Surface Defect Detection: dataset & papers

🐎📈 Constantly summarizing open source data sets in the field of surface defect research is very important. Important critical papers from year 2017 have been collected and compiled, which can be viewed in the :open_file_folder: [Papers] folder. 🐋

https://pic3.zhimg.com/80/v2-f2f84bb695855bae7a0093cd9022f3c2_720w.jpg">

At present, surface defect equipment based on machine vision has widely replaced artificial visual inspection in various industrial fields, including 3C, automobiles, home appliances, machinery manufacturing, semiconductors and electronics, chemical, pharmaceutical, aerospace, light industry and other industries. Traditional surface defect detection methods based on machine vision often use conventional image processing algorithms or artificially designed features plus classifiers. Generally speaking, imaging schemes are usually designed by using the different properties of the inspected surface or defects. A reasonable imaging scheme helps to obtain images with uniform illumination and clearly reflect the surface defects of the object. In recent years, many defect detection methods based on deep learning have also been widely used in various industrial scenarios.

Compared with the clear classification, detection and segmentation tasks in computer vision, the requirements for defect detection are very general. In fact, its requirements can be divided into three different levels: "what is the defect" (classification), "where is the defect" (positioning) And "How many defects are" (split).

1. Key Issues in Surface Defect Detection

1）Small Sample Problem

The current deep learning methods are widely used in various computer vision tasks, and surface defect detection is generally regarded as its specific application in the industrial field. In traditional understanding, the reason why deep learning methods cannot be directly applied to surface defect detection is because in a real industrial environment, there are too few industrial defect samples that can be provided.

Compared with the more than 14 million sample data in the ImageNet dataset, the most critical problem faced in surface defect detection is small sample problem. In many real industrial scenarios, there are even only a few or dozens of defective images. In fact, for the small sample problem which is one of the key problems in industrial surface defect detection, there are currently 4 different solutions:

- Data Amplification and Generation

The most commonly used defect image expansion method is to use multiple image processing operations such as mirroring, rotation, translation, distortion, filtering, and contrast adjustment on the original defect samples to obtain more samples. Another more common method is data synthesis, where individual defects are often fused and superimposed on normal (non-defective) samples to form defective samples.

- Network Pre-training and Transfer Learning

Generally speaking, using small samples to train deep learning networks can easily lead to overfitting, so methods based on pre-training networks or transfer learning are currently one of the most commonly used methods for samples.

- Reasonable Network Structure Design

The need for samples can also be greatly reduced by designing a reasonable network structure. Based on the compressed sampling theorem to compress and expand small sample data, we use CNN to directly classify the compressed sampling data features. Compared with the original image input, compressing the input can greatly reduce the network's demand for samples. In addition, the surface defect detection method based on the twin network can also be regarded as a special network design, which can greatly reduce the sample requirement.

- Unsupervised or Semi-supervised Method

In the unsupervised model, only normal samples are used for training, so there is no need for defective samples. The semi-supervised method can use unlabeled samples to solve the network training problem in the case of small samples.

2）Real-time Problem

<...

Surface Defects Detection

## Overview

Surface Defects Detection is a dataset for object detection tasks - it contains Defects annotations for 1,799 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Metal Surface Defect

## Overview

Metal Surface Defect is a dataset for object detection tasks - it contains Scratches annotations for 238 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Steel Surface Defect

## Overview

Steel Surface Defect is a dataset for object detection tasks - it contains Burn annotations for 1,799 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Dataset

This dataset was created by Danielfi Nez

Contents

601 images of four types of aircraft fuselage defects. The camera was used to photograph different parts of the aircraft fuselage in different lighting environments.

Context

Surface defect inspection and detection within narrow, hollow cylindrical surfaces i.e., pipes and barrels can enormously impact the structural integrity of industrial products. Defect detection can play a major role in building inspection, finding minor defects to prolong the product's life.

Content

The dataset contains images of inside cylindrical surfaces. All images are in a single folder. The image folder contains 1,071 channel 3 images. The annotations for each image are recorded in seperate XML files. for five types of defects i.e., dirt, rusting, pitting, chipping, and thermal cracking.

The authors of the Severstal: Steel Defect Detection dataset acknowledge that steel holds a paramount position as one of the most vital building materials in modern construction. Its resilience against both natural elements and wear caused by human activities has rendered it indispensable worldwide. In the pursuit of enhancing the efficiency of steel production, the Severstal competition aims to play a pivotal role in the detection of defects within the steel production process.

Surface Defect Detection System Market Outlook

In 2023, the global surface defect detection system market size was valued at approximately USD 4.5 billion, and it is projected to reach USD 10.5 billion by 2032, with a robust CAGR of 9.5% from 2024 to 2032. The remarkable growth of this market can be attributed to the increasing demand for quality assurance and automation in manufacturing processes. The growing integration of advanced technologies such as Machine Vision and Artificial Intelligence (AI) for defect detection is significantly propelling market growth.

