Erhan KAHYA*

Department of Electronics and Automation, Tekirdag Namik Kemal University, Turkey

*Corresponding Author: Erhan KAHYA, Department of Electronics and Automation, Tekirdag Namik Kemal University, Turkey.

Received: April 24, 2025 Published: May 14, 2025

Abstract

Thanks to developments in the field of deep learning in recent years, important results have been achieved in various research projects. The YOLOv8 model, which is primarily used for object detection, exhibits varying degrees of superiority in certain tasks with its different sub-models. In specific evaluations such as classification, identification and disease detection, the subcomponents of each model show different performance in their own areas. The characteristics of all sub-models of YOLOv8 were analysed and it was determined which model has speed, resource utilisation, high accuracy and balanced performance. The study focuses on the optimization of apple detection by integrating deep learning approaches. Four different models of Yolov8 (YOLOv8S, YOLOv8M, YOLOv8L and YOLOv8XL) are analysed to accurately detect apples on branches. In the experimental analysis, a comprehensive evaluation was conducted using performance metrics such as accuracy, recognition value and mean accuracy (mAP) of each model. The results show that the YOLOv8S model stands out for its fast processing and low cost advantage, while the YOLOv8XL model offers the highest accuracy. In addition, the YOLOv8M model was characterised by high recognition rates.

