Banana fruits are typically harvested and transported while still green and hard, referred to as green bananas. However, frequent collisions often occur between fruit fingers, working parts, and adjacent fruit fingers during this stage. This study aims to investigate the mechanical properties of fruit fingers at different growth positions. The experimental material was selected as the finger of the banana plant (Musa spp.) on a supporting platform created by 3D printing technology. A complete factorial experiment was performed using a pendulum method. The test conditions included three impact energies (0.27, 0.52, and 0.88 J) and three repeated times (1, 5, and 10) across three growth positions (the inner rows of the first and second nodes, the outer rows of the first and second nodes, and the inner and outer rows of the last nodes) within a green banana bunch. Mechanical parameters were calculated, such as peak acceleration, coefficient of restitution (CoR), bruise area (BA), bruise volume (BV), and bruise susceptibility (BS). Among them, the BS represented the ratio of BV to the total absorbed impact energy. A multi-way analysis of variance was also conducted at a significance level of 5% to determine the statistical significance of the mean values of the parameters. The results demonstrated that there was a strong positive correlation between peak acceleration and bruise sizes, and a strong negative correlation between the CoR and BS. Specifically, the higher peak acceleration resulted in the more severe damage to the fruit fingers, whereas the smaller CoR made the green bananas more susceptible to damage. Moreover, the impact energy, repeated times, their interaction, and the location of banana growth significantly dominated the mechanical parameters of the BA, BV, and BS. The higher impact energy led to the greater peak acceleration, BA, BV, and BS, whereas, the lower CoR was observed. Consequently, the higher impact energy tended to increase the susceptibility of banana fruit to damage. Once the impact energy was below the threshold for the plastic deformation of green bananas, the peak acceleration and CoR were improved non-linearly with each impact up to the first five impacts, after which the increment decreased progressively for each subsequent impact. Similar trends were observed for the BA and BV, while the opposite was true for the BS. Therefore, the susceptibility of banana fruit decreased with the increasing impacts. It is challenging for the reduced number of impacts to less than five during production. Fruit damage can be minimized to reduce the energy required to hit the banana fingers. Once the impact energy exceeded the threshold, an initial increase in the peak acceleration and CoR was followed by a decrease, due to the plastic deformation and ductile fracture of the banana finger from continued impacts. Both BV and the rate of increase were enhanced with the number of repetitions. Furthermore, the BS of banana fingers in the outer row was generally smaller than that in the inner row, indicating that the inner row was more susceptible to impact-induced bruise damage. These findings can provide a strong reference to managing the protective measures and risk factors during banana harvesting and transportation.

Conventional estimation of banana hands and fingers has often been confined to the complex, interlocked structures and frequent occlusions impeding. This research aims to develop a non-destructive, accurate, and rapid estimation of the mass of the entire banana hands and individual fingers. Imaging and computational techniques were also selected as an alternative to the manual or inadequate automated approaches. The more efficient post-harvest processing and grading were facilitated in the banana industry. Firstly, the morphology and geometry were acquired to predict the mass. The registered color and depth (RGB-D) images of the banana hands were captured from the convex and concave viewpoints using a controlled laboratory setup. Secondly, the individual fingers were then precisely segmented using the Segment Anything Model (SAM), a zero-shot instance segmentation. The occlusions were also managed without requiring the task-specific training datasets. The depth information was acquired to convert into the three-dimensional (3D) point clouds. The computational efficiency was then optimized using voxel grid down-sampling. The statistical outlier was also removed for the data integrity. Thirdly, the comprehensive features were extracted from the color images, including the two-dimensional (2D) morphology and size descriptors (such as pixel area, contour perimeter, and aspect ratio). The 3D geometric properties (including principal dimensions, surface area, and convex hull volume) were obtained from the processed point clouds. These multi-modal features were generated for the whole banana hands and each segmented finger. Finally, the mass prediction models were developed with a multiple linear regression (MLR) model as a baseline. Five non-linear machine learning algorithms were also used, including support vector regression (SVR), k-nearest neighbors (KNN), gradient boosting (GB), random forest (RF), and backpropagation neural network (BPNN). Model performance was assessed using R², RMSE (root mean squared error), and MAPE (mean absolute percentage error). Furthermore, the importance analysis was carried out to eliminate the recursive features, thus focusing primarily on the RF model. The influential predictors were then identified to construct and optimize the models. The comparative analysis showed that the RF model outperformed the rest. The non-linear approaches were then required to capture the relationships between extracted features and banana mass. In the mass estimation of the whole banana hand, the concave view was achieved in better performances (R² = 0.984, RMSE = 77.78 g, and MAPE=5.37%) with the RF model after optimization. The 3D features, particularly surface area and convex hull volume, were the most critical for the accurate prediction of the hand mass. In individual finger mass, the RF model was more accurate for the exposed outer fingers (viewed convexly; optimized RF: R² = 0.794, RMSE = 13.14 g, MAPE = 6.12%) than that for the occluded inner fingers (viewed concavely; optimized RF: R² = 0.668, RMSE = 17.47 g, MAPE = 9.07%). Interestingly, the 2D features (like pixel area and contour perimeter) dominated the mass prediction on the outer fingers. There was the differential feature importance of the finger position and visibility. Two strategies of mass estimation were also evaluated: An average finger mass was calculated (from the predicted total hand mass divided by actual finger count), and then directly predicted the individual finger mass. Both derived average finger mass (using the best hand model) and directly predicted outer finger mass was achieved with high accuracy (relative error <10% for ~80% of samples). The average mass method was better suited to assess the overall quality. While the direct prediction was offered the detailed data for accessible outer fingers. The computational efficiency showed that the direct estimation of the finger mass was faster (~7.7 s per hand), including the SAM segmentation step (~1 s), compared with the average mass estimation on the complex point cloud of the entire hand (~76.6 s per hand). The 3D features were calculated from the multiple simple point clouds which the less computationally demanding than those from single, large, and intricate ones. There was the "divide and conquer" benefit from the SAM-based segmentation. The RGB-D imaging and machine learning were integrated to validate the accurate, non-destructive mass determination of the banana hands and fingers. The utility of the SAM was obtained for the complex fruit segmentation in the agricultural contexts. The RF was the better modeling choice than the rest. Differential contributions of the 2D and 3D features were gained to quantify the varying viewpoint impacts. The direct estimation of the individual finger can offer detailed information and higher computational efficiency than before. The banana grading can also be developed to enhance post-harvest operations. While the 3D feature computation from the complex point clouds can be identified as the primary bottleneck in real-time industrial applications.