|
|
|
|
|
|
| Non-Destructive Detection of Soybean Seed Thermal Damage Based on
Hyperspectral Imaging and MSC1DCNN |
| TAN Ke-zhu1, SUN Wei-qi1, ZHUO Zong-hui1, LI Kai-nuo1, ZHANG Xi-hai1, 2*, YAN Chao3* |
1. College of Electrical Engineering and Information, Northeast Agricultural University, Harbin 150030，China
2. National Key Laboratory of Smart Farm Technology and System, Northeast Agricultural University, Harbin 150030, China
3. College of Agriculture, Northeast Agricultural University, Harbin 150030, China
|
|
|
|
|
Abstract Soybean seeds are prone to heat damage due to improper storage and transportation. Heat damage affects the seed quality and germination rate, making it crucial to accurately detect heat-damaged soybean seeds for improving seed quality and agricultural production. This paper proposes a non-destructive detection method for heat-damaged soybean seeds based on hyperspectral imaging and a Multi-scale Cross-channel One-dimensional Convolutional Neural Network (MSC1DCNN). Firstly, hyperspectral imaging systems were used to capture spectral data of soybean seeds in the 400～1 000 nm wavelength range. The spectral curves of different heat-damaged soybean seeds (normal, mild heat damage, and severe heat damage) were compared and analyzed. It was found that the spectral reflectance in the 420～500 nm blue light region and the 750～1 000 nm near-infrared region gradually increased with the degree of heat damage. These spectral variations provided effective spectral features for subsequent heat damage detection. Secondly, the MSC1DCNN model was applied for classification. The model achieved an accuracy, recall, and F1 score of 99.07% on the test set, outperforming Support Vector Classification (SVC) (F1 score of 88.32%), k-Nearest Neighbor (KNN) (F1 score of 84.39%), and One-dimensional Convolutional Neural Network (1D CNN) (F1 score of 92.90%). Notably, the MSC1DCNN model had a misclassification rate of 1.39% in distinguishing mild heat-damaged seeds from normal seeds, which was significantly lower than SVC (12.04%), KNN (15.74%), and 1D CNN (9.72%). Finally, a germination experiment was conducted to verify the effect of heat damage on the germination rate of soybean seeds. The experimental results demonstrated that heat damage significantly reduced the germination rate of soybean seeds, further confirming the potential harm of heat damage to soybean growth. In conclusion, the MSC1DCNN model proposed in this study offers an effective solution for the non-destructive detection of heat-damaged soybean seeds, providing new insights for seed quality detection and automated screening.
|
|
Received: 2025-02-05
Accepted: 2025-06-27
|
|
|
|
Corresponding Authors:
ZHANG Xi-hai, YAN Chao
E-mail: xhzhan@neau.edu.cn；yanchao504@126.com
|
|
[1] National Bureau of Statistics(国家统计局). China Statistis Yearbook(中国统计年鉴). Beijing: China Statistics Press(北京：中国统计出版社), 2024.
[2] Lima R E, Coradi P C, Rodrigues D M, et al. Journal of Stored Products Research, 2024, 108: 102386.
[3] General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China(中华人民共和国国家质量监督检验检疫总局). GB 4404.2—2010—Seeds of Food Crops Part 2: Legume(GB 4404.2—2010—粮食作物种子第2部分: 豆类), 2010.
[4] XIA Xiao-yu, ZHU Ying, HUANG Yu-yang, et al(夏晓雨, 朱 颖, 黄雨洋, 等). Soybean Science(大豆科学), 2024, 43(5): 648.
[5] General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China(中华人民共和国国家质量监督检验检疫总局). GB/T 7415—2008—Seed Storage of Agricultural Crops(GB/T 7415—2008—农作物种子贮藏), 2008.
[6] CHEN Ping, HE Hong-zhou, SHAN Zhen-ju, et al(陈 萍, 何洪洲, 单振菊, 等). China Oils and Fats(中国油脂), 2015, 40(10): 31.
[7] Staton M J. Reducing Soybean Harvest Losses. In Encyclopedia of Digital Agricultural Technologies. Springer International Publishing，2023.
[8] HUANG Zhen(黄 振). Agricultural Engineering(农业工程), 2016, 6(5): 57.
[9] Zhu D, Guan D, Fan B, et al. LWT, 2022, 171: 114136.
[10] LIU Hong-chao，LI Jun, WANG Bu-jun(刘宏超，李 俊，王步军). China Oils and Fats(中国油脂), 2021, 46(1): 38.
