datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
pcb-defect-segmentation
Dataset Labels
['dry_joint', 'incorrect_installation', 'pcb_damage', 'short_circuit']
Number of Images
{'valid': 25, 'train': 128, 'test': 36}
How to Use
Install datasets:
pip install datasets
Load the dataset:
from datasets import load_dataset
ds = load_dataset("keremberke/pcb-defect-segmentation", name="full")
example = ds['train'][0]
Roboflow Dataset Page
https://universe.roboflow.com/diplom-qz7q6/defects-2q87r/dataset/8… See the full description on the dataset page: https://huggingface.co/datasets/keremberke/pcb-defect-segmentation.PCB_defect
⚡ 데이터셋 요약
본 데이터셋은 naked PCB(부품 실장 전 PCB) 이미지로 구성되어 있으며, 총 1386장, 6종 결함, 이미지당 3~5개 결함을 포함
이미지는 실제 AOI 유사 촬영 시스템으로 템플릿 보드를 촬영한 뒤, Photoshop으로 결함을 삽입해 합성
즉, “현장(real) 결함”이 아니라, 제어된 합성 결함이라는 점이 데이터 해석/일반화에서 중요한 전제
🌳 데이터셋 구조
PCB_defect/
├── README.md
├── Meta Data/
│ └── Huang et al.(2019), A PCB Dataset for Defects Detection and Classification.pdf
├── Missing_hole/ # 결함 유형
│ ├── missing_hole01.jpg # [입력] PCB 이미지
│ ├──… See the full description on the dataset page: https://huggingface.co/datasets/RobotHuman/PCB_defect.PCB-Solder-Joint-Defect-Detection-Dataset
PCB Solder Joint Defect Detection Dataset
The PCB manufacturing industry is facing challenges in maintaining high-quality standards, particularly in the detection of solder joint defects post-wave and reflow soldering. Existing solutions often rely on manual inspection or less efficient automated systems that are prone to errors. This dataset aims to address the specific technical challenge of accurately identifying and classifying defects in solder joints, fulfilling the business… See the full description on the dataset page: https://huggingface.co/datasets/Mobiusi/PCB-Solder-Joint-Defect-Detection-Dataset.pcb-defect-assetsindustrial-pcb-defect-detection-dataset
EdgePCB Defect Detection Dataset
Overview
The EdgePCB Defect Detection Dataset is a large-scale annotated dataset designed for training and evaluating deep learning models for automated PCB (Printed Circuit Board) inspection. The dataset supports real-time object detection tasks and is specifically curated for industrial applications using edge AI systems.
It is developed as part of the EdgePCB-AI project, which focuses on deploying YOLOv8-based defect detection models on… See the full description on the dataset page: https://huggingface.co/datasets/Tanishjain9/industrial-pcb-defect-detection-dataset.PCB-Solder-Joint-Defect-Detection-Dataset
PCB Solder Joint Defect Detection Dataset
The PCB manufacturing industry is facing challenges in maintaining high-quality standards, particularly in the detection of solder joint defects post-wave and reflow soldering. Existing solutions often rely on manual inspection or less efficient automated systems that are prone to errors. This dataset aims to address the specific technical challenge of accurately identifying and classifying defects in solder joints, fulfilling the business… See the full description on the dataset page: https://huggingface.co/datasets/TerLiphi/PCB-Solder-Joint-Defect-Detection-Dataset.pcb-defects-datasetpcb-defect-segmentation
Dataset Labels
['dry_joint', 'incorrect_installation', 'pcb_damage', 'short_circuit']
Number of Images
{'valid': 25, 'train': 128, 'test': 36}
How to Use
Install datasets:
pip install datasets
Load the dataset:
from datasets import load_dataset
ds = load_dataset("keremberke/pcb-defect-segmentation", name="full")
example = ds['train'][0]
Roboflow Dataset Page
https://universe.roboflow.com/diplom-qz7q6/defects-2q87r/dataset/8… See the full description on the dataset page: https://huggingface.co/datasets/pranjalkar9/pcb-defect-segmentation.PCB_defect