|
|
|
|
|
|
Hyperspectral Image Features Combined With Spectral Features Used to Classify the Bruising Time of Peach |
OUYANG Ai-guo, LIU Hao-chen, CHENG Long, JIANG Xiao-gang, LI Xiong, HU Xuan |
School of Mechatronics & Vehicle Engineering, East China JiaoTong University, National and Local Joint Engineering Research Center of Fruit Intelligent Photoelectric Detection Technology and Equipment, Nanchang 330013, China |
|
|
Abstract From the ripening of the fruit tree to reaching the consumers, the peaches need to go through a series of processes such as picking, packaging, and transportation. In each process, bruised fruit may occur. Therefore, it is particularly important to check which process produces the most bruises and to improve the processing process in a targeted manner. Throughout the application of hyperspectral technology in detecting fruit bumps at home and abroad, most of them ignore image features and only use spectral features. Modeling based on image features combined with spectral features is rare. Secondly, the interval is usually the number of days in terms of the qualitative judgment of fruit bump time. The larger time interval, the longer fruit bump time, and the more obvious change, the higher detection accuracy. There is no effective method of classifying the bump time for the fruits which were bruised in a very short time. In this paper, 90 simulated surface bruises were taken as experimental samples, and hyperspectral images of the bruises 12, 24, 36 and 48 h were collected respectively. The spectral feature extraction of the peach sample uses the average spectrum of 100 pixels in the region of interest to prevent the spectral information of a single-pixel from being significantly different from the overall spectral information; The PC1 image that can best reflect the bruise of the peach is selected after dimensionality reduction by principal component analysis (PCA). In the weight coefficient curve of the PC1 image, 4 characteristic wavelength points (512, 571, 693, 853 nm) at the peak and valley points are selected as the characteristic image. The average gray value which calculates as the characteristic image after graying is used as the feature of the bruised peach image. Finally, based on the least squares support vector machine (LS-SVM) algorithm, three discriminant models, namely the spectral feature model, image feature model and image feature combined with the spectral feature model of the peach bruise time were established, and the performance of models was judged according to their classification accuracy. The research results show that the classification accuracy of the three peach bruise models increases with the increase of bruise time; the model based on the radial basis kernel function (RBF_kernel) combined with the spectral features has the best predictive effect, and it has the best prediction effect on bruises. The recognition accuracy rates of the peach samples at 12, 24, 36 and 48 h were 83.33%, 96.67%, 100% and 100%, respectively. This may be due to the model established by the radial basis kernel function with nonlinear characteristics is more suitable for peach Classification of bump time. The model combining image features with spectral features can better estimate the fruit bump time, and it can provide a certain reference and basis for fruit external quality sorting, which has certain reference significance for fruit sales and deep processing enterprises.
|
Received: 2020-08-12
Accepted: 2020-12-05
|
|
|
[1] ZHENG Zheng-zheng,LI Xue-gong(郑铮铮,李学工). Standard Science(标准科学),2017,(1):31.
[2] ZHANG Hai-liang,GAO Jun-feng,HE Yong(章海亮,高俊峰,何 勇). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报),2013,44(9):177.
[3] Zhou X,Sun J,Tian Y,et al. International Journal of Remote Sensing,2020,41(6):2263.
[4] LIU Yan-de,CHENG Meng-jie,HAO Yong(刘燕德,程梦杰,郝 勇). Journal of East China JiaoTong University(华东交通大学学报),2018,35(4):1.
[5] Liu D,Zeng X A,Sun D W. Critical Reviews in Food Science and Nutrition,2015,55(12):1744.
[6] ZHANG Bao-hua,HUANG Wen-qian,LI Jiang-bo,et al(张保华,黄文倩,李江波,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2014,34(5):1367.
[7] López-Maestresalas A, Keresztes J C, Goodarzi M, et al. Food Control, 2016, 70: 229.
[8] Baranowski P, Mazurek W, Pastuszka-Wozniak J. Postharvest Biology and Technology, 2013, 86: 249.
[9] María Rocío Jiménez, Pilar Rallo, Hava F. Rapoport, María Paz Suárez. Postharvest Biology and Technology, 2016, 111:117.
[10] LIU Ze-xun,WAN Zhi,LI Xian-sheng,et al(刘则洵,万 志,李宪圣,等). Optics and Precision Engineering(光学精密工程),2015,23(7):1829.
[11] Govindarajan Konda Naganathan,Lauren M Grimes,Jeyamkondan Subbiah,et al. Computers and Electronics in Agriculture,2008,64(2):225.
[12] LIU Xue-mei,ZHANG Hai-liang(刘雪梅,章海亮). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报),2012,43(9):160.
