Apple Grading Method Design and Implementation for Automatic Grader Based on Improved YOLOv5

Abstract

Apple grading is an essential part of the apple marketing process to achieve high profits. In this paper, an improved YOLOv5 apple grading method is proposed to address the problems of low grading accuracy and slow grading speed in the apple grading process and is experimentally verified by the designed automatic apple grading machine. Firstly, the Mish activation function is used instead of the original YOLOv5 activation function, which allows the apple feature information to flow in the deep network and improves the generalization ability of the model. Secondly, the distance intersection overUnion loss function (DIoU_Loss) is used to speed up the border regression rate and improve the model convergence speed. In order to refine the model to focus on apple feature information, a channel attention module (Squeeze Excitation) was added to the YOLOv5 backbone network to enhance information propagation between features and improve the model’s ability to extract fruit features. The experimental results show that the improved YOLOv5 algorithm achieves an average accuracy of 90.6% for apple grading under the test set, which is 14.8%, 11.1%, and 3.7% better than the SSD, YOLOv4, and YOLOv5s models, respectively, with a real-time grading frame rate of 59.63 FPS. Finally, the improved YOLOv5 apple grading algorithm is experimentally validated on the developed apple auto-grader. The improved YOLOv5 apple grading algorithm was experimentally validated on the developed apple auto grader. The experimental results showed that the grading accuracy of the automatic apple grader reached 93%, and the grading speed was four apples/sec, indicating that this method has a high grading speed and accuracy for apples, which is of practical significance for advancing the development of automatic apple grading.

Deep learning-based method for real-time spinach seedling health monitoring

“…The study adopted hybrid fusion enhancement to expand the spinach seedling dataset to improve the robustness of the model. It included five data enhancement operations, including brightness enhancement, horizontal flipping, rotation, colored jitter, 19 and Mixup algorithm. Data enhancement methods for spinach seedlings was shown in Fig.…”

Optimal Routing and Charging Strategy of Electric Vehicles Based on Traffic Flow Prediction

“…This not only reduces the road operational efficiency but also increases the pressure on traffic management personnel [3,4]. Alleviating traffic congestion has become one of the most challenging issues in providing efficient traffic management and convenient travel experiences [5][6][7].…”

Detection of early bruises on apples using near‐infrared camera imaging technology combined with adaptive threshold segmentation algorithm

“…The mAP was 17.45% higher than the baseline model YOLOv4‐tiny. In order to achieve accurate and fast apple grading, Xu et al (2023) improved the generalization ability, convergence speed and feature extraction ability of YOLOv5s model, with the grading accuracy of 93% and the grading speed of four apples per second. Yang, Yuan, et al (2023) proposed an improved YOLOv7 model which was inserted the CSPResNeXt‐50 module and VoVGSCSP module, further improving the detection accuracy and speed for maize pests, with mAP reaching 76.3% and the detection speed reaching 67 frames per second (FPS).…”