Related Experiment Video
Updated: Sep 23, 2025
10:04
A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
Published on: March 3, 2018
6.8K
A Two-Stage Method to Detect the Sex Ratio of Hemp Ducks Based on Object Detection and Classification Networks
Xingze Zheng1, Feiyi Li1, Bin Lin1
1College of Information Engineering, Sichuan Agricultural University, Ya'an 625000, China.
Animals : an Open Access Journal From MDPI
|May 14, 2022
Summary
Automated sex classification for hemp ducks improves breeding efficiency. This AI method accurately determines duck sex ratios, overcoming manual counting limitations for better farm management.
Area of Science:
- Agricultural Science
- Computer Science
- Animal Science
Background:
- Accurate sex ratio determination is crucial for profitable hemp duck farming.
- Manual counting methods are inefficient and prone to errors due to duck movement and human limitations.
Purpose of the Study:
- To develop an efficient and accurate automated method for duck sex classification and sex ratio estimation.
- To address the limitations of manual counting in commercial duck farming environments.
Main Methods:
- Creation of the first manually annotated sex classification dataset for hemp ducks, including group, whole body, and head images.
- Application of deep neural network models, including Yolov5 and VovNet_27slim, for object detection and sex classification.
Main Results:
- The developed automated method achieved an average accuracy of 98.68% for duck sex classification.
- The combined Yolov5 and VovNet_27slim model reached 99.29% accuracy, with a 98.60% F1 score and 269.68 frames per second.
Conclusions:
- The proposed automated method is a feasible and effective tool for sex classification of ducks in farming conditions.
- This technology can significantly enhance the estimation of sex ratios, promoting the duck farming industry.
