Deteksi dan Klasifikasi Penyakit Pada Daun Kopi Menggunakan Yolov7

Abstract

In improving the economy of developing countries, the highest export commodity is the coffee plant. Indonesia produces 639 thousand tons of coffee every year. Therefore, establishing Indonesia as 4th in the world. However, decreased productivity due to diseases of the coffee plant leaves can reduce the productivity of coffee production. Leaf diseases include Miner, Rust, Phoma, and Cercospora. Based on extant issues in agriculture, utilization such as artificial intelligence, Computer Vision, and Bigdata can decrease the costs incurred to trade with plant diseases. With significant advances in artificial intelligence in Machine Learning comes the Deep Learning method. YOLO is Deep Learning seeded as an object detection compared to other approaches. YOLOv7 is the latest version of the YOLO architecture that can detect speed, high Precision, easy-to-train data, and implementation. The main contribution of this research was to develop using model-based YOLOv7, use coffee leaf costume datasets, data augmentation, and preprocessing datasets. This research utilizes Google Colab and GPU Tesla T4 to get a result F1-score of 0.93, Precision of 0.926, Recall of 0.932, mAP@IoU .5 of 0.956, mAP@IoU .5:.95 of 0.927 for the entire trained data class. However, the best result is the binary class to get a result F1-score of 0.99, Precision of 0.991, Recall of 1, mAP@IoU .5 of 0.998, mAP@IoU .5:.95 of 0.994.

Keywords

• yolov7
• object detection
• leaf diseases
• computer vision