Journal of Integrated Artificial Intelligence Science and Engineering

Classification of oil palm fresh fruit bunches utilising multiband optical sensors: A review

2025-02-08T14:58:02+07:00

Indonesia, as the world's largest palm oil producer, faces the challenge of improving crude palm oil production efficiency through the classification of fresh fruit bunch (FFB) maturity levels. This study aims to develop a FFB classification system using multiband optical sensors based on visible light and near-infrared spectra. A total of 191 FFB samples were classified into two categories, namely ripe and unripe, using the reflectance of the near-infrared (NIR) spectrum. Results show that the combination of visible and NIR spectra at a wavelength of 660 nm has high accuracy in detecting oil content in FFB. The classification model based on oil content showed an accuracy of 66.7%, better than the visual inspection model (52.1%). This study shows the great potential of optical sensor technology to improve the efficiency and quality of the palm oil industry in Indonesia.

Leveraging machine learning and image processing computer vision systems to detect defects and improve tomato quality: A review

2025-02-08T15:01:50+07:00

Computer vision is a technology that integrates image processing and machine learning to evaluate product quality objectively and non-destructively. This study establishes a computer vision system for defect detection and quality assessment of tomatoes by image processing methods and machine learning algorithms, including support vector machine and artificial neural network. The procedure commences with the collection of tomato photos, succeeded by pre-processing, segmentation, and the extraction of features related to colour, texture, and shape. Machine learning models are subsequently utilised to categorise tomatoes according to their ripeness levels and the existence of faults. The results indicate that the system can accurately detect flaws and evaluate the quality of tomatoes, demonstrating superior efficiency compared to manual techniques. This method is anticipated to enhance the uniformity of quality standards and diminish waste in the agriculture sector.

Detection of ripeness level of oil palm fresh fruit bunches using YOLOv4 model in automated harvesting system: A review

2025-07-12T11:43:34+07:00

This research discusses the development of an automated system for detecting ripe oil palm fruits (fresh fruit bunch, FFB) using computer vision and artificial intelligence (AI) technology. The main objective of this study is to improve efficiency and productivity in the oil palm harvesting process by adopting the latest technology. Several related studies have developed non-destructive methods for classifying the ripeness of FFB. This research utilizes the YOLOv4 deep learning model to detect ripe FFB in real-time. Visual data of FFB is obtained by capturing images using an Intel Realsense D435 camera on oil palm trees. The data is then labeled and divided into training and validation sets. Through evaluation, the YOLOv4 model with a network input size of 512 × 512 was found to be the best model for TBS detection task. The training process was conducted for 2000 iterations, achieving a mean average precision (mAP) of 87.9% in the final iteration. This model successfully detects ripe FFB with high accuracy. The results of this research indicate that the use of computer vision and artificial intelligence technology can help optimize the oil palm harvesting process. With this automated system, the palm oil industry can address labor shortages and improve production efficiency. This study provides an important contribution to the development of the oil palm industry with potential applications in broader fields.