A Systematic Review on Deep Learning with CNNs Applied to Surface Defect Detection

Abstract

Surface defect detection with machine learning has become an important tool in industries and a large field of study for researchers or workers in recent years. It is necessary to have a simplified source of information that helps us to better focus on one type of surface. In this systematic review, we present a classification for surface defect detection based on convolutional neural networks (CNNs) focused on surface types. Findings: Out of 253 records identified, 59 primary studies were eligible. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we analyzed the structures of each study and the concepts related to defects and their types on surfaces. The presented review is mainly focused on finding a classification for the types of surfaces most used in industry (metal, building, ceramic, wood, and special). We delve into the specifics of each surface category, offering illustrative examples of their applications within both industrial and laboratory settings. Furthermore, we propose a new taxonomy of machine learning based on the obtained results and collected information. We summarized the studies and extracted the main characteristics such as type of surface, problem types, timeline, type of network, techniques, and datasets. Among the most relevant results of our analysis, we found that the metallic surface is the most used, as it is the one found in 62.71% of the studies, and the most prevalent problem type is classification, accounting for 49.15% of the total. Furthermore, we observe that transfer learning was employed in 83.05% of the studies, while data augmentation was utilized in 59.32%. Our findings also provide insights into the cameras most frequently employed, along with the strategies adopted to address illumination challenges present in certain articles and the approach to creating datasets for real-world applications. The main results presented in this review allow for a quick and efficient search of information for researchers and professionals interested in improving the results of their defect detection projects. Finally, we analyzed the trends that could open new fields of study for future research in the area of surface defect detection.

A Real-Time Automated Defect Detection System for Ceramic Pieces Manufacturing Process Based on Computer Vision with Deep Learning

“…Similar research on materials such as metal, concrete, wood, ceramics, and specialty surfaces exists and is detailed in our systematic review [ 5 ]. We identified common characteristics and challenges in these materials and applied them specifically to the ceramic context.…”

“…A systematic review process was used to carefully examine the objectives, methodology, results, and conclusions of each selected study. This approach facilitated a thorough and comparative assessment of the studies, culminating in our systematic review [ 5 ], which provides significant insight into current advances in surface defect detection.…”

“…These defects are mainly found on metal surfaces and can serve as a guide for further studies on materials or surfaces. The five most prevalent types of surfaces, categorized from our systematic analysis [ 5 ], are metal, building, wood, ceramic, and special surfaces. The industry has conducted the most studies on metal surfaces.…”

“…According to the literature reviewed by Prakash et al [ 4 ], CNNs demonstrate superiority in the quantity of existing articles, information extraction from images, and performance over traditional machine learning models such as Support Vector Machines (SVMs), Cellular Neural Networks, and various image processing algorithms. After conducting our systematic review [ 5 ], we found that CNNs are predominantly used to detect defects in metals but have also been shown to be effective on other materials such as wood, ceramics, and surfaces. Consequently, the use of CNNs for surface defect detection provides a stable foundation and serves as an ideal starting point for further research on new or less-studied surfaces, thereby opening up new research opportunities.…”

A Hybrid System for Defect Detection on Rail Lines through the Fusion of Object and Context Information

“…Concerning defect detection, the primary emphasis is on object detection, as defects are treated as entities requiring both localization and classification. Deep learning-based defect [ 15 ] detection algorithms prioritize data-driven feature extraction. By leveraging vast datasets, these algorithms extract deep features, offering distinct advantages over surface-level defect detection methods.…”