|
|
|
|
|
|
| Visual Identification of Slight-Damaged Cotton Seeds Based on Near Infrared Hyperspectral Imaging |
| GAO Pan1, ZHANG Chu3, Lü Xin2*, ZHANG Ze2, HE Yong3* |
1. College of Information Science and Technology, Shihezi University, Shihezi 832003, China
2. Key Laboratory of Oasis Ecology Agriculture, Shihezi University, Shihezi 832003, China
3. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China |
|
|
|
|
Abstract High quality cotton seeds are the basis of precision seeding technique. In this paper, near-infrared hyperspectral imaging technology is used to realize the visible identification of micro-damaged cotton seeds, which lays a theoretical foundation for the development of cotton seeds selection equipment. Near-infrared hyperspectral images of two kinds of 540 cotton seeds, undamaged and micro-damaged, were acquired, of which 405 samples were used as the calibration set, and 135 samples were used as prediction set. After analyzing the original spectral curve of the full wave band, the noise at both ends was removed. Firstly, KS algorithm was used to divide samples, and the spectra was pretreated by smoothing algorithm( Savitsky-Golay), respectively using the second derivative spectra (2nd spectra) method, principal component analysis loading (PCA-loading) method and successive projection algorithm (SPA) method to extract the feature wavelength, then partial least squares discriminant analysis (PLS-DA) model, K nearest neighbor (KNN) model and support vector machine (SVM) model ware used to analyze the characteristic spectrum. By comparing the analysis results, SPA-PLS-DA was selected as the model, the discrimination rate of the calibration set and the prediction set is up to 91.50% and 90.33%, respectively. Finally, the SPA-PLS-DA model is used to identify the mixed images of undamaged and micro-damaged cotton seeds. The identification results were identified by different colors,the corresponding visual identification figure is generated, and good recognition results were obtained. Moreover, the recognition rate of micro-damaged cotton seeds was above 90%. The result indicates that the near-infrared hyperspectral technology and image processing technology can be used to realize the visual identification of the micro-damaged cottonseeds.
|
|
Received: 2017-07-05
Accepted: 2017-12-25
|
|
|
|
Corresponding Authors:
Lü Xin, HE Yong
E-mail: lxshz@126.com; yhe@zju.edu.cn
|
|
[1] Ambrose A, Kandpal L M, Kim M S, et al. Infrared Physics & Technology, 2016, 75: 173.
[2] ZOU Wei, FANG Hui, LIU Fei, et al(邹 伟，方 慧，刘 飞，等). Journal of Zhejiang University Agriculture & Life Sciences(浙江大学学报·农业与生命科学版), 2011, 37(2): 175.
[3] WU Xiang, ZHANG Wei-zheng, LU Jiang-feng, et al(吴 翔，张卫正，陆江锋，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2016, 36(2): 511.
[4] ZHANG Chu, LIU Fei, KONG Wen-wen, et al(张 初，刘 飞，孔汶汶，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报)，2013，29(20): 270.
[5] Kong W W, Zhang C, Liu F, et al. Sensors, 2013, 13 (7): 8916.
[6] Wang L, Sun D W, Pu H B, et al. Food Analytical Methods, 2016, 9(1): 225.
[7] Cozzolino D, Cynkar W, Shah N, et al. Food Analytical Methods, 2012, 5(3): 381.
[8] Yadav A R, Anand R S, Dewal M L, et al. Applied Soft Computing, 2015, 32: 101.
[9] Vitale R, Bevilacqua M, Bucci R, et al. Chemometr. Intell. Lab., 2013, 121: 90.
[10] Balabin R M, Safieva R Z, Lomakina E I. Microchem. J., 2011, 98(1): 121.
[11] ZHU Li-wei, HUANG Yan-yan, WANG Qing, et al(朱丽伟，黄艳艳，王 庆，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报)，2012, 28(26): 237.
