高光谱成像结合PSO-SVM的银杏果种类鉴别

doi:10.3964/j.issn.1000-0593(2024)03-0859-06

摘要
参考文献
相关文章 (15)

全文: PDF (11505 KB)
输出: BibTeX | EndNote (RIS)

摘要：银杏果富含维生素、银杏萜内酯和银杏黄酮等成分，具有抗氧化、抗肿瘤、预防心血管疾病等功能，可药食两用。由于银杏果品种不同，其主要成分含量和品质各异。另外，银杏果某些成分含量对其贮藏和加工工艺影响较大。为实现银杏果品种高效无损鉴别，提出一种基于高光谱成像技术的支持向量机（SVM）分类模型，并利用遗传算法（GA）和粒子群算法（PSO）优化模型参数提高种类鉴别正确率。以3个品种630个银杏果为研究对象，按2∶1划分为训练集和测试集，分别为420个和210个。利用高光谱图像采集系统获取900~1 700 nm范围内的银杏果图像，黑白校正后选取质心位置25×25 pixel感兴趣区域（ROI），提取该区域内平均光谱作为原始光谱数据。因原始光谱两端噪声较大，信噪比低且有效信息较少，截取945.98~1 698.75 nm范围内的光谱波段作为有效波段，并对去噪后光谱波段信息做标准正态变量变换（SNV）预处理，预处理后采用连续投影算法（SPA）和竞争性自适应重加权算法（CARS）提取特征波长，将其波长反射率作为输入矩阵X，预设样本类别1、2、3作为输出矩阵Y，分别建立SNV-SPA/CARS-（GA/PSO）-SVM六种银杏果品种鉴别模型。试验结果表明：SNV-CARS-PSO-SVM模型鉴别效果最佳，分类准确率96.67%，说明CARS提取特征波长变量能代表所有波长信息，且PSO-SVM模型具有较好种类鉴别效果，可实现银杏果鉴别，为银杏果种类高效无损鉴别提供新思路。

关键词：高光谱成像技术；银杏果；种类鉴别；粒子群算法；支持向量机

Abstract：Ginkgo fruit with antioxidant, anti-tumour and cardiovascular disease prevention functions is rich in vitamins, ginkgo lactones and ginkgo flavonoids, and can be used for both medicine and food. Due to the different varieties of Ginkgo fruit, the content of the main ingredientsis different and there are differences in quality. In addition, the content of certain components in ginkgo fruit has a greater impact on their storage and processing. In order to achieve efficient and non-destructive identification of ginkgo fruit varieties, the Support Vector Machine (SVM) classification model based on hyperspectral imaging technology was proposed, and Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) was used to optimizethe parameters of the model to improve the accuracy of species identification. In this study, 630 ginkgo fruits of three species were regarded as the research objects and divided into training and test sets according to 2∶1, with 420 and 210 samples respectively. The hyperspectral acquisition system acquired Ginkgo fruit images in the range of 900～1 700 nm. Then region of interest (ROI) of 25×25 pixel in the center of mass position was selected after black and white correction, and the average spectrum in the region was extracted as the original spectral data. Because of the large noise at both ends of the original spectra, the signal noise ratio was lower and the effective information was less. The spectral band in the range of 945.98~1 698.75 nm was intercepted as the effective band, which was pre-processed by Standard Normal Variate transformation (SNV). Successive Projection Algorithms (SPA) and Competitive Adaptive Reweighted Sampling (CARS) were used to extract the characteristic wavelengths. The wavelength reflectivity was used as the input matrix X, and the sample varieties 1, 2, 3 were used as the output matrix Y. Six identification models were established for the SNV-SPA/CARS-(GA/PSO)-SVM. The experimental results showed that the SNV-CARS-PSO-SVM model had the best identification performance, and the classification accuracy was 96.67%, indicating that the characteristic wavelength variables extracted by CARS could represent all wavelength information, and the PSO-SVM model had a better species identification effect, which could realize the identification of ginkgo fruit. This study provides a new idea for the efficient and non-destructive identification of ginkgo fruit species.

Key words：Hyperspectral image technology; Ginkgo fruit; Varieties identification; PSO; SVM

收稿日期: 2022-09-03 修订日期: 2022-11-12

中图分类号:

TP391

基金资助: 国家重点研发计划项目（2017YFD0301106），河南省科技攻关计划项目（222102110196），河南省高等学校青年骨干教师培养计划项目（2017GGJS062），龙门实验室前沿探索课题(LMQYTSKT032)资助

通讯作者: 付三玲 E-mail: fusanling@126.com

作者简介: 张伏，1978年生，河南科技大学农业装备工程学院教授 e-mail: zhangfu30@126.com

引用本文:

张伏，张方圆，崔夏华，王新月，曹炜桦，张亚坤，付三玲. 高光谱成像结合PSO-SVM的银杏果种类鉴别[J]. 光谱学与光谱分析, 2024, 44(03): 859-864.
ZHANG Fu, ZHANG Fang-yuan, CUI Xia-hua, WANG Xin-yue, CAO Wei-hua, ZHANG Ya-kun, FU San-ling. Identification of Ginkgo Fruit Species by Hyperspectral Image Combined With PSO-SVM. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(03): 859-864.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2024)03-0859-06 或 https://www.gpxygpfx.com/CN/Y2024/V44/I03/859

