DOI QR코드

DOI QR Code

Accuracy Measurement of Image Processing-Based Artificial Intelligence Models

  • Received : 2024.02.06
  • Accepted : 2024.02.26
  • Published : 2024.03.31

Abstract

When a typhoon or natural disaster occurs, a significant number of orchard fruits fall. This has a great impact on the income of farmers. In this paper, we introduce an AI-based method to enhance low-quality raw images. Specifically, we focus on apple images, which are being used as AI training data. In this paper, we utilize both a basic program and an artificial intelligence model to conduct a general image process that determines the number of apples in an apple tree image. Our objective is to evaluate high and low performance based on the close proximity of the result to the actual number. The artificial intelligence models utilized in this study include the Convolutional Neural Network (CNN), VGG16, and RandomForest models, as well as a model utilizing traditional image processing techniques. The study found that 49 red apple fruits out of a total of 87 were identified in the apple tree image, resulting in a 62% hit rate after the general image process. The VGG16 model identified 61, corresponding to 88%, while the RandomForest model identified 32, corresponding to 83%. The CNN model identified 54, resulting in a 95% confirmation rate. Therefore, we aim to select an artificial intelligence model with outstanding performance and use a real-time object separation method employing artificial function and image processing techniques to identify orchard fruits. This application can notably enhance the income and convenience of orchard farmers.

Keywords

References

  1. X. Zhu, S. Mukhopadhyay, and H. Kurata, "A Review of RFID Technology and its Managerial Applications in Different Industries," Journal of Engineering and Technology Management, Vol. 29, No. 1, pp. 152-167, 2012. https://doi.org/10.1016/j.jengtecman.2011.09.011
  2. L. Ruiz Garcia, and L. Lunadei, "The Role of RFID in Agriculture: Applications, Limitations and Challenges," Computers and Electronics in Agriculture, Vol. 79, No. 1, pp. 4250, 2011.
  3. S. Zuo, L. Jin, Y. Chung, and D. Park, "An Index Algorithm for Tracking Pigs in Pigsty,"In P roc. of ICITMS, 2014.
  4. Y. Onishi, Yoshida, T., Kurita, H. et al. "An automated fruit harvesting robot by using deep learning," Robomech J 6, 13, 2019. DOI: https://doi.org/10.1186/s40648-019-0141-2
  5. F. Xiao, H. Wang, Y. Xu, R. Zhang, "Fruit Detection and Recognition Based on Deep Learning for Automatic Harvesting: An Overview and Review," Agronomy, Vol. 13, No. 6, pp. 1625, 2023. DOI: https://doi.org/10.3390/agronomy13061625
  6. S-. Y. Lee, T.-C. Huynh, J.-H. Park, J.-T. Kim, "Bolt-Loosening Detection using Vision-Based Deep Learning Algorithm and Image Processing Method," Journal of the Computational Structural Engineering Institute of Korea. pp. 265-272, 2019. DOI: https://doi.org/10.7734/COSEIK.2019.32.4.265
  7. J.Oh, "Straight Line Detection Using PCA and Hough Transform," Journal of the Korea Institute of Information and Communication Engineering. Vol. 22, No. 2, pp. 227~232, Feb. 2018. https://doi.org/10.6109/JKIICE.2018.22.2.227
  8. Y-. K. S.-H. Kim, "On the TFT LCD Cell Defect Inspection Algorithm using Morphology," Journal of the Korean Institute of Illuminating and Electrical Installation Engineers, Vol. 21, No. 1, January 31, 2007. DOI: https://doi.org/10.5207/jieie.2007.21.1.019
  9. G-. S. Lee, S-. H. Lee, "Prediction of changes in fine dust concentration using LSTM model," International Journal of Advanced Smart Convergence (IJASC), vol. 11, no.2, 2022. DOI: https://doi.org/ IJASC.2022.11.2.05
  10. B-. S. Jang, S-. H, Lee, "CNN based Sound Event Detection Method using NMF Preprocessing in Background Noise Environment," International Journal of Advanced Smart Convergence (IJASC), vol. 9, no.2, 2020. DOI: https://doi.org/ IJASC.2020.9.2.3