1.中国烟草总公司郑州烟草研究院 烟草工艺重点实验室,河南 郑州 450001
2.福建中烟工业有限责任公司,福建 厦门 361021
徐大勇,硕士,高级工程师,研究方向:卷烟加工工艺研究,E-mail:xdyong@126.com
李华杰,高级工程师,研究方向:烟草工艺研究,E-mail:lhj10522@fjtic.cn
扫 描 看 全 文
梅吉帆,李智慧,李嘉康等.基于高光谱成像技术的配方烟丝组分判别[J].分析测试学报,2021,40(08):1151-1157.
MEI Ji-fan,LI Zhi-hui,LI Jia-kang,et al.Components Discrimination for Formula Tobacco Based on Hyperspectral Imaging[J].Journal of Instrumental Analysis,2021,40(08):1151-1157.
梅吉帆,李智慧,李嘉康等.基于高光谱成像技术的配方烟丝组分判别[J].分析测试学报,2021,40(08):1151-1157. DOI: 10.19969/j.fxcsxb.20110702.
MEI Ji-fan,LI Zhi-hui,LI Jia-kang,et al.Components Discrimination for Formula Tobacco Based on Hyperspectral Imaging[J].Journal of Instrumental Analysis,2021,40(08):1151-1157. DOI: 10.19969/j.fxcsxb.20110702.
应用近红外(1 000~2 200 nm)高光谱成像技术开展了面对像素、面对样本的配方烟丝4种组分(叶丝、梗丝、薄片丝、膨胀丝)的判别研究。以样本高光谱图像的所有像素点光谱数据进行面对像素的组分判别;以样本所有像素点的平均光谱数据进行面对样本的组分判别。采用二阶导数法结合萨维茨基-戈莱平滑(SG)滤波对光谱数据进行预处理。通过面对像素数据的主成分分析,证实了基于面对像素的高光谱数据进行组分判别的可行性,以前5主成分建立的支持向量机模型很好地实现了叶丝与梗丝、叶丝与薄片丝的判别任务。建立了面对样本的4组分的K近邻和支持向量机判别模型,通过连续投影算法和二阶导数法进行特征波长选择,筛选出具有高判别准确率的波段,组分判别率达86.97%。
Near-infrared(1 000-2 200 nm) hyperspectral imaging technique was applied to the discrimination of components in formula tobacco, including cut lamina, cut stem, expanded tobacco and reconstituted tobacco. Two approaches, named pixel-wise and object-wise, were investigated to conduct this research. The pixel-wise components discrimination study was based on the spectral data of all pixels of the hyperspectral images of samples. Second derivative coupled with Savitzky-Golay(SG) algorithm was applied as preprocessing method for original spectral data. Through principal component analysis of the pixel data, the feasibility for component discrimination of the pixel hyperspectral data was confirmed. The established support vector machine(SVM) model based on first five components' data showed its excellent character in discriminating cut lamina and cut stem, cut lamina and reconstituted tobacco, obtaining intuitive discrimination results. The K-nearest neighbor and support vector machine discriminant model for the four components of samples was established. The characteristic wavelength was selected by the continuous projection algorithm and the second derivative method, and the band with high discrimination accuracy was selected, with a component discrimination rate reached 86.97%.
配方烟丝组分判别近红外高光谱成像技术像素分类主成分分析连续投影算法二阶导数法
formula tobaccocomponents discriminationnear-infrared hyperspectral imagingpixel-wise classificationprincipal component analysissuccessive projection algorithmsecond derivate method
Ding M Z, Liu H, Liu Q, Li Q S, Li L F, Zhao L, Wang H B, Wang H B. Food Mach.(丁美宙, 刘欢, 刘强, 李全胜, 李龙飞, 赵乐, 王海滨, 王洪波. 食品与机械), 2017, 33(9): 197-202.