[11] Hartman G L, West E D, Herman T K. Food Security, 2011, 3: 5.
[12] Ministry of Agriculture and Rural Affairs of the People's Republic of China(中华人民共和国农业农村部). NY/T 1599—2008—Determination of Heat Damage Kernel of Soybean(NY/T 1599—2008—大豆热损伤率的测定), 2008.
[13] Jeong S W, Lyu J Il, Jeong H W, et al. Plant Cell Reports, 2024, 43(7): 164.
[14] Furlanetto R H, Crusiol L G T, Nanni M R, et al. Remote Sensing, 2024, 16(11): 1900.
[15] Xiao D Y, Zhang L. Sensors and Actuators: A. Physical, 2024, 374: 115470.
[16] GAO Yan-xia, HU Chang-biao(高艳霞, 胡昌标). Computer and Modernization(计算机与现代化), 2011, 7(7): 88.
[17] ZHU Ya-qi(朱亚琪). Modern Food(现代食品), 2024, 30(2): 8.
[18] ZHANG Yu-rong, DENG Yi-hao, CHU Hong-qiang, et al(张玉荣, 邓毅浩, 褚洪强, 等). Journal of Henan University of Technology(Natural Science Edition)[河南工业大学学报(自然科学版)], 2023, 44(6): 105.
[19] Zheng L, Zhao M Y, Zhu J C, et al. Frontiers in Plant Science, 2023, 13: 1098864.
[20] LIU Cheng-liang, LIN Hong-zhen, LI Yan-ming, et al(刘成良, 林洪振, 李彦明, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2020, 51(1): 1.
[21] ZHAO Li-xin, HOU Fa-dong, LÜ Zheng-chao, et al(赵立新, 侯发东, 吕正超, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2020, 36(7): 184.
[22] LI Bin, ZHANG Feng, YIN Hai, et al(李 斌, 张 烽, 殷 海, 等). Spectroscopy and Spectral Analysi(光谱学与光谱分析), 2023, 43(2): 435.
[23] LI Miao, WANG Jing-xian, LI Hua-long, et al(李 淼, 王敬贤, 李华龙, 等). Smart Agriculture(智慧农业), 2019, 1(3): 46.
[24] XIE Jin-feng, CHEN Tao(谢金凤, 陈 涛). National Remote Sensing Bulletin, 2024, 28(1): 142.
[25] HUANG Xiao-yu, ZHANG Cong, CHEN Xiao-ling(黄晓宇, 张 聪, 陈晓玲). Journal of Chinese Agricultural Mechanization(中国农机化学报), 2024, 45(7): 194.
[26] SUN Jun, WU Zhao-qi, JIA Yi-lin, et al(孙 俊, 吴兆祺, 贾忆琳, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2023, 39(18): 192.
[27] XIA Yu, MENG Jing-wu, LUO Bin, et al(夏 宇, 孟静武, 罗 斌, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2024, 40(16): 261.
[28] QI Hao, LÜ Liang-jie, SUN Hai-fang, et al(齐 浩, 吕亮杰, 孙海芳, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2024, 55(7): 260.
[29] Yang Y, Liao J X, Li H B, et al. Spectroscopy Letters, 2023, 56(1): 28.
[30] WANG Sheng-nan, TAN Yong, LIU Chun-yu, et al(王盛楠, 谭 勇, 刘春宇, 等). Journal of Sensor Technology and Application(传感器技术与应用), 2022, 10(2): 177.
[31] QIN Li-feng, ZHANG Xi, ZHANG Xiao-qian(秦立峰, 张 熹, 张晓茜). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2020, 51(11): 212.
[32] Zhao J J, Wei F Y, Xu C. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024: 17416.
[33] Sapkota R, Flores-Calero M, Qureshi R, et al. Artificial Intelligence Review, 2025, 58: 274.
[34] Yang F C, Huang L D, Tan X W, et al. Signal, Image and Video Processing, 2024, 18(1): 173.
[35] Gao S H, Cheng M M, Zhao K, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(2): 652.
[36] Motamedi M, Haghighi M, Goli A. Scientia Horticulturae, 2019, 249: 306.
