Penulis: Moechammad Sarosa, Puteri Nurul Ma’rifah, Mila Kusumawardani, Dimas Firmanda Al Riza

Nama Jurnal: BIO Web of Conferences

Tahun: 2024

Volume: 117

Issue: Tidak ada

Halaman: 01021-01026

Deskripsi: Grapes are a type of vine that belongs to the Vitaceae family and has many health benefits. There are dozens of grape varieties that are widespread in Indonesia. Grape varieties can be differentiated based on their various leaf shapes. At first glance, it might look the same. However, if you look at the shape and character of each leaf, grapes have different types and leaf variants. In recent years, various plant leaf classification methods based on deep learning have been proposed. This research uses a deep learning method with the Faster R-CNN ResNet-50 algorithm and uses pre-trained COCO weights to classify grape varieties through leaf images. For this purpose, a dataset of grape leaf images from five varieties was taken independently. Based on the tests that have been carried out, it shows that the improved network can effectively increase the efficiency of network operation. After testing four times ranging from 3,000 steps to 8,000 steps, the accuracy of recognizing leaf variations reached the highest level of 90.11% at 8,000 test steps with a loss of 0.134721. The results of this research show that the algorithm can classify types of grapes based on their leaves.

Pendahuluan: Grapes are a type of vine that belongs to the Vitaceae family and has many health benefits [1]. There are dozens of grape varieties that are widespread in Indonesia. Cultivation, potential quality, and selling price of grapes depend on the variety [2]. Therefore, the interest of grape growers in the accurate identification of grape varieties is increasing, whether to determine the correct way of propagating grape cuttings according to the variety or to estimate the supply price of grapes. Grape varieties can be differentiated based on their various leaf shapes [3]. At first glance, it might look the same. However, if you look at the shape and character of each leaf, grapes have different types and leaf variants. In recent years, various methods of classifying plant leaves have been proposed [4]–[9]. Of some methods to classify plant leaves, most of the research applies deep learning methods, which can help classify objects effectively, but none of the studies have discussed the classification of grapes through the leaves. Deep learning methods have been widely used for research, such as image detection and classification [10]–[15]. Convolutional neural networks (CNN) are one of the most common and widely used models of deep learning and have good performance because most CNN architectures have superior capabilities in learning the features of an object [16]. The CNN method continues to develop until the newest method proposed by Shaoqing Ren et al., namely Faster R-CNN [17]. This research uses a deep learning method with the Faster R-CNN ResNet-50 algorithm and uses pre-trained COCO weights to classify grape varieties through leaf images. The classification of grape leaves used in this research consists of five types of grape leaves: academic, jupiter, local, taldun, and transfiguration. It is hoped that this research can help grape farmers classify grape plant types so that the management of these plants can be optimal.

Kata Kunci: Grape plant, Grape varieties, Inception ResNet, Leaf detection, ResNet

Total Kunjungan: 35 kali