基于RGB和CIELab预测紫苏叶片花青素含量

doi:10.13304/j.nykjdb.2023.0164

摘要/Abstract

摘要：

为推进富含花青素的紫苏品种选育，指导逆境胁迫下的紫苏生产管理，以紫苏为研究对象，采集田间叶片并使用数码相机拍照，结合红绿蓝色彩空间（red green blue color space，RGB）和CIELab色彩空间（CIELab color space）2种图像色彩分析手段处理图片，与叶片花青素含量进行相关性和显著性分析，筛选出相关系数较高的色彩参数，建立单变量回归反演模型，最终综合建模得到预测效果最优的紫苏叶片花青素含量预测模型。结果表明，在RGB色彩空间中，红光标准化值（normalized redness intensity，NRI）、绿光标准化值（normalized greenness intensity，NGI）与花青素含量呈极显著相关，其中NGI的相关系数大于NRI。当叶片正反面色彩贡献比为2∶1时，NGI与花青素含量的相关性最大，相关系数为0.853 2。对比不同模型发现，以NGI为自变量建立的指数模型拟合效果最好，相关系数为0.838 1，决定系数（R²）达0.755 0。在CIELab色彩空间中，红度（a^*）与花青素含量的相关性最好，且相关系数同样在叶片正反面色彩贡献比为2∶1时达最大，为0.735 6。基于a^*建立的幂模型拟合效果最好，相关系数和R²分别为0.743 8和0.679 8。分别使用NGI模型和a^*模型对叶片花青素含量进行估测，验证后发现a^*模型的预测效果更好，准确性和稳定性更高，因此以a^*模型为预测紫苏叶片花青素含量的最优模型。

关键词: 紫苏, RGB, CIELab, 花青素, 数码相机

Abstract:

In order to promote the breeding of Perilla frutescens varieties with high anthocyanin and guide the production management of Perilla frutescens under the stress of adversity， Perilla frutescens was as the research object， the field leaves were collected and taken photos with a digital camera. The image color of photo was analyzed by red green blue color space （RGB） and CIELab color space. And the relationship between color parameters and leaf anthocyanin content was analyzed for screening out color parameters with high correlation coefficient. Univariate regression inversion model was established， and finally the best predictive model of anthocyanin content in the leaves of Perilla frutescens was obtained. The results showed that in RGB color space， the normalized redness intensity （NRI） and normalized greenness intensity （NGI） had significant correlations with anthocyanin content， and the correlation coefficient of NGI was greater than that of NRI. When the contribution ratio of leaves front and leaves back was 2∶1， the correlation between NGI and anthocyanin content was the highest with the correlation coefficient 0.853 2. Compared with different models，it was found that the exponential model established with NGI as the independent variable had the best fitting effect with the correlation coefficient 0.838 1 and the coefficient of determination （R²） 0.755 0. In the CIELab color space， a^* had the best correlation with anthocyanin content， and the correlation coefficient reached the maximum （0.735 6） when the contribution ratio of leaf front and leaf back was 2∶1. The power model based on a^* had the best fitting effect，and the correlation coefficient and R² were 0.743 8 and 0.679 8， respectively. The NGI model and a^* model were respectively used to estimate the content of anthocyanin in leaves. After verification， it was found that the prediction effect of the a^* model was better with higher accuracy and stability. Therefore， the model of a^* was used as the best model to predict the content of anthocyanins in Perilla frutescens leaves.

Key words: Perilla frutescens, RGB, CIELab, anthocyanin, digital camera

中图分类号:

S126

刘徐冬雨, 郭潇潇, 付晨青, 韩蕊, 李国辉, 王秀萍. 基于RGB和CIELab预测紫苏叶片花青素含量[J]. 中国农业科技导报, 2024, 26(7): 103-110.

Dongyu LIU-XU, Xiaoxiao GUO, Chenqing FU, Rui HAN, Guohui LI, Xiuping WANG. Prediction of Anthocyanin Content in Perilla frutescens Leaves Based on RGB and CIELab[J]. Journal of Agricultural Science and Technology, 2024, 26(7): 103-110.