One of the primary growth factors for the surface defect detection system market is the booming manufacturing and industrial sectors. As industries strive for higher reliability and quality in their products, the need for advanced defect detection technologies becomes paramount. The automation of quality control processes enabled by surface defect detection systems not only enhances efficiency but also reduces human error, leading to significantly improved product quality and consistency. This high demand for quality assurance drives the adoption of such systems across various sectors, thereby fueling market growth.

Furthermore, technological advancements in AI and Deep Learning are revolutionizing the surface defect detection system market. These technologies enable more accurate and faster detection of defects by analyzing vast amounts of data and identifying patterns that are not easily discernible by human inspection. The integration of AI with machine vision systems enhances their capability to detect even the most subtle and complex defects, thereby increasing their utility across diverse applications. As a result, industries are increasingly investing in these advanced systems to stay competitive and ensure product excellence.

The increasing stringency of regulatory standards related to product quality and safety also plays a crucial role in the market's expansion. Regulatory bodies across various regions are imposing stricter guidelines to ensure that products meet high-quality standards and are free from defects. Compliance with these regulations necessitates the adoption of surface defect detection systems, as they provide reliable and precise inspection capabilities. This regulatory push further accentuates the importance of these systems in maintaining product integrity and consumer safety, thereby contributing to market growth.

Regionally, the Asia Pacific region is expected to witness the highest growth rate during the forecast period. The rapid industrialization, particularly in countries like China and India, coupled with the increasing adoption of automation in manufacturing processes, is driving the demand for surface defect detection systems in the region. North America and Europe also hold significant market shares due to the presence of advanced manufacturing facilities and stringent quality standards in these regions. These regional dynamics highlight the diverse opportunities and growth potential across different geographical areas.

Component Analysis

The surface defect detection system market is segmented into three primary components: Hardware, Software, and Services. The hardware segment includes cameras, sensors, and other detection devices that are crucial for capturing images and data necessary for defect detection. The software segment comprises the algorithms and applications that analyze the captured data to identify defects. Services include installation, maintenance, and after-sales support provided by vendors to ensure the efficient operation of the systems.

The hardware segment dominates the market due to the extensive use of high-resolution cameras and advanced sensors in defect detection systems. These components are essential for capturing detailed images and data that are analyzed to detect surface defects. Technological advancements in hardware, such as the development of high-speed cameras and 3D sensors, are further enhancing the capabilities of defect detection systems. The continuous innovation in hardware components is expected to drive their demand, thereby contributing significantly to the market's growth.

The software segment is also experiencing substantial growth, driven by the integration of AI and machine learning algorithms in defect detection systems. These advanced software solutions enable more accurate and efficient defect detection by analyzing data and identifying patterns that are not easily detectable by traditional methods. The increasing adoption of cloud-based software solutions is further

malleable cast iron surface defect dataset(MCISD)

In automated surface visual inspection, it is often necessary to capture the inspected part under many different illumination conditions to capture all the defects. To address this issue, at CSEM we have acquired a real-world multi-illumination defect segmentation dataset, called CSEM-MISD and we release it for research purposes to benefit the community.

The dataset consists of three different types of metallic parts -- washers, screws, and gears (temporarily only the first one is available). Parts were captured in a half-spherical light-dome system that filtered out all the ambient light and successively illuminated it from 108 distinct illumination angles. Each 12 illumination angles share the same elevation level and the relative azimuthal difference between the adjacent illumination angles on the same level is 30 degrees. For more details, please read Sections 3 and 4 of our paper.

The washers dataset features 70 defective parts. Some defects, such as notches and holes, are visible in most images (illuminations) with intensity and texture variations among them, while others, such as scratches, are only visible in a few.

We split the datasets into train and test sets. The train sets contain 32 samples, and the test set 38 samples. Each sample comprises 108 images (each captured under a different illumination angle), an automatically extracted foreground segmentation mask, and a hand-labeled defect segmentation mask.

This dataset is challenging mainly because:

• each raw sample consists of 108 gray-scale images of resolution 512×512 and therefore takes 27MB of space;
• the metallic surfaces produce many specular reflections that sometimes saturate the camera sensors;
• the annotations are not very precise because the exact extent of defect contours is always subjective;
• the defects are very sparse also in the spatial dimensions: they cover only about 1.4% of the total image area in washers; this creates an unbalanced dataset with a highly skewed class representation.

