Context

The Open Lab on Human Robot Interaction of Peking University has released the PCB defect dataset. 6 types of defects are made by photoshop, a graphics editor published by Adobe Systems. The defects defined in the dataset are: missing hole, mouse bite, open circuit, short, spur, and spurious copper

Content

This is a public synthetic PCB dataset containing 1386 images with 6 kinds of defetcs (missing hole, mouse bite, open circuit, short, spur, spurious copper) for the use of detection, classification and registration tasks.

Acknowledgements

PCB dataset was downloaded using public link from https://github.com/Ixiaohuihuihui/Tiny-Defect-Detection-for-PCB

Authors of dataset: Huang, Weibo, and Peng Wei. "A PCB dataset for defects detection and classification." arXiv preprint arXiv:1901.08204 (2019).

Original Credit: https://github.com/Ironbrotherstyle/PCB-DATASET

This is the PCB Defect DATASET.

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-mount technology (SMT) is a technology that automates electronic circuits production in which components are mounted or placed onto the surface of printed circuit boards. Solder paste printing (SPP) is the most delicate stage in SMT. It prints solder paste on the pads of an electronic circuit panel. Thus, SPP is followed by a solder paste inspection (SPI) stage to detect defects. SPI scans the printed circuit board for missing/less paste, bridging between pads, miss alignments, and so forth. Boards with anomaly must be detected, and boards in good condition should not be disposed of. Thus SPI requires high precision and a high recall. More than 230 boards is collected and enhanced to 1200+ images.

This dataset is part of the open-source distributed synergy AI benchmarking project KubeEdge-Ianvs. It is released by KubeEdge SIG AI members from China Telecom and Raisecom Technology.

Benchmarking tools on incremental learning and single task learning is available on ianvs GitHub. Test reports are available on ianvs ReadTheDocs. Both the tools and the test reports are open for contribution!

This dataset combines the data from the following sources: - pcb-oriented-detection: https://www.kaggle.com/datasets/yuyi1005/pcb-oriented-detection - pcb-component-detection: https://sites.google.com/view/chiawen-kuo/home/pcb-component-detection - FICS-PCB: - https://www.researchgate.net/publication/344475848_FICS-PCB_A_Multi-Modal_Image_Dataset_for_Automated_Printed_Circuit_Board_Visual_Inspection - https://trust-hub.org/#/data/fics-pcb - Also at https://universe.roboflow.com/erl-n2gvo/component-detection-caevk/browse - PCB-Vision: https://arxiv.org/pdf/2401.06528 https://zenodo.org/records/10617721 - CompDetect Dataset: https://universe.roboflow.com/dataset-lmrsw/compdetect

All images are of the original high quality, with only the PCB-Vision images being rotated to ensure tight bounding boxes.

See the project at https://github.com/aryan-programmer/pcb-fault-detection for more information on the preprocessing steps taken.

Defects generated during PCB manufacturing, transportation, and storage seriously impact the quality and performance of electronic components. However, detection accuracy is limited due to excessive background interference and the small size of defect targets. To alleviate these issues, this paper proposes an improved PCB defect detection method based on RT-DETR, named SCP-DETR. Firstly, to effectively detect small targets, the S2 feature layer is incorporated into the neck feature fusion. While this improves detection capability, it also introduces considerable computational overhead. To mitigate this, we use SPDConv (Space-to-Depth Convolution) to process the S2 feature layer, reducing the computational complexity. The processed S2 feature layer is then fused with the S3 feature layer and higher-level features. Subsequently, we feed these features into a specially designed CO-Fusion module. By embedding our proposed CSPOKM(CSP Omni-Kernel Module) into the original fusion module, the CO-Fusion module effectively learns feature representations from global to local scales, ultimately enhancing small-target detection performance. Finally, downsampling operations are replaced with PSConv(Pinwheel-shaped Convolution), which better accommodates the Gaussian spatial pixel distributions of subtle small targets. Experimental results demonstrate that the proposed method achieves an mAP@0.5 of 97%, surpassing RT-DETR-r18 by 3%, and an mAP@0.5:0.95 of 53.4%, representing an improvement of 2.2%. Additionally, compared with the recently released YOLOv11m, our method improves mAP@0.5 by 5.6%. These results demonstrate the superior performance of the proposed method in PCB defect detection, which holds significant implications for industrial production. The code is available at https://github.com/Yttong-rr/SCPDETR/tree/master.