Mix Convolutional Neural Networks for Hyperspectral Wheat Variety
Discrimination
LI Guo-hou1, LI Ze-xu1, JIN Song-lin1, ZHAO Wen-yi2, PAN Xi-peng3, LIANG Zheng4, QIN Li5, ZHANG Wei-dong1*
1. College of Information Engineering, Henan Institute of Science and Technology, Xinxiang 453003, China
2. Artificial Intelligence Academy, Beijing University of Posts and Telecommunications, Beijing 100876, China
3. College of Computer and Information Security, Guilin University of Electronic Science and Technology, Guilin 541004, China
4. Internet Academy, University of Anhui, Hefei 230039, China
5. Faculty of Electrical Engineering Computer Science, Ningbo University, Ningbo 315211, China
Abstract Different varieties of wheat meet the market's diverse needs, but it also brings the risk of mixed wheat varieties. To improve the purity of wheat varieties and thus the economic value of the selection, breeding, and processing, the identification of wheat seeds plays a key role. Traditional methods of physical and chemical analysis of wheat variety purity take a long time to identify and destroy seeds, which can no longer meet the urgent needs of modern agriculture. Hyperspectral imaging is a new, fast, efficient, and nondestructive identification technique that has achieved remarkable results in seed variety identification. Unfortunately, most existing methods use only spectral information without considering spatial information sufficiently to produce unsatisfactory classification results. A hyperspectral imaging device was used to acquire hyperspectral images of the front and back of wheat seeds of eight varieties in the paper. Meanwhile, we propose a hyperspectral wheat variety identification method based on a hybrid convolutional neural network with an attention mechanism, which mainly uses the advantageous complementary features of 3D convolution and 2D convolution to extract valuable features of wheat for driving the identification of wheat varieties. Precisely, we first extract the regions of interest of wheat varieties and use multiple scattering correction methods to weaken the spectral differences of the same variety due to differences in scattering levels. Meanwhile, we use principal component analysis to reduce the useless spectral bands of 3D data and thus retain and compress the valuable features for identifying wheat varieties. Subsequently, a 3D convolution module acquires spatial dimension and feature information between different spectra, a 2D convolution module is used to obtain spatial features and the image's inherent feature information, and an attention mechanism is introduced into the 2D convolution model to refine the features. Finally, the identification of different wheat varieties in the same region is achieved at the fully connected layer. Extensive experiments on our collected dataset show that the proposed method performs better than the state-of-the-art methods, and its classification accuracy reaches 97.92%. Besides, the proposed method has better classification performance for a small sample. In short, the proposed method has good effectiveness and robustness for hyperspectral wheat seed identification and provides a new method for the online identification of wheat seeds.
[1] Sun Ke, Wang Zhengjie, Tu Kang, et al. Scientific Reports, 2016, 6(1): 37994(https:doi.org/10.1038/srep37994).
[2] Jin Songlin, Zhang Weidong, Yang Pengfei, et al. Computers and Electrical Engineering, 2022, 101: 108077.
[3] Huang Min, Tang Jinya, Yang Bao, et al. Computers and Electronics in Agriculture, 2016, 122: 139.
[4] Jin Baichuan, Zhang Chu, Jia Liangquan, et al. ACS Omega, 2022, 7(6): 4735.
[5] Wei Yanlin, Li Xiaofeng, Pan Xin, et al. Sensors, 2020, 20(23): 6980.
[6] ZHU Qi-bing, FENG Zhao-li, HUANG Min, et al(朱启兵，冯朝丽，黄 敏，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2013, 33(2): 517.
[7] Sivakumar Mahesh, Jayas Digvir S, Paliwal Jitendra, et al. Transactions of the ASABE, 2014, 57(1): 63.
[8] Fabiyi Samson Damilola, Vu Hai, Tachtatzis Christos, et al. IEEE Access, 2020, 8: 22493.
[9] Miao Aimin, Zhuang Jiajun, Tang Yu, et al. Sensors, 2018, 18(12): 4391.
[10] Wang L, Pang L, Yan L, et al. Journal of Applied Spectroscopy, 2022, 89(1): 84.
[11] Sivakumar Chitra, Chaudhry Muhammad Mudassir Arif, Paliwal Jitendra. LWT, 2022, 154: 112799.
[12] Shao Yuanyuan, Shi Yukang, Xuan Guantao, et al. Vibrational Spectroscopy, 2022, 118: 103340.
[13] ZHANG Hang, YAO Chuan-an, JIANG Meng-meng, et al(张 航，姚传安，蒋梦梦，等). Journal of Triticeae Crops(麦类作物学报), 2019, 39(1): 96.
[14] Nie Pengcheng, Zhang Jinnuo, Feng Xuping, et al. Sensors and Actuators B: Chemical, 2019, 296: 126630.
[15] Zhao Xin, Que Haotiao, Sun Xiulan, et al. Infrared Physics & Technology, 2022, 125: 104270.
[16] Wu Na, Weng Shizhuang, Chen Jinxin, et al. Computers and Electronics in Agriculture, 2022, 196: 106850.
[17] Gai Zhaodong, Sun Laijun, Bai Hongyi, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2022, 279: 121432.
[18] Liu Hongyu, Qu Fuheng, Yang Yong, et al. Journal of Physics: Conference Series, 2022, 2284(1): 012017.
[19] Hao Jie, Dong Fujia, Li Yalei, et al. Infrared Physics & Technology, 2022, 125: 104286.
[20] Ji Shuiwang, Xu Wei, Yang Ming, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 35(1): 221.
[21] Woo Sanghyun, Park Jongchan, Lee Joon-Young, et al. CBAM: Convolutional Block Attention Module，European Conference on Computer Vision, 2018. 3.
[22] Chen Yingnong, Thaipisutikul Tipajin, Han Chinchuan, et al. Remote Sensing, 2021, 13(1): 130.
[23] Liu Ziwei, Jiang Jinbao, Du Ying, et al. IEEE Access, 2021, 9: 147527.
[24] Tang Haojin, Huang Zhiquan, Li Yanshan, et al. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 1.
[25] Li Qiaosi, Wong Frankie Kwan Kit, Fung Tung. Remote Sensing of Environment, 2021, 258: 112403.
[26] LI Guan-dong, ZHANG Chun-ju, GAO Fei, et al(李冠东, 张春菊, 高 飞, 等). Chinese Journal of Graphical Imagery(中国图象图形学报), 2019, 24(4): 639.
[27] Paoletti Mercedes E, Haut Juan Mario, Fernandez-Beltran Ruben, et al. IEEE Transactions on Geoscience and Remote Sensing, 2018, 57(2): 740.
[28] Roy S K, Krishna G, Dubey S R, et al. IEEE Geoscience and Remote Sensing Letters, 2019, 17(2): 277.