The dataset is organized as follows:

• each sample resides in the Test, Train, or Unannotated directory;
• each sample has its own directory which contains the individual images, the foreground, and defect segmentation masks;
• each image is stored in 8-bit greyscale png format and has a resolution of 512 x 512 pixels;
• Image file names are formatted using three string fields separated with the underscore character: prefix_sampleNr_illuminationNr.png, where the prefix is e.g. washer, the sampleNr might be a three-digit number 001, and the illuminationNr is formed of 3 digits, first corresponding to the elevation index (1 - highest angle, 9 - lowest angle), and the additional two corresponding to the azimuth index (01-12).
• Each dataset contains light_vectors.csv, which contains the illumination angles (in lexicographic order of the illuminationNr), and light_currents.csv that contains the numbers roughly corresponding to the light intensity.

We provide data loaders implemented in python at the project's repository.

If you find our dataset useful, please cite our paper:

Honzátko, D., Türetken, E., Bigdeli, S. A., Dunbar, L. A., & Fua, P. (2021). Defect segmentation for multi-illumination quality control systems. Machine vision and Applications.

Panel Surface Defect Detection

## Overview

Panel Surface Defect Detection is a dataset for object detection tasks - it contains Letters annotations for 2,528 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

NG samples are regarded as positive samples

The global surface defect detection system market, valued at $1181 million in 2025, is projected to experience robust growth, driven by increasing automation in manufacturing, stringent quality control standards across diverse industries, and the rising adoption of advanced imaging techniques like AI-powered vision systems. The 7.6% CAGR from 2019 to 2033 indicates a significant expansion, with the market expected to surpass $2000 million by 2033. Key drivers include the need for enhanced product quality, reduced production costs through early defect detection, and the growing demand for non-destructive testing methods. The market's segmentation likely includes technologies (e.g., machine vision, laser scanning, X-ray inspection), industry verticals (e.g., automotive, electronics, pharmaceuticals), and deployment types (e.g., inline, offline). Competitive pressures are expected to remain high due to the presence of numerous established players and emerging technology providers. Growth is being fueled by several factors. Advancements in machine learning and artificial intelligence are enabling more accurate and efficient defect detection, leading to improved productivity and lower scrap rates. Furthermore, the integration of surface defect detection systems into Industry 4.0 initiatives is accelerating adoption, particularly among large-scale manufacturers seeking greater process optimization and real-time data analysis. However, the market might face certain restraints such as high initial investment costs associated with advanced systems and the need for specialized technical expertise for implementation and maintenance. Nevertheless, the long-term benefits in terms of quality improvement, cost reduction, and enhanced operational efficiency are expected to outweigh these challenges, ensuring continued market expansion throughout the forecast period.

In the development of surface defect detection algorithms for steel, benchmark datasets play a crucial role. However, the widely used benchmark datasets generally suffer from limited scale, insufficient coverage of defect categories, and poor annotation accuracy, making it difficult to meet the growing demand for surface defect detection in steel. To this end, this study constructed and annotated a large-scale, multi-scale benchmark dataset SD10 (Steel Defect Detection) covering 10 typical types of defects: Crazing, Inclusion, Patches, Pitted Surface, Rolled in Scale, Scratches, Blowhole, Break, Fray, and Uneven. The dataset aims to break through the application bottleneck of existing datasets, provide high-quality and reliable data support for in-depth research and optimization iteration of steel surface defect detection algorithms.

Solar cells are playing a significant role in aerospace equipment. In view of the surface defect characteristics in the manufacturing process of solar cells, the common surface defects are divided into three categories, which include difficult-detecting defects (mismatch), general defects (bubble, glass-crack and cell-crack) and easy-detecting defects (glass-upside-down). Corresponding to different types of defects, the deep learning model with different optimization methods and a classification detection method based on multi-models fusion are proposed in the paper. In the proposed model, in order to solve the mismatch problem between the default anchor boxes size of YOLOv5s model and the extreme scale of the battery mismatch defect label boxes, the K-means algorithm was adopted to re-cluster the dedicated anchor boxes for the mismatch defect label boxes. In order to improve the comprehensive detection accuracy of YOLOv5s model for the general defects, the YOLOv5s model was also improved by the methods of image preprocessing, anchor box improving and detection head replacing. In order to ensure the recognition accuracy and improve the detection speed for easy-detecting defects, the lightweight classification network MobileNetV2 was also used to classify the cells with glass-upside-down defects. The experimental results show that the proposed optimization model and classification detection method can significantly improve the defect detection precision. Respectively, the detection precision for mismatch, bubble, glass-crack and cell-crack defects are up to 95.64%, 91.8%, 93.1% and 98.0%. By using lightweight model to train the glass-upside-down defect dataset, the average classification accuracy reaches 100% and the detection speed reaches 13.29 frames per second. The comparison experiments show that the proposed model has a great improvement in detection accuracy compared with the original model, and the defect detection speed of lightweight classification network is improved more obviously, which confirms the effectiveness of the proposed optimization model and the multi-defect classification detection method for solar cells defect detection.