Keywords: Deep Learning; YOLOv8; Identification; Apple

References

1. Xuan G., et al. “Apple detection in natural environment using deep learning algorithms”. IEEE Access 8 (2020): 216772-216780.
2. Öztürk B. “Red Chief Elma Çeşi̇di̇nde, Ami̇noethoxyvi̇nylglyci̇ne’ni̇n (Avg) Ve Naftalen Aseti̇k Asi̇t’i̇n (Naa) Hasat Önü Döküm Ve Meyve Kali̇tesi̇ Üzeri̇ne Etki̇si̇”. Anadolu Journal of Agricultural Sciences 3 (2012): 120-126.
3. Öztürk B., et al. “Hasat Öncesi AVG Uygulamalarının Soğukta Muhafaza Süresince Jonagold Elma Çeşidinin Meyve Kalitesi Üzerine Etkileri”. Uluslararası Tarım Ve Yaban Hayatı Bilimleri Dergisi (2017): 1-1.
4. Güneyli A., et al. “Granny Smith Elma Çeşidinde Hasat Sonrası Farklı Dozlarda 1-Metilsiklopropen Uygulamalarının Meyve Kalitesi Üzerine Etkileri”. Meyve Bilimi1 (2022): 16-22.
5. Kumar RC Joshi., et al. “Fruit-CNN: An Efficient Deep learning-based Fruit Classification and Quality Assessment for Precision Agriculture," 2021 13^th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), Brno, Czech Republic (2021): 60-65.
6. Yousif M. “Enhancing the accuracy of image classification using deep learning and preprocessing methods”. Artificial Intelligence and Robotics Development Journal4 (2024): 269-281.
7. Zhao Q and Liu Y. “Design of apple recognition model based on improved deep learning object detection framework Faster-RCNN”. Advances in Continouous and Discrete Models 1 (2024).
8. Tsirtsakis P., et al. “Deep learning for object recognition: a comprehensive review of models and algorithms”. International Journal of Cognitive Computing in Engineering 6 (2025): 298-312.
9. Kaukab S., et al. “Improving real-time apple fruit detection: multi-modal data and depth fusion with non-targeted background removal”. Ecological Informatics 82 (2024): 102691.
10. Kuznetsova A., et al. “Using YOLOv3 Algorithm with Pre- and Post-Processing for Apple Detection in Fruit-Harvesting Robot”. Agronomy7 (2020): 1016.
11. Yang X., et al. “Lightweight and efficient deep learning models for fruit detection in orchards”. Scientific Reports1 (2024).
12. Sherkhane PD and Ratnaparkhi NS. “Deep learning techniques used in agriculture: a review. International Journal for Research in Applied Science and Engineering Technology 12.3 (2024): 1-5.
13. Huang, et al. “Metricopt: learning to optimize black-box evaluation metrics. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021): 174-183.
14. Sun, et al. “Detection of orchard apples using improved yolov5s-gbr model”. Agronomy 14.4 (2024): 682.
15. Kang H and Chen C. “Fast implementation of real-time fruit detection in apple orchards using deep learning”. Computers and Electronics in Agriculture 168 (2020): 105108.
16. Hani, et al. “Apple Counting using Convolutional Neural Networks”. 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS),Madrid, Spain (2018).
17. Gao, et al. “Application of Advanced Deep Learning Models for Efficient Apple Defect Detection and Quality Grading in Agricultural Production”. Agriculture 14.7 (2024): 1098.
18. Yıldırım Ş and Ulu B. “Deep learning based apples counting for yield forecast using proposed flying robotic system”. Sensors13 (2023): 6171.
20. KARADAĞ B and Arı A. “Akıllı mobil cihazlarda yolov7 modeli ile nesne tespiti”. Politeknik Dergisi 3 (2023): 1207-1214.
21. Günen MA. “Nokta bulutu verisi kullanılarak elma bahçesinden meyve tespiti”. El-Cezeri Fen Ve Mühendislik Dergisi (2021).
22. Lin Y., et al. “Ag-yolo: a rapid citrus fruit detection algorithm with global context fusion”. Agriculture1 (2024): 114.
23. Widiati W and Haryanto T. “Deep learning for automatic classification of avocado fruit maturity”. Jurnal Pilar Nusa Mandiri1 (2024): 75-80.
24. Ukwuoma CC., et al. “Recent advancements in fruit detection and classification using deep learning techniques”. Mathematical Problems in Engineering (2022): 1-29.
25. Liang X., et al. “Real-time grading of defect apples using semantic segmentation combination with a pruned yolo v4 network”. Foods19 (2022): 3150.
26. Zhang G., et al. “An apple detection and localization method for automated harvesting under adverse light conditions”. Agriculture3 (2024): 485.
27. Xu D., et al. “Intelligent detection of muskmelon ripeness in greenhouse environment based on yolo-rfew”. Agronomy 6 (2024): 1091.
28. Zhai Y., et al. “Machine learning based blueberry detection method by cie-yolov5”. International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023) (2024):
29. Neupane C., et al. “In-orchard sizing of mango fruit: 1. comparison of machine vision based methods for on-the-go estimation”. Horticulturae 12 (2022): 1223.
30. Lawal OM., et al. “Lightweight fruit detection algorithms for low‐power computing devices”. IET Image Processing 9 (2024): 2318-2328.
31. Siddiqi R. “Comparative performance of various deep learning based models in fruit image classification. Proceedings of the 11^th International Conference on Advances in Information Technology (2020).
32. Afsharpour P., et al. “Robust deep learning method for fruit decay detection and plant identification: enhancing food security and quality control”. Frontiers in Plant Science (2024): 15.
33. Kahya E., et al. “Recognition Of Kiwifruit On Seedling For Precision Harvesting Systems With Yolov8 Deep Learning Model”. International Conference On Global Practice Of Multidisciplinary Scientific Studies-Vııı (2024): 620-634.
34. Mimma N., et al. “Fruits classification and detection application using deep learning”. Scientific Programming (2022): 1-16.
35. Rahman MM., et al. “A deep cnn approach to detect and classify local fruits through a web interface”. Smart Agricultural Technology 5 (2023): 100321.
36. Kahya E., et al. “Application of YOLOv8L Deep Learning in Robotic Harvesting of Persimmon (Diospyros)”. ISPEC Journal of Agricultures Sciences3 (2023): 587-601.
37. Lu D., et al. “Plant detection and counting: Enhancing precision agriculture in UAV and general scenes”. IEEE Access (2023).
38. Kahya E., et al. “Yolov8 Deep Learning Application To Be Used In Robotic Pepper Harvesting (Capsicum Annuum). 5^th International Cukurova Agriculture And Veterinary Congress (2023): 430-441.
39. Dewi C., et al. “Fruit Classification System with Deep Learning and Neural Architecture Search (2024).
40. Sa I., et al. “Deepfruits: a fruit detection system using deep neural networks”. Sensors 8 (2016): 1222.
41. Kahya E., et al. “Yolov5 model application in real-time robotic eggplant harvesting”. Journal of Agricultural Science2 (2024): 9.

Citation

Citation: Erhan KAHYA. “Deep Learning for Apple Branch Detection: an Analysis of the Performance of YOLOV8 Models".. Acta Scientific Agriculture 9.6 (2025): 15-24.

Copyright

Copyright: © 2025 Erhan KAHYA. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.