Automatic Detection of Small Sample Apple Surface Defects Using ASDINet
Author:
Hu Xiangyun1, Hu Yaowen1, Cai Weiwei2ORCID, Xu Zhuonong1ORCID, Zhao Peirui3, Liu Xuyao1, She Qiutong3, Hu Yahui4, Li Johnny5ORCID
Affiliation:
1. College of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha 410004, China 2. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China 3. College of Food Science and Engineering, Central South University of Forestry and Technology, Changsha 410004, China 4. Plant Protection Research Institute, Academy of Agricultural Sciences, Changsha 410125, China 5. Department of Soil and Water Systems, University of Idaho, Moscow, ID 83844, USA
Abstract
The appearance quality of apples directly affects their price. To realize apple grading automatically, it is necessary to find an effective method for detecting apple surface defects. Aiming at the problem of a low recognition rate in apple surface defect detection under small sample conditions, we designed an apple surface defect detection network (ASDINet) suitable for small sample learning. The self-developed apple sorting system collected RGB images of 50 apple samples for model verification, including non-defective and defective apples (rot, disease, lacerations, and mechanical damage). First, a segmentation network (AU-Net) with a stronger ability to capture small details was designed, and a Dep-conv module that could expand the feature capacity of the receptive field was inserted in its down-sampling path. Among them, the number of convolutional layers in the single-layer convolutional module was positively correlated with the network depth. Next, to achieve real-time segmentation, we replaced the flooding of feature maps with mask output in the 13th layer of the network. Finally, we designed a global decision module (GDM) with global properties, which inserted the global spatial domain attention mechanism (GSAM) and performed fast prediction on abnormal images through the input of masks. In the comparison experiment with state-of-the-art models, our network achieved an AP of 98.8%, and a 97.75% F1-score, which were higher than those of most of the state-of-the-art networks; the detection speed reached 39ms per frame, achieving accuracy-easy deployment and substantial trade-offs that are in line with actual production needs. In the data sensitivity experiment, the ASDINet achieved results that met the production needs under the training of 42 defective pictures. In addition, we also discussed the effect of the ASDINet in actual production, and the test results showed that our proposed network demonstrated excellent performance consistent with the theory in actual production.
Funder
Scientific Research Project of Education Department of Hunan Province Changsha Municipal Natural Science Foundation Natural Science Foundation of Hunan Province Natural Science Foundation of China Hunan Key Laboratory of Intelligent Logistics Technology
Subject
Plant Science,Health Professions (miscellaneous),Health (social science),Microbiology,Food Science
Reference57 articles.
1. FAO (2021). World Food and Agriculture—Statistical Yearbook 2021, FAO. 2. Correlation of production constraints with the yield gap of apple cropping systems in Luochuan County, China;Zhang;J. Integr. Agric.,2019 3. Huang, K., Tian, Y., Tan, J., Salvi, D., Karwe, M., and Nitin, N. (2020). Role of contaminated organic particles in cross-contamination of fresh produce during washing and sanitation. Postharvest Biol. Technol., 168. 4. Singh, R.P., and Anderson, B.A. (2004). Understanding and Measuring the Shelf-Life of Food, Elsevier. 5. Recent developments in novel shelf life extension technologies of fresh-cut fruits and vegetables;Ma;Trends Food Sci. Technol.,2017
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|