Performa Model Faster R-Cnn Untuk Klasifikasi Penyakit Daun Jagung

Abstract

Image classification is one of the main challenges in the field of digital image processing and computer vision. This study aims to develop an image classification system using the Faster R-CNN object detection method. The Faster R-CNN model is utilized to detect objects in images while also classifying the extracted features from those images. The dataset used in this study was sourced from Kaggle and data taken directly by researcher. The data underwent several preprocessing stages, including data transformation, splitting into training / validation / testing sets, and model performance evaluation based on metrics such as accuracy, precision, recall, anda F1-Score. The experimental results demonstrate that the Faster R-CNN method can achieve high classification performance, with accuracy reaching up to 98,98% at a data ratio of 60:20:20. In addition, the model also shows performance stability at other data ratios. This study confirms that deep learning methods can deliver excellent results in image classification tasks. This research is expected to be a reference for the development of other image classification systems, especially those that require accurate object detection and classification.