Segmentation-based deep-learning approach for surface-defect detection

By Domen Tabernik, Samo Sela, Jure Skvarc, Danijel Skocaj. Journal of Intelligent Manufacturing, 2019

909 citations recorded by the source corpus.

Automated surface-anomaly detection using machine learning has become an interesting and promising area of research, with a very high and direct impact on the application domain of visual inspection. Deep-learning methods have become the most suitable approaches for this task. They allow the inspection system to learn to detect the surface anomaly by simply showing it a number of exemplar images. This paper presents a segmentation-based deep-learning architecture that is designed for the detection and segmentation of surface anomalies and is demonstrated on a specific domain of surface-crack detection. The design of the architecture enables the model to be trained using a small number of samples, which is an important requirement for practical applications. The proposed model is compared with the related deep-learning methods, including the state-of-the-art commercial software, showing that the proposed approach outperforms the related methods on the specific domain of surface-crack detection. The large number of experiments also shed light on the required precision of the annotation, the number of required training samples and on the required computational cost. Experiments are performed on a newly created dataset based on a real-world quality control case and demonstrates that the proposed approach is able to learn on a small number of defected surfaces, using only approximately 25–30 defective training samples, instead of hundreds or thousands, which is usually the case in deep-learning applications. This makes the deep-learning method practical for use in industry where the number of available defective samples is limited. The dataset is also made publicly available to encourage the development and evaluation of new methods for surface-defect detection.

Subfields: Biomedical Engineering, Computational Mechanics, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/b77b1fc188f3834541efbb75add8f1ea80fd6225

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Ling Shao
2. Deng-Ping Fan
3. Ming-Ming Cheng
4. Ge-Peng Ji
5. Liang Wang

In Computational Mechanics

1. Ling Shao
2. Deng-Ping Fan
3. Ming-Ming Cheng
4. Ge-Peng Ji

In Industrial and Manufacturing Engineering

1. Danijel Skocaj
2. Ming-Ming Cheng

Citations in the corpus

• Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning (2021, background): “Several studies have emphasized the necessity for more complex data-sets [13,57,58].”
• AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection (2023, neutral): “(Jezek et al., 2021), BTAD (Mishra et al., 2021), SDD (Tabernik et al., 2020), DAGM (Wieler & Hahn, 2007), and DTD-Synthetic (Aota et al., 2023).”
• Concealed Object Detection (2021, background): “In contrast, artificial camouflage is usually used in art design/gaming to hide information, occurs in products during the manufacturing process (so-called surface defects [42], defect detection [43], [44]), or appears in our daily life (e.”
• Surface Defect Detection Methods for Industrial Products: A Review (2021, background): “com/competition/entrance/231682/information (accessed on 21 June 2021) Kolektor [112] Electronic commutator https://www.”
• Mixed supervision for surface-defect detection: from weakly to fully supervised learning (2021, methodology): “KolektorSDD The KolektorSDD [35] dataset contains grayscale images of a real-world production item; many of them contain visible surface cracks.”