Journal of Integrated Artificial Intelligence Science and Engineering

Utilizing computer vision for the detection, classification, and mapping of coffee cherries during the harvest: A review

2025-02-08T14:35:43+07:00

Computer vision is a technology that integrates image processing and pattern recognition to extract information from digital images. This research uses the you only look once (YOLO) method to detect, classify, and map the maturity stage of coffee fruit during harvest. The YOLOv3-tiny model was applied to classify coffee fruits into three categories including unripe, ripe, and overripe. Results showed an average precision of 86.0%, 85.2%, and 80.0%, respectively. The system enables more efficient harvest management by utilizing spatial and temporal information for coffee fruit quality mapping. This mapping can help farmers reduce operational costs and improve efficiency through the application of precision farming techniques. This technology proves great potential in improving the quality and quantity of coffee yields with a fast and accurate computer-based approach.

Combination of computer vision and laser-light backscattering imaging for oil palm fruit ripeness classification: A review

2025-02-08T14:41:50+07:00

Laser-light backscattering imaging (LLBI) is an optical imaging technique that records the interaction of light with plant tissue, generating light reflection data relevant for assessing product quality. This research combines LLBI and an RGB-based computer vision system to non-destructively classify the maturity level of oil palm fresh fruit bunches. This technique offers a faster, more cost-effective and more accurate solution than traditional methods. The analysis includes RGB imaging and light reflection, where parameters such as color intensity, principal axis length, and area are analyzed using image processing algorithms. Results showed that the combination of LLBI and a computer vision system significantly improved the accuracy of ripeness classification, with a strong correlation between imaging parameters and quality attributes such as oil content and color. This approach provides an important step in improving harvesting efficiency and the production of high-quality palm oil.

Thermal imaging as an indicator of oil palm fresh fruit bunches: A review

2025-02-08T14:55:51+07:00

Thermal imaging is a non-contact, non-destructive method that records infrared radiation from the surface of an object to produce a temperature image. This research examines the use of thermal imaging alongside machine learning techniques, namely k-nearest neighbor (kNN) and artificial neural networks (ANN), to classify the maturity level of oil palm fresh fruit bunches. Thermal imaging data were analyzed to obtain the temperature difference as the main indicator in classifying the unripe, ripe, and overripe categories. Results showed that ANN provided higher classification accuracy (92.5% on test) than kNN (74.2% on test). Both methods proved the effectiveness of rapid, non-contact, and non-destructive ripeness assessment. These findings highlight the potential of integrating thermal imaging with advanced computational approaches to improve efficiency and accuracy in agricultural applications.