A Computer Vision–Based Method for Determining the Vaccine Injection Position in Pangasius Fingerlings

Pangasius farming in the Mekong Delta is a major component of Vietnam’s aquaculture industry, characterized by large-scale production, intensive farming practices, and significant contributions to export revenue. However, vaccination of Pangasius fingerlings is still predominantly performed manually, resulting in low productivity, high labor demand, and inconsistent injection accuracy, which limit large-scale deployment in commercial hatcheries. Therefore, there is an urgent need to develop an automated and accurate vaccination method for Pangasius fingerlings. This study proposes a novel computer vision–based approach for non-contact measurement of Pangasius fingerlings and accurate determination of the vaccine injection position. The proposed method leverages the image processing capabilities of the OpenCV library in combination with statistical morphological characteristics of Pangasius fingerlings to localize the injection position. The Python-implemented algorithm is lightweight and can run on an embedded Raspberry Pi platform, supporting practical in-field deployment. Experimental results demonstrate an average positioning accuracy of 97.65%, confirming the effectiveness of the proposed approach and its potential to serve as a technological foundation for automated vaccination systems in Pangasius aquaculture.

@article{Truong2026,
  title     = {A Computer Vision–Based Method for Determining the Vaccine Injection Position in Pangasius Fingerlings},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {2},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Nguyen Phuc Truong and Luong Vinh Quoc Danh and Nguyen Chanh Nghiem},
  doi       = {10.14569/IJACSA.2026.0170216},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170216}
}