[13] Chang Y,Chao Y T,Kuang W H,et al. Journal of Food and Drug Analysis,2013,21:268.
[14] LIU Yan-de,XIAO Huai-chun,SUN Xu-dong,et al(刘燕德,肖怀春,孙旭东,等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2018,34(3):180.
[15] Sun Y,Wei K,Liu Q,et al. Sensors,2018,18(4):1295. |
[1] |
WEI Si-ye1, 2, FAN Xing-cheng3, MAO Han1, 2, CAO Tao4, 5, CHENG Ao3, FAN Xing-jun3*, XIE Yue3. Abundance and Spectral Characteristics of Molecular Weight Separated Dissolved Organic Matter Released From Biochar at Different Pyrolysis Temperatures[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(06): 1809-1815. |
[2] |
DONG Rui, TANG Zhuang-sheng, HUA Rui, CAI Xin-cheng, BAO Dar-han, CHU Bin, HAO Yuan-yuan, HUA Li-min*. Research on Classification Method of Main Poisonous Plants in Alpine Meadow Based on Spectral Characteristic Variables[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1076-1082. |
[3] |
ZHANG Tian-liang, ZHANG Dong-xing, CUI Tao, YANG Li*, XIE Chun-ji, DU Zhao-hui, ZHONG Xiang-jun. Identification of Early Lodging Resistance of Maize by Hyperspectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1229-1234. |
[4] |
LI Lian-jie1, 2, FAN Shu-xiang2, WANG Xue-wen1, LI Rui1, WEN Xiao1, WANG Lu-yao1, LI Bo1*. Classification Method of Coal and Gangue Based on Hyperspectral
Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1250-1256. |
[5] |
SHI Ji-yong, LIU Chuan-peng, LI Zhi-hua, HUANG Xiao-wei, ZHAI Xiao-dong, HU Xue-tao, ZHANG Xin-ai, ZHANG Di, ZOU Xiao-bo*. Detection of Low Chromaticity Difference Foreign Matters in Soy Protein Meat Based on Hyperspectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1299-1305. |
[6] |
FAN Nai-yun, LIU Gui-shan*, ZHANG Jing-jing, YUAN Rui-rui, SUN You-rui, LI Yue. Rapid Determination of TBARS Contents in Tan Mutton Using Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 713-718. |
[7] |
DUAN Min-jie, LI Yan-ming, LI Xin-yu*, XIE Jun-fei, WANG Qian, ZHAO Song-ting, XU Rui, WANG Yue-rong. Study on Hyperspectral Characteristics and Difference of Urban Colorful Plants in Beijing in Autumn[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 841-846. |
[8] |
QIAO Lu, WANG Song-lei*, GUO Jian-hong, HE Xiao-guang. Combination of Spectral and Textural Informations of Hyperspectral Imaging for Predictions of Soluble Protein and GSH Contents in Mutton[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(01): 176-183. |
[9] |
YE Rong-ke1, KONG Qing-chen1, LI Dao-liang1, 2, CHEN Ying-yi1, 2, ZHANG Yu-quan1, LIU Chun-hong1, 2*. Shrimp Freshness Detection Method Based on Broad Learning System[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(01): 164-169. |
[10] |
WU Ye-lan1, CHEN Yi-yu1, LIAN Xiao-qin1, LIAO Yu2, GAO Chao1, GUAN Hui-ning1, YU Chong-chong1. Study on the Identification Method of Citrus Leaves Based on Hyperspectral Imaging Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(12): 3837-3843. |
[11] |
OUYANG Ai-guo, WAN Qi-ming, LI Xiong, XIONG Zhi-yi, WANG Shun, LIAO Qi-cheng. Research on Rich Borer Detection Methods Based on Hyperspectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(12): 3844-3850. |
[12] |
DUAN Long1, YAN Tian-ying1, WANG Jiang-li2, 3, YE Wei-xin1, CHEN Wei1, GAO Pan1, 2*, LÜ Xin2, 3*. Combine Hyperspectral Imaging and Machine Learning to Identify the Age of Cotton Seeds[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(12): 3857-3863. |
[13] |
XU Zhao-jin, LI Dong-liang, SHEN Li*. Study on Diffuse Reflection and Absorption Spectra of Organic and Inorganic Chinese Painting Pigments[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(12): 3915-3921. |
[14] |
CHANG Jin-qiang, ZHANG Ruo-yu*, PANG Yu-jie, ZHANG Meng-yun, ZHA Ya. Classification of Impurities in Machine-Harvested Seed Cotton Using Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3552-3558. |
[15] |
LIN Xiao-mei1, WANG Xiao-meng1, HUANG Yu-tao1*, LIN Jing-jun2*. PSO-LSSVM Improves the Accuracy of LIBS Quantitative Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3583-3587. |
|
|
|
|