Related Experiment Video
Updated: Aug 31, 2025
08:55
A Rapid, Simple Workflow for Quantification of External Adult Drosophila Structures
Published on: November 8, 2024
535
An annotated image dataset of medically and forensically important flies for deep learning model training
1Institute for Tropical Biology and Conservation, Universiti Malaysia Sabah, Jalan UMS, 88400, Kota Kinabalu, Sabah, Malaysia. songquan.ong@ums.edu.my.
Scientific Data
|August 20, 2022
Summary
This study introduces a novel image dataset for automated identification of forensically and medically important dipterous flies. This resource aids in developing efficient insect recognition systems, overcoming limitations of traditional methods.
Area of Science:
- Entomology
- Computer Vision
- Bioinformatics
Background:
- Traditional insect taxonomy methods are laborious and time-consuming.
- Automated recognition systems using image processing offer a promising alternative for insect identification.
- A specialized image dataset for forensic and medical dipterous flies is currently lacking.
Purpose of the Study:
- To introduce a new, comprehensive image dataset for dipterous flies of forensic and medical importance.
- To facilitate the training and evaluation of automated insect recognition systems.
- To address the need for a standardized dataset in entomological image analysis.
Main Methods:
- Compilation of 2876 images of dipterous flies.
- Images provided in two dimensions: 224x224 pixels and 96x96 pixels for microcontrollers.
- Dataset includes three families (Calliphoridae, Sarcophagidae, Rhiniidae) and five genera, with five species variants per genus.
Main Results:
- A novel image dataset of 2876 dipterous fly images has been created.
- The dataset covers key families and genera relevant to forensic and medical entomology.
- Images are available in multiple resolutions suitable for various computational platforms.
Conclusions:
- The developed dataset is crucial for advancing automated identification of medically and forensically significant flies.
- This resource will accelerate the development of computer vision models for entomological applications.
- It provides a foundation for more efficient and accurate insect identification in critical fields.
