Quality Sorting of Silver Barb Fish Using Deep Learning and Chatbot-Based Image Analysis

Authors

  • Atchara Choompol Department of Computer Engineering, Faculty of Engineering and Industrial Technology, Kalasin University
  • Sarayut Gonwirat Department of Computer Engineering, Faculty of Engineering and Industrial Technology, Kalasin University
  • Ronnachai Sangmuenmao Department of Computer Engineering, Faculty of Engineering and Industrial Technology, Kalasin University
  • Narong Wichapa Department of Industrial Engineering, Faculty of Engineering and Industrial Technology, Kalasin University
  • Parichat Berkhuntod Department of Computer Engineering, Faculty of Engineering and Industrial Technology, Kalasin University
  • Phaewa Sikalun Department of Computer Engineering, Faculty of Engineering and Industrial Technology, Kalasin University
  • Phattarapol Phaowarit Department of Information Technology, Faculty of Science, Ubon Ratchathani University

DOI:

https://doi.org/10.14456/jeit.2024.23

Keywords:

Fish quality classification, Deep learning, Image classification, Chatbot

Abstract

This research aimed to address the limitations of manual quality sorting of silver barb fish, which suffered from limited accuracy and inconsistency. A deep learning model was developed to enhance the efficiency of fish quality classification based on image analysis. The model employed a Convolutional Neural Network (CNN), which was trained using a dataset of 700 images collected over a period of seven days. The ADAM optimizer was utilized to adjust the model's parameters during training, improving the accuracy of image classification. Additionally, a chatbot was developed through the Line Application to facilitate real-time fish quality inspection. The research findings demonstrated that the developed model classified fish quality with an accuracy of 98.12%, highlighting its potential for effective application in the fishing industry.

References

[1] กรมประมง, "รายงานสถานการณ์การผลิตสัตว์น้ำในประเทศไทย ปี 2563," กรมประมง, กรุงเทพฯ, 2563.

[2] สุทธิวัฒน์ เบญจกุล, "การตรวจสอบคุณภาพสัตว์น้ำ," มหาวิทยาลัยสงขลานครินทร์, สงขลา, 2548.

[3] A. Krizhevsky, I. Sutskever, and G. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Proceedings of the Neural Information Processing Systems (NIPS), 2012.

[4] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-Based Learning Applied to Document Recognition," Proceedings of the IEEE, 1998.

[5] F. Chollet, Deep Learning with Python, O'Reilly Media, United States, 2018.

[6] T. Li and X. Zhang, "Deep Learning for Fish Species Classification," Marine Technology Journal, 2022.

[7] A. Jain and B. Kamath, "Applications of Computer Vision in Object Detection," International Journal of Computer Science, 2020.

[8] P. He and S. Li, "Convolutional Neural Network for Image Classification," Location not specified, 2019.

[9] D. Kingma and J. Ba, "ADAM: A Method for Stochastic Optimization," International Conference on Learning Representations (ICLR), 2015.

[10] Line Corporation, "Line Messaging API documentation," Line Corporation, Japan, 2023.

[11] X. Wang, "Applications of Deep Learning in Aquaculture," Aquatic Science Review, 2023.

[12] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, "Densely Connected Convolutional Networks," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

[13] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," International Conference on Learning Representations (ICLR), 2015.

[14] R. Girshick, "Fast R-CNN," International Conference on Computer Vision (ICCV), 2015.

[15] O. Russakovsky et al., "ImageNet Large Scale Visual Recognition Challenge," International Journal of Computer Vision (IJCV), 2015.

Downloads

Published

2024-10-30

How to Cite

[1]
A. Choompol, “Quality Sorting of Silver Barb Fish Using Deep Learning and Chatbot-Based Image Analysis”, JEIT, vol. 2, no. 5, pp. 44–51, Oct. 2024.