[12] Gustin J L, Jackson S, Williams C, et al. Journal of Agricultural and Food Chemistry, 2013, 61(46): 10872. |
| [1] |
YU Hui-ling1, PAN Shen2, LIANG Yu-liang2, ZHANG Yi-zhuo2*. Prediction Method of Wood Bending Strength Based on KF Optimizing NIR[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(09): 2897-2902. |
| [2] |
CHEN Zhi-li1, LIU Qiang2，YIN Wen-qi2，LIU Hong-tao2，YANG Yi1. Visualization of Petroleum Hydrocarbon Content in Latosol Based on Hyperspectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(09): 2916-2922. |
| [3] |
JIANG Xin-hua1, XUE He-ru1*, GAO Xiao-jing1, ZHANG Li-na2, ZHOU Yan-qing1, DU Ya-juan1, 3. Study on Detection of Chilled Mutton Freshness Based on Hyperspectral Imaging Technique and Sparse Kernel Canonical Correlation Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(08): 2498-2504. |
| [4] |
WU Long-guo1, WANG Song-lei1, 2, HE Jian-guo1, 2*. Study on Soil Moisture Mechanism and Establishment of Model Based on Hyperspectral Imaging Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(08): 2563-2570. |
| [5] |
HUANG Yu-ping1,3, Renfu Lu2, QI Chao1, CHEN Kun-jie1*. Tomato Maturity Classification Based on Spatially Resolved Spectra[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(07): 2183-2188. |
| [6] |
HUANG Di-yun, LI Jing-bin*, YOU Jia, KAN Za. The Classification of Delinted Cottonseeds Varieties by Fusing Image Information Based on Hyperspectral Image Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(07): 2227-2232. |
| [7] |
WANG Xiao-bin1, 2, 3, 4, 5，HUANG Wen-qian2, 3, 4, 5，WANG Qing-yan2, 3, 4, 5，LI Jiang-bo2, 3, 4, 5，WANG Chao-peng2, 3, 4, 5，ZHAO Chun-jiang1, 2, 3, 4, 5*. Application of Near Infrared Hyperspectral Imaging for Detection of Azodicarbonamidein Flour[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(03): 805-812. |
| [8] |
FENG Xu-ping1, 2, PENG Cheng3, ZHANG Chu1, 2, LIU Xiao-dan1, 2, SHEN Ting-ting1, 2, HE Yong1, 2*, XU Jun-feng3. A Simple and Efficient Method for CRISPR/Cas9-Induced Rice Mutant Screening[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(02): 570-574. |
| [9] |
WENG Hai-yong, CEN Hai-yan*, HE Yong. Hyperspectral Model Transfer for Citrus Canker Detection Based on Direct Standardization Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(01): 235-239. |
| [10] |
WANG Hong-bo1,2，HUANG Xiao-xian1，FANG Chen-yan1,2，ZHANG Teng-fei1,2，WEI Jun1. On-Orbit Spectral Calibration Method of Grating Dispersive Imaging Spectrometer[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(01): 296-301. |
| [11] |
HUANG Hui1, 2, SHEN Ye1,2, GUO Yi-lu1, WANG Hang-zhou1, ZHAN Shu-yue1, YANG Ping3, SONG Hong1*, HE Yong4. Visualized Determination of Moisture Content in Dried Scallop with Hyperspectral Imaging System[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(11): 3525-3529. |
| [12] |
LIU Chen1, 2, 3, 4，WANG Qing-yan2, 3, 4，HUANG Wen-qian2, 3, 4，CHEN Li-ping1, 2, 3, 4*，YANG Gui-yan2, 3, 4， WANG Xiao-bin2, 3, 4. Measurement of Light Penetration Depth through Milk Powder Layer in Raman Hyperspectral Imaging System[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(10): 3103-3107. |
| [13] |
LIU Yan-de, HAN Ru-bing, ZHU Dan-ning, MA Kui-rong, XIAO Huai-chun, SUN Xu-dong. Nondestructive Testing for Yellow Peach Bruise and Soluble Solids Content by Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(10): 3175-3181. |
| [14] |
TIAN Ming-lu1,2,3, BAN Song-tao1, CHANG Qing-rui1*, ZHANG Zhuo-ran1, WU Xu-mei1, WANG Qi1. Quantified Estimation of Anthocyanin Content in Mosaic Virus Infected Apple Leaves Based on Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(10): 3187-3192. |
| [15] |
YU Yang, ZHANG Xin*, LIAO Yi, ZHANG Zhuo-yong. Visible-Near Infrared Hyperspectral Imaging Combined with Chemometric Methods to Distinguish Human Facial Information[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(08): 2339-2345. |
|
|
|
|