图/表 8

参考文献 38

1	魏长玲,郭宝林,张琛武,等.中国紫苏资源调查和紫苏叶挥发油化学型研究[J].中国中药杂志,2016,41(10):1823-1834.
	WEI C L, GUO B L, ZHANG C W, et al.. Perilla resources of China and essential oil chemotypes of Perilla leaves [J]. China J. Chin. Materia Med., 2016, 41(10):1823-1834.
2	崔新爽.中国不同种源地紫苏在哈尔滨的适应性研究[D].哈尔滨:东北林业大学,2020.
	CUI X S. Adaptability of Perilla from different provenances in China in Harbin [D]. Harbin: Northeast Forestry University, 2020.
3	魏国江,潘冬梅,刘淑霞,等.黑龙江省大庆市盐碱地种植紫苏技术研究[J].黑龙江农业科学,2011(2):26-29.
	WEI G J, PAN D M, LIU S X, et al.. Study on planting technique of Perilla in saline land in Daqing of Heilongjiang [J]. Heilongjiang Agric. Sci., 2011(2):26-29.
4	徐创军,杨立中,唐家良,等.紫色土坡地不同种植模式生态经济效益综合评价[J].中国生态农业学报,2008,16(1):196-199.
	XU C J, YANG L Z, TANG J L, et al.. Comprehensive evaluation of eco-economic benefits of different cropping systems in slope-land purple soils [J]. Chin. J. Eco-Agric., 2008, 16(1):196-199.
5	贾瑞海.食药兼用植物紫苏的应用研究与发展前景[J].农技服务,2007,24(2):102-104.
6	王仙萍,李敏,张敏琴,等.贵州紫苏资源收集以及叶色多样性分析[J].中国农学通报,2013,29(10):132-136.
	WANG X P, LI M, ZHANG M Q, et al.. Resources collection and leaf color diversity analysis of Perilla frutescens (L.) in Guizhou province [J]. Chin. Agric. Sci. Bull., 2013, 29(10):132-136.
7	陈道宗.油菜及其近缘种不同组织花青素累积的分子机制研究[D].武汉:华中农业大学,2020.
	CHEN D Z. Molecular mechanism studies on anthocyanin accumulation in various tissues of rapeseed and its related species [D]. Wuhan: Huazhong Agricultural University, 2020.
8	姜秀娟,刘海霞,徐爱,等.花色苷提取的最新研究进展[J].农业技术与装备,2021(11):54-55.
	JIANG X J, LIU H X, XU A, et al.. Recent advances in extraction of anthocyanins [J]. Agric. Technol. Equip., 2021(11):54-55.
9	WALLACE T C, GIUSTI M M. Anthocyanins-nature’s bold, beautiful, and health-promoting colors [J/OL]. Foods, 2019, 8(11):550 [2023-02-05]. .
10	LIU Y, ZHANG X M, LI H, et al.. Technologies for extracting anthocyanins from the red raspberry and their free radical scavenging ability [J]. Adv. J. Food Sci. Technol., 2018, 14(6):166-180.
11	XU L, TIAN Z Z, CHEN H, et al.. Anthocyanins, anthocyanin-rich berries, and cardiovascular risks: systematic review and meta-analysis of 44 randomized controlled trials and 15 prospective cohort studies [J/OL]. Front Nutr., 2021, 8:747884 [2023-02-05]. .
12	YURI N, KEIKO I K, HITOSHI M, et al.. Therapeutic effects of anthocyanins for vision and eye health [J/OL]. Molecules, 2019, 24(18):3311 [2023-02-05]. .
13	AUNG H N, TRINH N A, KI B L, et al.. .Overexpression of rosea1 from snapdragon enhances anthocyanin accumulation and abiotic stress tolerance in transgenic tobacco [J/OL]. Front. Plant Sci., 2018, 9:1070 [2023-02-05]..