[37] Zhang J, Wang J, Li M, et al. Food Research International, 2022, 155: 111115. |
| [1] |
DAI Jing-jing1, 2*, LIU Zhi-bo2*, BAI Long-yang2, SONG Yang1, 2, WANG Nan2, CHEN Wei1, 2, YUAN Chang-jiang3. Hyperspectral Prospecting Enlightenment of the Luobu Mineralization Site in Tibet[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2849-2855. |
| [2] |
LI Chang-sheng, GAO Shu-hui*, LI Kai-kai. Feature Analysis and Classification of the Line-Crossing Sequences
Between Stamp Inks and Laser Printing Toner Based on
Hyperspectral Techniques[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2804-2815. |
| [3] |
WEI Wei1, WANG Dan2, WANG Bo-tao3, TAN Zuo-jun1, LIU Quan1, XIE Jing1*. Research on the Inversion of Moisture Content in Rapeseed Silique Peel Based on Hyperspectral Fusion Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2863-2874. |
| [4] |
WANG Jie1, SUN Xiao-lin2*, WU Dan-hua3, ZHOU Ya-nan1, LIU Chang4, CAO Yue4, TANG Ye-tao4, ZHANG Mei-wei1, WANG Xiao-qing1, ZENG Ling-tao1, CUI Yu-pei1. Prediction of Soil Organic Matter for Farmlands Covered With High
Density of Vegetation Based on UAV Hyperspectral Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2885-2896. |
| [5] |
YANG Guang1, HU Hao-wen1, JIN Chun-bai1, REN Chun-ying2*, WANG Long-guang1, WANG Qi1, LIU Wen-jing1*. Research on the Selection Method of Visually Significant Band for Ground Object Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2950-2959. |
| [6] |
LIU En-qin1, 2, HUANG Wei3, XU Yong3, YANG Man2, GAO Bing2, MO Ding-ru4. Hyperspectral Camouflaged Identification Driven by Spatial-Spectral
Characteristics[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2942-2949. |
| [7] |
ZHU Shi-hao1, FENG Jie1*, LI Xin-ting1, SUN Li-cun1, LIU Jie2, YUAN Ping1, YANG Ren-xiang1, DENG Hong-yang1. Reconstruction of Chinese Paintings Based on Hyperspectral Image
Fusion Using Res-CAE Deep Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(09): 2428-2436. |
| [8] |
BU Zi-chuan, LIU Ji-hong*, REN Kai-li, LIU Chi, ZHANG Jia-geng, YAN Xue-wen. Raman Spectral Sample Data Enhancement Method Based on Voigt
Function[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(09): 2502-2510. |
| [9] |
GUO Hui1, 2, HAN Zi-wei1, 2*, WU Dou-qing1, 2. Estimation of Soil Organic Matter Content in Coal Mining Tensile
Fracture Area Based on Spectral Index[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(09): 2569-2577. |
| [10] |
HU Wei-cheng, LI Yun-peng*, WANG Hong-wei, DAI Xue-jing, WANG Hua-peng. Hyperspectral Image Visualization and Recognition of Bloodstains and Their Analogues Based on Attention Mechanism[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(09): 2625-2631. |
| [11] |
FAN Xiao-yong1, LI Heng-kai1*, LIU Kun-ming2, WANG Xiu-li3, YU Yang1, LI Xiao-yu1. A Multi-Layer Attention Convolutional Neural Network Model for Fine Classification of Hyperspectral Images in Rare Earth Mining Areas[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(09): 2666-2675. |
| [12] |
DUAN Lu-nan1, 2, ZHANG Ai-wu1, 2*, CHEN Yun-sheng1, 2, GAO Feng3, GUO Ju-wen3. Research on Mural Line Drawing Enhancement Method Combining
Wavelet Transform and Hyperspectral Imagery[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(09): 2676-2683. |
| [13] |
JIAO Long1, LI Ying1, TONG Rong-chao2, WANG Cai-ling3. Identification of Sandstone Lithology Based on Hyperspectral Combined With Support Vector Machine Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(09): 2496-2501. |
| [14] |
LI Shan1, 2, 3, LIN Peng1, 2, 3, XU Zhen-hao1, 2, 3*, XIANG Hang1, 2, 3, LI Qian-ji1, 2, 3. Intelligent Lithology Identification Based on Transfer Learning of Rock Hyperspectral Images[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2289-2301. |
| [15] |
LIU Ao-ran1, 2, MENG Xi2, LIU Zhi-guo2, SONG Yu-fei2*, ZHAO Xue-man2, ZHI Dan-ning2. Hyperspectral Estimation of Soluble Solids Content in Winter Jujube Based on LSTM-TE Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2326-2334. |
|
|
|
|