[1] WU Ya-ping, CAO Meng, WANG Li(吴亚萍, 操萌, 王莉). Forest Science and Technology(林业科技通讯), 2021, (11): 46.
[2] CHEN Peng, HE Feng-ren, YU Bi-yu(陈鹏, 何凤仁, 余碧钰). Journal of Yangzhou University(Agricultural and Life Science Edition)[扬州大学学报(农业与生命科学版)], 1999, (1): 32.
[3] ZHANG Feng-lun, ZHENG Qun-xiong, WU Su-ling, et al(张锋伦, 郑群雄, 吴素玲, 等). Jiangsu Agricultural Sciences(江苏农业科学), 2008, (4): 230.
[4] BAI Wei-dong, HUANG Guo-yong, KONG De-jun(白卫东, 黄国勇, 孔德俊). Science and Technology of Food Industry(食品工业科技), 2004, (8): 140.
[5] JIAO Jun, SHENG Yang, WANG Biao, et al(焦俊, 圣阳, 王标, 等). Laser & Optoelectronics Progress(激光与光电子学进展), 2021, 58(22): 44.
[6] REN Chuan-yi, CHENG Jun-yong, CHEN Zhen-chao, et al(任传义, 程军勇, 陈振超, 等). Forest Research(林业科学研究), 2017, 30(5): 779.
[7] Zhang Xiaoai, Hu Yue, Liu Liping, et al. IOP Conference Series: Earth and Environmental Science, 2019, 332(3): 032026.
[8] Yang Haoyan, Ni Jiangong, Gao Jiyue, et al. Scientific Reports, 2021, 11(1): 15756.
[9] BAI Wen-ming, WANG Lai-bing, CHENG Ri-qing, et al(白文明, 王来兵, 成日青, 等). Chinese Journal of Pharmaceutical Analysis(药物分析杂志), 2018, 38(10): 1661.
[10] SONG Jun, WANG Dong, GUO Ling-an, et al(宋君, 王东, 郭灵安, 等). Chinese Journal of Analysis Laboratory(分析试验室) , 2014, 33(3): 292.
[11] YANG Shu-qin, PENG Kang, LIU Xu(杨蜀秦, 彭康, 刘旭). Journal of South China Agricultural University(华南农业大学学报), 2018, 39(5): 110.
[12] ZHANG Han-wen, LI Ye, JIANG Sheng, et al(张瀚文, 李野, 江晟, 等). Journal of Jilin University(Science Edition)[吉林大学学报(理学版)], 2022, 60(3): 655.
[13] ZHENG Jie, RU Chen-lei, ZHANG Lu, et al(郑洁, 茹晨雷, 张璐, 等). China Journal of Chinese Materia Medica(中国中药杂志), 2021, 46(10): 2571.
[14] 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.
[15] ZHANG Lu, RU Chen-lei, YIN Wen-jun, et al(张璐, 茹晨雷, 殷文俊, 等). Chinese Journal of Pharmaceutical Analysis(药物分析杂志), 2021, 41(4): 726.
[16] ZHANG Lin-zhong, DING Ling-ling, CAI Xue-zhen, et al(章林忠, 丁玲玲, 蔡雪珍, 等). Journal of Anhui Agricultural University(安徽农业大学学报), 2019, 46(1): 160.
[17] BAO Yi-dan, CHEN Na, HE Yong, et al(鲍一丹, 陈纳, 何勇, 等). Optics and Precision Engineering(光学精密工程), 2015, 23(2): 349.
[18] ZHOU Cong, WANG Hui, YANG Jian, et al(周聪, 王慧, 杨健, 等). China Journal of Chinese Materia Medica(中国中药杂志)，2022, 47(22): 6027.
[19] Zou S, Tseng Y C, Zare A, et al. Biosystems Engineering, 2019, 188: 165.
[20] Ríos-Reina R, Callejón R M, Amigo J M. Food Control, 2021，130：108365.
[21] TAN Ke-zhu, CHAI Yu-hua, SONG Wei-xian, et al(谭克竹, 柴玉华, 宋伟先, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2014, 30(9): 235.
[22] Moscetti R, Saeys W, Keresztes J C, et al. Food and Bioprocess Technology, 2015, 8(7): 1593.
[23] ZHAO Fan, YAN Zhao-ru, SONG Hai-yan(赵凡, 闫昭如, 宋海燕). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2021, 41(7): 2240.
[24] WANG Jing-hui, CHENG Jiao-jiao, LIU Yang, et al(王靖会, 程娇娇, 刘洋, 等). Journal of Agricultural Science and Technology(中国农业科技导报), 2021, 23(9): 121.
[25] SHEN Yu, FANG Sheng, WANG Feng-yun, et al(沈宇, 房胜, 王风云, 等). Journal of Agricultural Science and Technology(中国农业科技导报), 2020, 22(3): 64.
[26] LI Rui, FU Long-sheng(李瑞, 傅隆生). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2017, 33(S1): 362.
[27] PAN Xi, LI Ran, WEI Min, et al(潘曦, 李冉, 魏敏, 等). Food & Machinery(食品与机械), 2022, 38(7): 85.
[28] MO Song-tao, DONG Tao, ZHAO Xi-xuan, et al(莫松涛, 董涛, 赵汐璇, 等). Journal of Fruit Science(果树学报), 2022, 39(12): 2418.
[29] CHENG Tian-tian, WANG Ke-jian, HAN Xian-zhong, et al(成甜甜, 王克俭, 韩宪忠, 等). Food & Machinery(食品与机械), 2020, 36(11): 46.