Related Experiment Video
Updated: May 26, 2025
05:16
Flying Insect Detection and Classification with Inexpensive Sensors
Published on: October 15, 2014
25.1K
ElectroCom61: A multiclass dataset for detection of electronic components.
Md Faiyaz Abdullah Sayeedi1, Anas Mohammad Ishfaqul Muktadir Osmani1, Taimur Rahman1
1Department of Computer Science and Engineering, United International University, Bangladesh.
Data in Brief
|February 24, 2025
Summary
We introduce ElectroCom61, a new dataset for detecting 61 electronic components, crucial for advancing automation in industry and education. This dataset enhances machine learning model robustness for real-world applications.
Area of Science:
- Computer Vision
- Machine Learning
- Robotics
Background:
- Efficient electronic component detection is vital for automation in industrial, robotics, and technical education.
- Existing datasets may not adequately represent real-world complexities for robust model training.
Purpose of the Study:
- To introduce ElectroCom61, a novel multi-class object detection dataset for 61 electronic components.
- To provide a robust dataset for developing advanced electronic component detection systems.
Main Methods:
- Collected and annotated 2121 images of electronic components from United International University (UIU).
- Ensured image diversity with varied lighting, backgrounds, distances, and camera angles.
- Structured the dataset into training, validation, and test sets with minimal pre-processing.
Main Results:
- ElectroCom61 comprises 61 distinct electronic component classes.
- The dataset is designed to enhance the robustness of machine learning models for component detection.
- Technical validation code is publicly available on GitHub.
Conclusions:
- ElectroCom61 is a valuable resource for developing sophisticated electronic component detection systems.
- The dataset has broad applications in education, e-waste management, and manufacturing automation.
- Facilitates advancements in automated sorting and inventory management.
