In this work, we present a Physics-Informed Neural Network (PINN) framework for the classification of oil palm fresh fruit bunch (FFB) ripeness using RGB images. Unlike conventional Convolutional Neural Networks (CNNs) that learn solely from visual patterns, the proposed PINN integrates a physics-based index—derived from the red-to-green pixel intensity ratio—directly into the network architecture and loss function. This hybrid design embeds wavelength-dependent physical knowledge related to chlorophyll degradation during ripening, enabling the model to learn more robust and generalizable features even with limited and imbalanced training data. The PINN model achieves a peak accuracy of 0.73, outperforming the purely data-driven CNN baseline (0.68) by a margin of 5%. Overall, the PINN demonstrates superior performance in minority-class detection and maintains stable convergence under three different lighting conditions (different light spectra). These results highlight the effectiveness of integrating domain-specific physical insights into deep learning models, offering a promising pathway toward reliable, non-destructive, and automated ripeness assessment for agricultural applications.
Oil palm fresh fruit bunch (FFB) ripeness classification is essential for improving the oil extraction rate, oil quality, and mill processing efficiency. However, RGB-based classification is often limited by insufficient colour information from dark unripe fruitlets and shadowed regions of the bunch surface. This study evaluated the effect of image input representation on convolutional neural network (CNN)-based FFB ripeness classification. Four models with the same CNN architecture were compared using RGB, RGB + infrared (IR), CIEL*a*b*, and CIEL*a*b* + IR inputs. RGB and IR images were acquired using a dual-camera setup positioned 3 m from the FFB sample. The CIEL*a*b* + IR model achieved the best overall performance, with weighted-average precision, recall, and F1-score values of 0.84, 0.81, and 0.81, respectively, compared with 0.79, 0.76, and 0.76 for RGB-only. The addition of IR improved model performance by providing complementary near-infrared reflectance information, while CIEL*a*b* colour-space transformation provided a more discriminative colour representation. Class activation heat maps showed that the models focused mainly on fruitlet regions, with the CIEL*a*b* + IR model producing more distinct activation over ripeness-relevant areas. These findings demonstrate that the proposed four-channel CIEL*a*b* + IR image representation improves CNN-based FFB ripeness classification by combining lightness-separated colour information with near-infrared reflectance features, although underripe FFB remains challenging, where it produced the highest rate of false positives because of its transitional and heterogeneous characteristics.
In this work, a reflectance polarimetry imaging system based on liquid crystal polarization rotator is proposed for the assessment of ripening process of mangoes. A low-cost voltage-controlled liquid crystal polarization rotator and a wire-grid polarizer were integrated into input ray path of a digital camera, enabling selective acquisition of horizontally or vertically polarized (0° and 90°) input images. Unripe Chokanan mango samples were subjected to the illumination of linearly polarized LED light at different wavelength. Digital images at two polarization states were recorded daily until the mangoes were fully ripened on the eighth day. Average reflectance intensity and Degree of Linear Polarization (DoLP) and the findings indicate the dynamic correlation between the varying reflectance intensity, illumination wavelength and the associated dominant pigments (e.g. carotenoids, anthocyanins and chlorophylls) in the fruit epidermis during the ripening process. In addition, the DoLP at different wavelengths have shown different variation characteristics with ripening. Notably, DoLPs at 593 and 660 nm decrease with ripening, due to decreasing moisture content in the fruit epidermis that promises light scattering and depolarization in the epidermis tissues. The study demonstrates the potential of reflectance polarimetry as a non-invasive method for assessing the ripeness and storage condition of fruits.