Chen S W, Hu S L, Cui N, Wang F Y, Liu Q, Yu H Y, Zhang C S. Southwest China J. Agric. Sci.(陈帅伟, 胡苏林, 崔宁, 王法懿, 刘群, 于海洋, 张超帅. 西南农业学报), 2015, 28(6): 2742-2745.
Xu C L, Song C P, Dai Y, Ma K Y, Wang W C, Shi P P, Wang M, She S K. J. Hunan Agric. Univ.: Nat. Sci.(徐成龙, 宋朝鹏, 戴亚, 马扩彦, 王文超, 石盼盼, 王梅, 佘世科. 湖南农业大学学报:自然科学版), 2013, 39(1): 23-25.
Yu J J. Cigarette Technology. 2nd ed. Beijing: China Agriculture Press(于建军. 卷烟工艺学. 2版. 北京: 中国农业出版社), 2009: 20-30.
Hu L Z, Zhang S J, Yu X P, Zhang L H. Acta Tabacaria Sinica(胡立中, 张胜军, 余小平, 张灵辉. 中国烟草学报), 2010, 16(2): 26-30.
Lin H, Zhang X Y, Cao F J, Zhou J. China Patent(林慧, 张馨予, 曹伏军, 周骏. 中国专利), CN110779832A. 2020-02-11.
Zhengzhou Tobacco Research Institute of CNTC. China Patent(中国烟草总公司郑州烟草研究院. 中国专利), CN107271312B. 2019-06-21.
Dai Q, Sun D W, Xiong Z J, Cheng J H, Zeng X A. Compr. Rev. Food Sci. Food Saf., 2014, 13(5): 891-905.
Zhao D E, Wu R, Zhao B G, Chen Y Y. Spectrosc. Spectral Anal.(赵冬娥, 吴瑞, 赵宝国, 陈媛媛.光谱学与光谱分析), 2019, 39(3):921-926.
Feng C L, Zhu Q B, Zhu X, Huang M. J. Sci. Jiangnan Univ.: Nat. Sci. Ed.(冯朝丽, 朱启兵, 朱晓, 黄敏. 江南大学学报:自然科学版), 2012, 11(2): 149-153.
Li J B, Rao X Q, Ying Y B, Wang D T. Trans. Chin. Soc. Agric. Eng.(李江波, 饶秀勤, 应义斌, 王东亭. 农业工程学报), 2010, 26(8): 222-228.
Barbin D, Elmasry G, Sun D W, Allen P. Meat Sci., 2012, 90(1): 259-268.
Zhong S X, Li Z B, Tang R N. Nat. Sci. J. Hainan Univ.(钟穗希, 李子波, 唐荣年. 海南大学学报: 自然科学版), 2020, 38(3): 260-269.
Cheng S X, Xie C Q, Wang Q N, He Y, Shao Y N. Spectrosc. Spectral Anal.(程术希, 谢传奇, 王巧男, 何勇, 邵咏妮. 光谱学与光谱分析), 2014, 34(5): 1362-1366.
Cheng Z, Zhang L Q, Liu H Y, Zhu A S. Spectrosc. Spectral Anal.(成忠, 张立庆, 刘赫扬, 诸爱士. 光谱学与光谱分析), 2010, 30(4):949-952.
Fang X R, Gao J F, Xie C Q, Zhu F L, Huang L X, He Y. Spectrosc. Spectral Anal.(方孝荣, 高俊峰, 谢传奇, 朱逢乐, 黄凌霞, 何勇. 光谱学与光谱分析), 2015, 35(7):1949-1955.
Xia J, Yang Y W, Cao H X. Comput. Electron. Agric., 2018, 145: 27-34.
Yin W X, Zhang C, Zhu H Y, Zhao Y R, He Y. Plos One, 2017, 12(7): 891-905.
Cao X L, Deng M J, Cui G X. Spectrosc. Spectral Anal.(曹晓兰, 邓梦洁, 崔国贤. 光谱学与光谱分析), 2019, 39(6):1905-1908.
0
浏览量
9
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构