3], and more and more safety problems are caused by material defects. Hence people pay more attention to the identification and detection of material anomaly.…”

Damage Identification on Impact and Lightning Damage of Flax Composite Laminates (Linum usitatissimum) Using Long-Pulse Thermography of a Low-Resolution Infrared Camera

“…The analyses have been used for the classification of the material defect and to detect the defect on the material surface (Fang et al, 2020). For detection of the defect, it can be divided into true positive (TP) where it shows that the actual defect is detected as a defect; true negative (TN) where the actual defect is wrongly detected as noise or background; false positive (FP) where the actual noise is wrongly detected as a defect; and false negative (FN) where the actual noise is detected as noise.…”