Abstract
The doping rate is one of the important indexes to evaluate the quality grade and price of wheat. In order to accurately and quickly recognize impurities (wheat husk) in wheat grains, images of doped wheat were collected and Convolutional Neural Network (CNN) was used to realize the classification and recognition of grains and impurities in wheat grains. In this study, image segmentation and image enhancement were used to preprocess the acquired images to establish the image database of wheat grains and impurities. According to the characteristics of image data, the classic CNN, VGGNet and ResNet network models for wheat impurity images recognition were established. Simulation analysis shows that, compared with the classical CNN and VGGNet network models, the ResNet network model has the best recognition performance. The recognition accuracy of the test set is 96.94%, the recognition time is 5.60 ms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Standardization Administration of China. GB 1351-2008 Wheat. Standards Press of China, Beijing (2001)
Yafei, X., Defu, R., Zhijun, Q., Xianping, Y., Haiquan, H.: Study on the detection method of impurity in imported grain crops. J. Agric. Process. (Acad.) 08, 135–136 (2012)
Zhang, B.: Research on wheat appearance quality detection by machine vision based on deep learning. Northwest A&F University (2019)
Yurong, Z., Saisai, C., Xianqing, Z.: Advances in wheat image detection technology. J. Chin. Cereals Oils Assoc. 29(04), 118–123 (2014)
Chemists A: Cereal Chem 1989 | Discrimination of Wheat and Nonwheat Components in Grain Samples by Image Analysis. Publications (1989)
Chen, S.S.: Research on machine vision technology for wheat quality index, Henan University of Technology (2014)
Jayas, D.S., Visen, N.S., Paliwal, J., et al.: Cereal grain and dockage identification using machine vision. Biosys. Eng. 85(1), 51–57 (2003)
Su, Y.N.: Study on detection of water content and identification of impurity and imperfect grain based on machine vision and hyperspectral image technology, Zhejiang University (2011)
Ferentinos, K.P.: Deep learning models for plant disease detection and diagnosis. Comput. Electron. Agric. 145, 311–318 (2018)
Zhang, S., Huang, W., Zhang, C.: Three-channel convolutional neural networks for vegetable leaf disease recognition. Cogn. Syst. Res. 53(JAN), 31–41 (2019)
Arnal, B.: Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification. Comput. Electron. Agric. 153, 46–53 (2018)
Alvaro, F., Sook, Y., Sang, K., et al.: A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition. Sensors 17(9), 2022 (2017)
Artzai Picon, A., et al.: Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild. Comput. Electron. Agric. 161, 280–290 (2019)
Yang, L., et al.: Identification of rice diseases using deep convolutional neural networks. Neurocomputing 267, 378–384 (2017)
Rangarajan, A.K., Purushothaman, R., Ramesh, A.: Tomato crop disease classification using pre-trained deep learning algorithm. Procedia Comput. Sci. 133, 1040–1047 (2018)
Funding
This research was financially supported by National Science Foundation of China (61871176): Research of Abnormal Grain Conditions Detection using Radio Tomographic Imaging based on Channel State Information; National Science Foundation of China (61901159): Research on Beamspace Channel Estimation in Massive MIMO Systems by Fusing Multi-Dimensional Characteristic Information; Applied research plan of key scientific research projects in Henan colleges and Universities (19A510011): Research of Abnormal Grain Conditions Detection Based on Radio Tomographic Imaging based on RSSI; Scientific Research Foundation Natural Science Project In Henan University of Technology (2018RCJH18): Research of Abnormal Grain Conditions Detection using Radio Tomographic Imaging based on Received Signal Strength Information; the Innovative Funds Plan of Henan University of Technology Plan (2020ZKCJ02): Data-Driven Intelligent Monitoring and Traceability Technique for Grain Reserves.
Author information
Authors and Affiliations
Contributions
Chunhua Zhu and Tiantian Miao proposed the original idea and Tiantian Miao carried out the experiment. Chunhua Zhu and Tiantian Miao wrote the paper. Tiantian Miao supervised and reviewed the manuscript. All authors read and approved the final manuscript.
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
The authors declare no conflict of interest.
Rights and permissions
Copyright information
© 2022 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Zhu, C., Miao, T. (2022). Research on Wheat Impurity Image Recognition Based on Convolutional Neural Network. In: Xiang, W., Han, F., Phan, T.K. (eds) Broadband Communications, Networks, and Systems. BROADNETS 2021. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 413. Springer, Cham. https://doi.org/10.1007/978-3-030-93479-8_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-93479-8_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93478-1
Online ISBN: 978-3-030-93479-8
eBook Packages: Computer ScienceComputer Science (R0)