# Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning

arXiv: https://arxiv.org/abs/1808.02518 · HTML: https://mlsanity.com/paper/1808.02518/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2018.

## Built on by (most cited first, 16 of 16)

- [Deep Industrial Image Anomaly Detection: A Survey](https://mlsanity.com/paper/2301.11514/) (2023)
- [PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection](https://mlsanity.com/paper/2310.07716/) (2023)
- [Computer Vision on X-ray Data in Industrial Production and Security Applications: A Comprehensive Survey](https://mlsanity.com/paper/2211.05565/) (2022)
- [Automatic Volumetric Segmentation of Additive Manufacturing Defects with 3D U-Net](https://mlsanity.com/paper/2101.08993/) (2021)
- [Enhancing Glass Defect Detection with Diffusion Models: Addressing Imbalanced Datasets in Manufacturing Quality Control](https://mlsanity.com/paper/2505.03134/) (2025)
- [A Survey of Surface Defect Detection of Industrial Products Based on A Small Number of Labeled Data](https://mlsanity.com/paper/2203.05733/) (2022)
- [Alternative Data Augmentation for Industrial Monitoring using Adversarial Learning](https://mlsanity.com/paper/2205.04222/) (2022)
- [Automated Defect Recognition of Castings defects using Neural Networks](https://mlsanity.com/paper/2209.02279/) (2022)
- [The SAM2-to-SAM3 Gap in the Segment Anything Model Family: Why Prompt-Based Expertise Fails in Concept-Driven Image Segmentation](https://mlsanity.com/paper/2512.06032/) (2025)
- [A Dynamic Time Warping-Transfer Learning Approach to Transferring Knowledge in Stress-strain Behaviors from Polymers to Metals: An Affordable and Generalizable Additive Manufacturing Part Qualification Framework](https://mlsanity.com/paper/2512.08699/) (2025)
- [Defect detection and segmentation in X-Ray images of magnesium alloy castings using the Detectron2 framework](https://mlsanity.com/paper/2202.13945/) (2022)
- [Few-shot incremental learning in the context of solar cell quality inspection](https://mlsanity.com/paper/2207.00693/) (2022)
- [ContextMix: A context-aware data augmentation method for industrial visual inspection systems](https://mlsanity.com/paper/2401.10050/) (2024)
- [Deep Learning Strategies for Industrial Surface Defect Detection Systems](https://mlsanity.com/paper/2109.11304/) (2021)
- [CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community](https://mlsanity.com/paper/2407.06485/) (2024)
- [DART: A Vision-Language Foundation Model for Comprehensive Rope Condition Monitoring](https://mlsanity.com/paper/2605.04943/) (2026)

## Abstract (arXiv)

Quality control is a fundamental component of many manufacturing processes, especially those involving casting or welding. However, manual quality control procedures are often time-consuming and error-prone. In order to meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. Recently, Convolutional Neural Networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this article, a system is proposed for the identification of casting defects in X-ray images, based on the Mask Region-based CNN architecture. The proposed defect detection system simultaneously performs defect detection and segmentation on input images, making it suitable for a range of defect detection tasks. It is shown that training the network to simultaneously perform defect detection and defect instance segmentation, results in a higher defect detection accuracy than training on defect detection alone. Transfer learning is leveraged to reduce the training data demands and increase the prediction accuracy of the trained model. More specifically, the model is first trained with two large openly-available image datasets before finetuning on a relatively small metal casting X-ray dataset. The accuracy of the trained model exceeds state-of-the art performance on the GRIMA database of X-ray images (GDXray) Castings dataset and is fast enough to be used in a production setting. The system also performs well on the GDXray Welds dataset. A number of in-depth studies are conducted to explore how transfer learning, multi-task learning, and multi-class learning influence the performance of the trained system.