Mechanization in agriculture & Conserving of the resources
Vol. 69 (2025), Issue 1, pg(s) 17-19

MECHANIZATION IN AGRICULTURE

Methodology for determining the apple variety based on computer processing of digital images

  • 1 Kazakh National Agrarian Research University, Almaty, Kazakhstan

Abstract

This paper presents the development and experimental validation of a method for automatic identification of apple varieties based on the analysis of visual features extracted from digital images. The proposed approach uses classical computer vision techniques without applying neural networks or deep learning, which makes the system interpretable, lightweight, and reproducible for laboratory and industrial use.
The algorithm includes the stages of image acquisition, preprocessing, object segmentation, feature extraction, and classification using statistical models such as Support Vector Machines (SVM), k-Nearest Neighbors (k-NN), and logistic regression. The extracted features include geometric parameters (area, perimeter, circularity, eccentricity, axis ratio) and color characteristics (mean HSV values, red color percentage, hue distribution).
Experimental validation was performed on a dataset containing five apple varieties: Sinap Almaty, Fuji, Brebourne, Gold Delicious, and Hybrid. The system achieved an average classification accuracy of 90%, with the highest results for varieties with distinctive morphological or color characteristics. Comparative analysis with manual sorting demonstrated significant advantages in terms of processing speed, objectivity, and scalability.
The proposed method can be implemented on compact single-board computers, making it suitable for mobile quality control stations and automated sorting lines. Future work includes the integration of weight and texture parameters and the expansion of the variety database for broader applicability.

Keywords

References

  1. 1. Nurtuleuov A., Moldazhan A., Kulmakhambitova A., Zinchenko D. Justification of the method and algorithm for determining the quality indicators of apples and their automatic sorting into categories // Scientific journal. - 2021. - No. 3 (91). - P. 125-133. DOI: 10.37884/3-2021/14.
  2. Alikhanov J., Moldazhanov A., Kulmakhambetova A., Zinchenko D., Azizov A., Nurtuleuov A., Sarsenbekuly D. Digital technology for determining quality indicators and classification of apple fruits based on computer vision and deep learning // AGRICULTURAL MACHINERY 2024. Proceedings of the XII International Scientific Congress, 26–29 June 2024, Varna, Bulgaria. – P. 21–23.
  3. 3. Jakhfer Alikhanov, Moldazhanov Aidar, Akmaral Kulmakhambetova, Dimitriy Zinchenko, Alisher Nurtuleuov, Zhandos Shynybay, Tsvetelina Georgieva, Plamen Daskalov Methodology for Determining the Main Physical Parameters of Apples by Digital Image Analysis Scientific journal "AgriEngineering" AgriEngineering Volume 7, Issue 3 March 2025 Article number 57 DOI: 10.3390/agriengineering7030057
  4. Bhatt A.K., Pant D. Automatic apple grading model development based on back propagation neural network and machine vision, and its performance evaluation // AI & Society. – 2015. – Vol. 30(1). – P. 45–56. DOI: 10.1007/s00146-014-0540-7.
  5. Sofu M.M., Erb O., Kayacan M.C., Cetisli B. Design of an automatic apple sorting system using machine vision // Computers and Electronics in Agriculture. – 2016. – Vol. 127. – P. 395–405. DOI: 10.1016/j.compag.2016.06.017.
  6. Moallem P., Serajoddin A., Pourghassem H. Computer vision-based apple grading for Golden Delicious apples based on surface features // Information Processing in Agriculture. – 2017. – Vol. 4. – P. 33–40. DOI: 10.1016/j.inpa.2016.10.003.
  7. Verdhan V. Computer Vision Using Deep Learning: Neural Network Architectures with Python and Keras. – Apress, 2021. – 420 p. DOI: 10.1007/978-1-4842-6616-8.

Article full text

Download PDF