14	柯燚,高飞,金韬,等.温度对植物花青素苷合成影响研究进展[J].中国农学通报,2015,31(19):101-105.
	KE Y, GAO F, JIN T, et al.. Review of temperature effect on anthocyanin synthesis [J]. Chin. Agric. Sci. Bull., 2015, 31(19):101-105.
15	西拉.果实发育过程中转色期前后水分胁迫对原花青素和花青素积累的影响[J].中外葡萄与葡萄酒,2011(11):76-76.
16	RYU J H, SEO K S, CHOI G L, et al.. Effects of LED light illumination on germination, growth and anthocyanin content of Dandelion (Taraxacum officinale) [J]. Kr. J. Plant Res., 2012, 25(6):731-738.
17	王方永,王克如,李少昆,等.利用数码相机和成像光谱仪估测棉花叶片叶绿素和氮素含量[J].作物学报,2010,36(11):1981-1989.
	WANG F Y, WANG K R, LI S K, et al.. Estimation of chlorophyll and nitrogen contents in cotton leaves using digital camera and imaging spectrometer [J]. Acta Agron. Sin., 2010, 36(11):1981-1989.
18	张沛健,尚秀华,吴志华.基于图像处理技术的5种红树林叶片形态特征及叶绿素相对含量的估测[J].热带作物学报,2020,41(3):496-503.
	ZHANG P J, SHANG X H, WU Z H. Morphological characteristics of leaves and estimation of relative chlorophyll content in five species of mangrove based on image processing technology [J]. Chin. J. Trop. Crops, 2020, 41(3):496-503.
19	王诣,闫志勇.基于图像处理的青冈栎叶绿素含量检测系统研究[J].中国农业科技导报,2017,19(4):59-64.
	WANG Y, YAN Z Y. Detection system of chlorophyll content of Cyclobalanopsis glauca using image processing technology [J]. J. Agric. Sci. Technol., 2017, 19(4):59-64.
20	贺英,邓磊,毛智慧,等.基于数码相机的玉米冠层SPAD遥感估算[J].中国农业科学,2018,51(15):2886-2897.
	HE Y, DENG L, MAO Z H, et al.. Remote sensing estimation of canopy SPAD value for maize based on digital camera [J]. Sci. Agric. Sin., 2018, 51(15):2886-2897.
21	李修华,卢显杰,奚金阳,等.智能手机RGB图像检测植物叶片叶绿素含量的通用方法[J].农业工程学报,2021,37(22):145-151.
	LI X H, LU X J, XI J Y, et al..Univeisal method to detect the chlorophyll content in plant leaves with RGB images captured by smart phones [J]. Trans. Chin. Soc. Agric. Eng.,2021, 37(22):145-151.
22	刘炜.基于图像处理的乳瓜叶片叶绿素含量预测研究[D].银川:宁夏大学,2020.
	LIU W. Prediction of chlorophyll content in leaves of cucumis based on image processing [D]. Yinchuan: Ningxia University, 2020.
23	包刘媛,李香勇,李洪相,等.环境条件对花青素苷稳定性的影响[C]//2016中国大理国际茶花大会论文集.大理,2016:346-355.
24	黎瑞珍,吴丽,刘美然,等.分光光度法测定火龙果中花青素的含量[J].海南热带海洋学院学报,2023,30(2):115-121.
	LI R Z, WU L, LIU M R, et al.. Determination of anthocyanin content in Pitaya fruit by spectrophotometry [J]. J. Hainan Trop. Ocean Univ., 2023, 30(2):115-121.
25	NULL R C T R, TEAM R, NULL R C T, et al.. R: a language and environment for statistical computing [J]. Computing, 2011, 1:12-21.
26	殷丽琴,彭云强,钟成,等.高效液相色谱法测定8个彩色马铃薯品种中花青素种类和含量[J].食品科学,2015,36(18):143-147.
	YIN L Q, PENG Y Q, ZHONG C, et al.. Determination of anthocyanidin composition of different pigmented potato (Solanum tuberosum L.) cultivars by HPLC [J]. Food Sci., 2015, 36(18):143-147.