The global surface defect detection system market is experiencing robust growth, projected to reach $1867 million in 2025 and maintain a Compound Annual Growth Rate (CAGR) of 7.4% from 2025 to 2033. This expansion is driven by several key factors. Increasing demand for higher quality control in various manufacturing sectors, particularly electronics, automotive, and pharmaceuticals, necessitates advanced defect detection technologies. The rising adoption of automation and Industry 4.0 initiatives further fuels market growth, as automated inspection systems enhance efficiency and reduce human error. Advancements in image processing, artificial intelligence (AI), and machine learning (ML) are enabling more sophisticated and accurate defect detection, leading to improved product quality and reduced waste. Furthermore, the increasing prevalence of stringent quality standards and regulations across industries is pushing manufacturers to adopt advanced surface defect detection systems. The competitive landscape is characterized by a mix of established players like AMETEK, Nordson, and ZEISS, and emerging technology providers, fostering innovation and driving down costs. The market segmentation, though not explicitly provided, is likely diverse, encompassing various technologies (e.g., machine vision, optical inspection, X-ray inspection), application types (e.g., metal, plastic, semiconductor), and industry verticals. Future growth will be shaped by ongoing technological innovation, including the integration of advanced analytics and cloud-based solutions for data analysis and remote monitoring. Challenges remain, however, including the high initial investment cost of sophisticated systems and the need for skilled personnel to operate and maintain them. Nonetheless, the long-term growth prospects for the surface defect detection system market remain positive, driven by the unrelenting demand for enhanced product quality and efficiency across a broad range of manufacturing sectors.

The global surface defect detection system market is experiencing robust growth, projected to reach a market size of $1723 million in 2025, exhibiting a Compound Annual Growth Rate (CAGR) of 7.9% from 2019 to 2033. This expansion is driven by several key factors. Increasing automation across various industries, particularly in manufacturing (automotive, semiconductors, and electronics), necessitates precise and efficient quality control. The demand for higher-quality products with reduced defects is a significant driver, pushing companies to adopt advanced surface defect detection systems. Furthermore, technological advancements in image processing and non-destructive testing (NDT) techniques are enabling the development of more accurate, faster, and cost-effective solutions. The integration of AI and machine learning algorithms further enhances the capabilities of these systems, leading to improved defect identification and classification. Growing adoption of Industry 4.0 principles and the increasing need for real-time monitoring and analysis are further propelling market growth. Market segmentation reveals a strong presence across diverse applications, with the automotive, semiconductor, and electronics sectors showing significant demand. Based on technology, image processing-based systems currently dominate the market due to their versatility and accuracy, although NDT methods are gaining traction owing to their suitability for specific applications. Geographically, North America and Europe are currently leading the market, driven by early adoption of advanced technologies and stringent quality standards. However, rapid industrialization and economic growth in Asia-Pacific are expected to fuel significant market expansion in this region in the coming years, presenting lucrative opportunities for market players. The presence of established players like AMETEK, Nordson, and others, coupled with the emergence of innovative startups, indicates a competitive yet dynamic market landscape. Challenges remain, including high initial investment costs and the need for skilled personnel to operate and maintain these sophisticated systems. However, ongoing technological innovation and increasing affordability are expected to mitigate these challenges in the long term.

This dataset provides synthetic samples of surface defects generated on a CAD model of a car door. The defects include bumps and peaks, simulated using Free-Form Deformation (FFD) to ensure geometric realism and adaptability to curved surfaces. Surface acquisition is emulated using a virtual 3D profilometric sensor, incorporating both geometric and sensor noise to closely replicate real-world inspection conditions.

All samples are labeled, and the dataset includes depth images, trajectory data, and raw sensor outputs, making it suitable for training and evaluating surface defect detection models in industrial settings.

This dataset is associated with the TriPlay repository on GitHub:🔗 GitHub Repository

It is also related with the following publication:

📄 Simulation of Laser Profilometer Measurements in the Presence of Speckle Using Perlin Noise

(This dataset is also associated with a manuscript currently under review.)

🔑 Key Features

High-Quality Synthetic Defects: Includes localized surface deformations (bumps and peaks) modeled with Free-Form Deformation.

Virtual Profilometric Scanning: Simulates data acquisition with a 3D profilometer to capture realistic sensor readings.

Realistic Sensor Noise: Adds surface and depth distortion to simulate real acquisition conditions.

Per-Step Trajectory and Sensor Data: Includes detailed trajectory files and raw outputs per scanning step.

Automatically Generated Annotations: Bounding boxes and defect metadata are included for supervised learning.

Wood Surface Defect Dataset

## Overview

Wood Surface Defect Dataset is a dataset for object detection tasks - it contains Wood annotations for 288 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).