<![CDATA[ABSTRAKPenentuan tingkat kematangan buah melon sangat penting untuk menjaga kualitas dan daya simpan. Metode tradisional yang bergantung pada penilaian visual, penciuman, dan mengetuk buah bersifat subjektif dan tidak konsisten. Penelitian ini mengusulkan sistem estimasi usia dan tingkat kematangan buah melon berbasis citra dengan metode Faster R-CNN menggunakan backbone ResNet-50. Dataset sebanyak 1.683 citra melon dikumpulkan dari kebun hidroponik, kemudian melalui proses anotasi, preprocessing, dan augmentasi sebelum digunakan untuk pelatihan model. Evaluasi kinerja dilakukan menggunakan mean Average Precision (mAP), precision, recall, F1-score, dan accuracy. Hasil pengujian menunjukkan akurasi 92,42%, F1-score 0,890, dan mAP (0.5:0.95) sebesar 0,828. Sistem ini mampu mendeteksi objek melon serta mengklasifikasikan tingkat kematangan menjadi tiga kategori dengan lebih objektif dibandingkan metode tradisional.Kata kunci: Machine Learning, Faster R-CNN, Kematangan Buah Melon, Pengolahan Citra, Deteksi ObjekABSTRACTThe determination of melon fruit maturity is crucial for maintaining quality and shelf life. Traditional methods that rely on visual assessment, smell, and tapping the fruit are subjective and inconsistent. This study proposes an image-based system for estimating the age and maturity level of melons using the Faster R-CNN method with a ResNet-50 backbone. A dataset of 1,683 melon images was collected from a hydroponic farm and subsequently processed through annotation, preprocessing, and augmentation before being used for model training. Performance evaluation was conducted using mean Average Precision (mAP), precision, recall, F1-score, and accuracy. The experimental results demonstrated an accuracy of 92.42%, an F1-score of 0.890, and an mAP (0.5:0.95) of 0.828. The proposed system is capable of detecting melon objects and classifying maturity levels into three categories more objectively than traditional methods.Keywords: Machine Learning, Faster R-CNN, Melon Ripeness, Image Processing, Object Detection]]>
