Design and Experimentation of a Machine Vision-Based Cucumber Quality Grader

Abstract

The North China type cucumber, characterized by its dense spines and top flowers, is susceptible to damage during the grading process, affecting its market value. Moreover, traditional manual grading methods are time-consuming and labor-intensive. To address these issues, this paper proposes a cucumber quality grader based on machine vision and deep learning. In the electromechanical aspect, a novel fixed tray type grading mechanism is designed to prevent damage to the vulnerable North China type cucumbers during the grading process. In the vision grading algorithm, a new convolutional neural network is introduced named MassNet, capable of predicting cucumber mass using only a top-view image. After obtaining the cucumber mass prediction, mass grading is achieved. Experimental validation includes assessing the electromechanical performance of the grader, comparing MassNet with different models in predicting cucumber mass, and evaluating the online grading performance of the integrated algorithm. Experimental results indicate that the designed cucumber quality grader achieves a maximum capacity of 2.3 t/hr. In comparison with AlexNet, MobileNet, and ResNet, MassNet demonstrates superior cucumber mass prediction, with a MAPE of 3.9% and RMSE of 6.7 g. In online mass grading experiments, the grading efficiency of the cucumber quality grader reaches 93%.

An Improved Method for Detecting Crane Wheel–Rail Faults Based on YOLOv8 and the Swin Transformer

“…It might encounter issues such as missed detection or imprecise localization when handling small objects or densely populated target areas within a scene. Therefore, recent advancements in the YOLO algorithm, namely YOLOv3 [14], YOLOv4 [15] and subsequent versions [16][17][18][19], aim to enhance detection accuracy and robustness by implementing novel techniques and optimization strategies, thereby striving for improved performance across diverse scenarios. The recently introduced YOLOv8 [20] adopts a streamlined model structure, augmented convolutional kernels, accelerated convolutional operations and a more concise architecture, resulting in swifter inference compared to its predecessors in the YOLO series.…”