การเปรียบเทียบคุณภาพมะม่วงพันธุ์น้ำดอกไม้โดยใช้อัลกอริทึม YOLOv11

Panisara Hadkhuntod; Katesuda Phokanit; Thanakorn Sangkudluo

Authors

Panisara Hadkhuntod Pibulsongkram Rajabhat University
Katesuda Phokanit Rajabhat Chaiyaphum University
Thanakorn Sangkudluo Naresuan University

Keywords:

Comparison, Nam Dok Mai Mango, YOLOv11 Algorithm

Abstract

Nam Dok Mai mangoes are an important economic crop, and manual quality sorting before market distribution often leads to human errors and delays. This study applied the YOLOv11 algorithm to assess mango quality through smartphone images. A total of 950 images were used, categorized into Normal (good quality) and Abnormal (defective) mangoes. Two labeling methods were implemented: Label A (whole-fruit annotation) and Label B (defect-only annotation). The dataset was divided into 80% for training, 10% for validation, and 10% for testing. Experimental results showed that YOLOv11n and YOLOv11s required less storage space and provided faster processing, while YOLOv11m achieved slightly higher accuracy but demanded greater computational resources. Moreover, Label A outperformed Label B in terms of mAP50–95, Precision, Recall, and F1-Score. The choice of algorithm depends on resource constraints: YOLOv11m is suitable for maximum accuracy, YOLOv11s for balanced performance, and YOLOv11n for the highest processing speed. The study demonstrates that using YOLOv11 enhances accuracy, reduces processing time, and minimizes human errors in mango quality classification, paving the way for future development of automated fruit sorting systems.

References

กษิดิศ สตางค์มงคล. (2566, 17 มกราคม). Confusion matrix คืออะไร พร้อมวิธีคำนวณค่าสถิติง่ายๆ. DataRockie. https://datarockie.com/blog/confusion-matrix-explained/

ไทยขึ้นเบอร์ 1 ส่งออกมะม่วง ตลาดเกาหลีใต้ ปี 2567. (2568, 3 มีนาคม). ไทยรัฐออนไลน์. https://www.thairath.co.th/scoop/infographic/2844988

นพรุจ พัฒนสาร และณัฐวุฒิ ศรีวิบูลย์. (2563). การประมวลผลภาพสำหรับการจําแนกคุณภาพมะม่วงพันธุ์ โชคอนันต์โดยการจําลองการมองเห็นของมนุษย์ด้วยวิธีการเรียนรู้เชิงลึก. วารสารวิทยาการและเทคโนโลยีสารสนเทศ, 10(1), 24-29. https://doi.org/10.14456/jist.2020.3

พีระศักดิ์ ฉายประสาท. (2553). การปลูกมะม่วงน้ำดอกไม้สีทอง. ภารกิจโครงการและประสานงานวิจัย สำนักงานคณะกรรมการวิจัยแห่งชาติ.

Bilal, M. M., Shivandappa, Sanju, H. K., Kumar, N. S., & Kaipa, V. K. (2024). Automated mango classification using convolutional neural networks (CNN). International Journal of Innovative Science and Research Technology, 9(9), 269-275. https://doi.org/10.38124/ijisrt/IJISRT24SEP163

Ghosh, A. (2024, October 8). YOLO11: Redefining real-time object detection. LearnOpenCV. https://learnopencv.com/yolo11/

Khanam, R., & Hussain, M. (2024). YOLOv11: An overview of the key architectural enhancements. arXiv. https://doi.org/10.48550/arXiv.2410.17725

Liu, C., Lin, W., Feng, Y., Guo, Z., & Xie, Z. (2023). ATC-YOLOv5: Fruit appearance quality classification algorithm based on the improved YOLOv5 model for passion fruits. Mathematics, 11(16), Article 3615. https://doi.org/10.3390/math11163615

Nagpal, R., Long, S., Jahagirdar, S., Liu, W., Fazackerley, S., Lawrence, R., & Singh, A. (2023). An application of deep learning for sweet cherry phenotyping using YOLO object detection. arXiv. https://doi.org/10.48550/arXiv.2302.06698

Rao, S. N. (2024, October 23). YOLOv11 architecture explained: Next-level object detection with enhanced speed and accuracy. Medium. https://medium.com/@nikhil-rao-20/yolov11-explained-next-level-object-detection-with-enhanced-speed-and-accuracy-2dbe2d376f71

Sapkota, R., Meng, Z., Churuvija, M., Du, X., Mab, Z., & Karkee, M. (2025). Comprehensive performance evaluation of YOLOv12, YOLOv11, YOLOv10, YOLOv9 and YOLOv8 on detecting and counting fruitlet in complex orchard environments. arXiv. https://doi.org/10.48550/arXiv.2407.12040

Yeh, J.-F., Lin, K.-M., Lin, C.-Y., & Kang, J.-C. (2023). Intelligent mango fruit grade classification using AlexNet-SPP with mask R-CNN-based segmentation algorithm. IEEE Transactions on AgriFood Electronics, 1(1), 41–49. https://doi.org/10.1109/TAFE.2023.3267617

Yoon, S., Cho, Y., & Ahn, T. I. (2024). Melon fruit detection and quality assessment using generative AI-based image data augmentation. arXiv. https://doi.org/10.48550/arXiv.2407.10413

Y-T-G, glenn-jocher, Laughing-q, RizwanMunawar, pderrenger, & ambitious-octopus. (2025, February 26). Ultralytics YOLO11. Ultralytics. https://docs.ultralytics.com/models/yolo11/

Zhu, L., & Spachos, P. (2021). Support vector machine and YOLO for a mobile food grading system. Internet of Things, 13, Article 100359. https://doi.org/10.1016/j.iot.2021.100359