.
2026 · Book ·
.
Profil penulis
BRIGITA
2 karya publik ditemukan.
2026: 2
.
.
PROTOTIPE SISTEM DETEKSI OTOMATIS BAJAKAH BERBASIS CITRA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)
Nunukan Regency, located in North Kalimantan Province, particularly in Pagar Village, is an area with high plant biodiversity, including the Bajakah plant (Spatholobus littoralis Hassk). This study aims to design and develop a prototype of an automatic image-based Bajakah stem detection system using the Deep Learning method, specifically the Convolutional Neural Network (CNN), in order to make the identification process faster, more effective, and more accurate. The dataset used in this study consisted of Bajakah stem images as the main data and non-Bajakah stem images as comparison data obtained through direct image acquisition in Pagar Village, Nunukan Regency, using a smartphone camera with a resolution of 3024 × 4032 pixels. The total dataset consisted of 500 original Bajakah stem images and 500 non-Bajakah stem images. All datasets then underwent preprocessing stages, followed by dataset splitting into 80% training data, 10% validation data, and 10% testing data to ensure the model could perform the learning and testing processes optimally. The results showed that the VGG16-based CNN model was able to detect and identify Bajakah stems effectively based on digital images. The success of the system was proven by excellent evaluation metrics, achieving accuracy, Precision, and Recall values of 100% on all testing data without any classification errors. In addition, implementation testing on new data showed a detection confidence level ranging from 98.26% to 100.00%. These results indicate that the developed system is highly reliable and valid for use. This study is expected to contribute to the application of image processing and deep learning technologies in the field of traditional herbal plant identification in Kalimantan.