TY - JOUR
T1 - Apple Surface Defect Detection Method Based on Weight Comparison Transfer Learning with MobileNetV3
AU - Si, Haiping
AU - Wang, Yunpeng
AU - Zhao, Wenrui
AU - Wang, Ming
AU - Song, Jiazhen
AU - Wan, Li
AU - Song, Zhengdao
AU - Li, Yujie
AU - Bação, Fernando
AU - Sun, Changxia
N1 - Si, H., Wang, Y., Zhao, W., Wang, M., Song, J., Wan, L., Song, Z., Li, Y., Bação, F., & Sun, C. (2023). Apple Surface Defect Detection Method Based on Weight Comparison Transfer Learning with MobileNetV3. Agriculture (Switzerland), 13(4), 1-26. [824]. https://doi.org/10.3390/agriculture13040824---This research is funded by the Henan Province Key Science-Technology Research Project under Grant No. 232102520006, the National Science and Technology Resource Sharing Service Platform Project under Grant No. NCGRC-2020-57.
PY - 2023/4/3
Y1 - 2023/4/3
N2 - Apples are ranked third, after bananas and oranges, in global fruit production. Fresh apples are more likely to be appreciated by consumers during the marketing process. However, apples inevitably suffer mechanical damage during transport, which can affect their economic performance. Therefore, the timely detection of apples with surface defects can effectively reduce economic losses. In this paper, we propose an apple surface defect detection method based on weight contrast transfer and the MobileNetV3 model. By means of an acquisition device, a thermal, infrared, and visible apple surface defect dataset is constructed. In addition, a model training strategy for weight contrast transfer is proposed in this paper. The MobileNetV3 model with weight comparison transfer (Weight Compare-MobileNetV3, WC-MobileNetV3) showed a 16% improvement in accuracy, 14.68% improvement in precision, 14.4% improvement in recall, and 15.39% improvement in F1-score. WC-MobileNetV3 compared to MobileNetV3 with fine-tuning improved accuracy by 2.4%, precision by 2.67%, recall by 2.42% and F1-score by 2.56% compared to the classical neural networks AlexNet, ResNet50, DenseNet169, and EfficientNetV2. The experimental results show that the WC-MobileNetV3 model adequately balances accuracy and detection time and achieves better performance. In summary, the proposed method achieves high accuracy for apple surface defect detection and can meet the demand of online apple grading.
AB - Apples are ranked third, after bananas and oranges, in global fruit production. Fresh apples are more likely to be appreciated by consumers during the marketing process. However, apples inevitably suffer mechanical damage during transport, which can affect their economic performance. Therefore, the timely detection of apples with surface defects can effectively reduce economic losses. In this paper, we propose an apple surface defect detection method based on weight contrast transfer and the MobileNetV3 model. By means of an acquisition device, a thermal, infrared, and visible apple surface defect dataset is constructed. In addition, a model training strategy for weight contrast transfer is proposed in this paper. The MobileNetV3 model with weight comparison transfer (Weight Compare-MobileNetV3, WC-MobileNetV3) showed a 16% improvement in accuracy, 14.68% improvement in precision, 14.4% improvement in recall, and 15.39% improvement in F1-score. WC-MobileNetV3 compared to MobileNetV3 with fine-tuning improved accuracy by 2.4%, precision by 2.67%, recall by 2.42% and F1-score by 2.56% compared to the classical neural networks AlexNet, ResNet50, DenseNet169, and EfficientNetV2. The experimental results show that the WC-MobileNetV3 model adequately balances accuracy and detection time and achieves better performance. In summary, the proposed method achieves high accuracy for apple surface defect detection and can meet the demand of online apple grading.
KW - deep learning
KW - defect detection
KW - image fusion
KW - transfer learning
KW - weight comparison
KW - WC-MobileNetV3
UR - http://www.scopus.com/inward/record.url?scp=85153788447&partnerID=8YFLogxK
UR - https://www.webofscience.com/wos/woscc/full-record/WOS:000977925800001
U2 - 10.3390/agriculture13040824
DO - 10.3390/agriculture13040824
M3 - Article
AN - SCOPUS:85153788447
SN - 2077-0472
VL - 13
SP - 1
EP - 26
JO - Agriculture (Switzerland)
JF - Agriculture (Switzerland)
IS - 4
M1 - 824
ER -