Poisonous Mushroom Detection using YOLOV5

Abstract

Mantar dünyadaki birçok ülkede yetişen ve tüketilen besin değeri yüksek bir gıdadır. Kolay edinilmesi, insan sağlığına faydalı olması ve lezzeti sebepleriyle tüketim için tercih edilmektedir. Yenilebilir olanları sağlık açısından faydalı olmakla beraber zehirli türleri de bulunmaktadır. Mantarların hangilerinin yenilebilir olduğunu ayırt etmek bu konuda bilgi sahibi olmayan kişiler için zordur. Dolayısıyla bu işlemin otomatik olarak sağlanması faydalı olacaktır. Çalışma, zehirli mantarların tanınmasını sağlayarak yenilmesini önlemeyi amaçlamaktadır. Bu kapsamda, en zehirli 8 mantar türünü içeren bir veri seti oluşturuldu. Oluşturulan veri seti, ön eğitimli YOLOV5 algoritması kullanılarak ince ayar yöntemi ile eğitildi. Yöntemin başarımını göstermek için precision, recall ve mAP kriterleri kullanıldı. İnce ayarlanmış model, sekiz farklı türün tanınmasını 0.77 mean Average Precision olarak sağlamıştır.

Keywords

• Object detection
• YOLOV5
• Poisonous mushroom detection

References

1. Krittanawong, C., Isath, A., Hahn, J., Wang, Z., Fogg, S. E., Bandyopadhyay, D., ... & Tang, W. W. (2020). Mushroom Consumption and Cardiovascular Health: A Systematic Review. The American Journal of Medicine.
2. Maurya, P., & Singh, N. P. (2020). Mushroom Classification Using Feature-Based Machine Learning Approach. In Proceedings of 3rd International Conference on Computer Vision and Image Processing (pp. 197-206). Springer, Singapore.
3. Sameh, A., Moghayer, M., Mohanad, G., & Mohammad, A. (2020). Classification of Mushroom Using Artificial Neural Network.
4. Wang, Y., Du, J., Zhang, H., & Yang, X. (2020). Mushroom Toxicity Recognition Based on Multigrained Cascade Forest. Scientific Programming, 2020.
5. Subramaniam, A., & Oh, B. J. (2016). Mushroom recognition using PCA algorithm. International Journal of Software Engineering and Its Applications, 10(1), 43-50.
6. Sunita, B., & Bishan, D. (2015). Mushroom classification using data mining techniques. International Journal of Pharma and Bio Sciences, 6(1).
7. Ayorınde I. T., & Badmos Z. O. (2019).Development of Deep Learning Model on Mushroom Dataset towards Classifying Poisonous Mushroom with Feature Selection. 3 rd Biennial International Conference on Transition from Observation to Knowledge to Intelligence (TOKI), University of Lagos, Nigeria.
8. Ortega, J. H. J. C., Lagman, A. C., Natividad, L. R. Q., Bantug, E. T., Resureccion, M. R., & Manalo, L. O. (2020). Analysis of Performance of Classification Algorithms in Mushroom Poisonous Detection using Confusion Matrix Analysis. International Journal, 9(1.3).

9. https://github.com/tzutalin/labelImg, Accessed January 2021.
10. Sharma, V., & Mir, R. N. (2020). A comprehensive and systematic look up into deep learning based object detection techniques: A review. Computer Science Review, 38, 100301.
11. Wu, X., Sahoo, D., & Hoi, S. C. (2020). Recent advances in deep learning for object detection. Neurocomputing, 396, 39-64.
12. Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012.
13. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580-587).
14. Cao, C., Wang, B., Zhang, W., Zeng, X., Yan, X., Feng, Z., ... & Wu, Z. (2019). An improved faster R-CNN for small object detection. IEEE Access, 7, 106838-106846.
15. He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 2961-2969).
16. Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., & Sun, J. (2017). Light-head r-cnn: In defense of two-stage object detector. arXiv preprint arXiv:1711.07264.
17. Cai, Z., & Vasconcelos, N. (2018). Cascade r-cnn: Delving into high-quality object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6154-6162).
18. Liu, Y., Sun, P., Wergeles, N., & Shang, Y. (2021). A Survey and Performance Evaluation of Deep Learning Methods for Small Object Detection. Expert Systems with Applications, 114602.
19. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016, October). Ssd: Single shot multibox detector. In European conference on computer vision (pp. 21-37). Springer, Cham.
20. Fu, C. Y., Liu, W., Ranga, A., Tyagi, A., & Berg, A. C. (2017). Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659.
21. Li, Z., & Zhou, F. (2017). FSSD: feature fusion single shot multibox detector. arXiv preprint arXiv:1712.00960.
22. Cui, L., Ma, R., Lv, P., Jiang, X., Gao, Z., Zhou, B., & Xu, M. (2018). MDSSD: multi-scale deconvolutional single shot detector for small objects. arXiv preprint arXiv:1805.07009.
23. Shen, Z., Liu, Z., Li, J., Jiang, Y. G., Chen, Y., & Xue, X. (2017). Dsod: Learning deeply supervised object detectors from scratch. In Proceedings of the IEEE international conference on computer vision (pp. 1919-1927).
24. Zhao, Q., Sheng, T., Wang, Y., Tang, Z., Chen, Y., Cai, L., & Ling, H. (2019, July). M2det: A single-shot object detector based on multi-level feature pyramid network. In Proceedings of the AAAI conference on artificial intelligence (Vol. 33, No. 01, pp. 9259-9266).
25. Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision (pp. 2980-2988).
26. Law, H., & Deng, J. (2018). Cornernet: Detecting objects as paired keypoints. In Proceedings of the European conference on computer vision (ECCV) (pp. 734-750).
27. Yang, Z., Liu, S., Hu, H., Wang, L., & Lin, S. (2019). Reppoints: Point set representation for object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 9657-9666).
28. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788).
29. Redmon, J., & Farhadi, A. (2017). YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7263-7271).
30. Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.
31. Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
32. Huang, Z., Wang, J., Fu, X., Yu, T., Guo, Y., & Wang, R. (2020). DC-SPP-YOLO: Dense connection
33. Jocher, G., Nishimura, K., Mineeva, T., Vilariño, R.: YOLOv5 (2020). https://github.com/ultralytics/yolov5. Accessed january 2021
34. M. Petruzzello, https://www.britannica.com/list/7-of-the-worlds-most-poisonous-mushrooms. Accessed january 2021.
35. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. (2019). Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 658-666).
36. CENGİL, E., & ÇINAR, A. Göğüs Verileri Metrikleri Üzerinden Kanser Sınıflandırılması. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 11(2), 513-519.
37. Padilla, R., Netto, S. L., & da Silva, E. A. (2020, July). A survey on performance metrics for object-detection algorithms. In 2020 International Conference on Systems, Signals and Image Processing (IWSSIP) (pp. 237-242). IEEE.
38. Henderson, P., & Ferrari, V. (2016, November). End-to-end training of object class detectors for mean average precision. In Asian Conference on Computer Vision (pp. 198-213). Springer, Cham.