Related Experiment Video
Updated: Jul 4, 2025
03:31
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
542
Comprehensive image dataset for enhancing object detection in chemical experiments.
Ryosuke Sasaki1, Mikito Fujinami2, Hiromi Nakai1,2
1Department of Chemistry and Biochemistry, School of Advanced Science and Engineering, Waseda University, 3-4-1 Okubo, Shinjuku-ku, Tokyo 169-8555, Japan.
Data in Brief
|January 31, 2024
Summary
This study introduces a new image dataset for chemical experiments, featuring annotated images of lab equipment and hands. This resource aims to advance machine vision applications in chemistry, improving experiment recording and safety.
Area of Science:
- Chemistry
- Computer Science
- Data Science
Background:
- Image recognition can improve chemical experiment recording and safety.
- A lack of suitable datasets hinders machine vision in chemistry.
Purpose of the Study:
- To present a novel, annotated image dataset for chemical experiments.
- To facilitate the development of deep learning models for object detection in chemistry.
Main Methods:
- Collected images from organic chemistry laboratory videos.
- Annotated images of chemical apparatuses and experimenter's hands.
- Organized the dataset into training, validation, and test subsets.
Main Results:
- A dataset of 5078 images with detailed annotations was created.
- Images feature diverse backgrounds and experimental situations.
- Annotations enable precise object detection using deep learning.
Conclusions:
- The dataset addresses the scarcity of resources for machine vision in chemistry.
- It supports advancements in automated experiment recording and risk management.
- Facilitates research in applying AI to chemical laboratory settings.