27	刘长姣,郑霞,熊湘炜,等.分光光度法测定黑米花青素方法的建立[J].粮食与油脂,2019,32(1):73-77.
	LIU C J, ZHENG X, XIONG X W, et al.. Detection of anthocyanin in black rice by spectrophotometry [J]. Cereals Oils, 2019, 32(1):73-77.
28	张寒俊,汪海波,习羽.改进香草醛法测定葡萄提取物中的原花青素[J].中国酿造,2010(8):147-149.
	ZHANG H J, WANG H B, XI Y. Improved method for determination of proanthocyanidin in grape extracts [J]. Chin. Brewing, 2010(8):147-149.
29	朱甜甜,胡玲,童金枝,等.秀丽莓茎、叶中原花青素测定[J].青海大学学报(自然科学版),2020,38(1):38-43.
	ZHU T T, HU L, TONG J Z, et al.. Determination of proanthocyanidins in stems and leaves of Rubus amabilis focke [J]. J. Qinghai Univ. (Nat. Sci.), 2020, 38(1):38-43.
30	王贝,侯益明.pH示差法测定花青素含量的方法研究[J].山东化工,2021,50(21):94-96.
	WANG B, HOU Y M. Study on the method of determininig anthocyanin content by pH-differential method [J]. Shandong Chem. Ind., 2021, 50(21):94-96.
31	彭可为,李婵,曹学仁,等.数字图像技术在植物病害自动识别中的研究进展[J].江西农业学报,2012,24(9):69-71.
	PENG K W, LI C, CAO X R, et al.. Research advance in application of digital image technology in automatic recognition of plant diseases [J]. Acta Agric. Jiangxi, 2012, 24(9):69-71.
32	郭伦丽.基于近红外和可见光图像的植物水分利用率测量方法研究[D].西安:西安理工大学,2021.
	GUO L L. Research on mesurement method of plant water use efficiency based on near infrared and visible images [D]. Xi’an: Xi’an University of Technology, 2021.
33	魏全全,李岚涛,任涛,等.基于数字图像技术的冬油菜氮素营养诊断[J].中国农业科学,2015,48(19):3877-3886.
	WEI Q Q, LI L T, REN T, et al.. Diagnosing nitrogen nutrition status of winter rapeseed via digital image processing technique [J]. Sci. Agric. Sin., 2015,48(19):3877-3886.
34	夏莎莎,张聪,李佳珍,等.基于手机相机获取冬小麦冠层数字图像的氮素诊断与推荐施肥研究[J].中国生态农业学报,2018,26(4):538-546.
	XIA S S, ZHANG C, LI J Z, et al.. Study on nitrogen nutrition diagnosis and fertilization recommendation of winter wheat using canopy digital images from cellphone camera [J]. Chin. J. Eco-Agric., 2018, 26(4):538-546.
35	刘子恒,敏乾,李海翼.数字图像技术在苦菜叶绿素含量测量中的应用[J].贵州大学学报(自然科学版),2017,34(6):11-13, 38.
	LIU Z H, MIN Q, LI H Y.The application of digital image processing technique in measuring chlorophyll concentration in bitter leaf [J]. J. Guizhou Univ.(Nat. Sci.), 2017, 34(6):11-13, 38.
36	董淼.苹果叶片和冠层叶绿素含量高光谱估算模型[D].乌鲁木齐:新疆农业大学,2018.
	DONG M. Models of estimating chlorophyll in leaves and canopy of Malus pumila ‘Hongfushi’ using hyperspectral data [D]. Urumqi: Xinjiang Agricultural University, 2018.
37	张颖,陈芳,郝远强,等.智能手机光谱仪检测紫薯花青素[C]//河南省化学会2020年学术年会论文集.许昌,2020:1-1.
38	娄卫东,林宝刚,周洪奎,等.基于图像特征的油菜叶绿素含量快速估算[J].浙江农业科学,2022,63(3):480-484.

指标 Index	花青素含量Anthocyanin content
指标 Index	正Front	反Back
红光标准化值NRI	0.635 1^**	0.710 4^**
绿光标准化值NGI	-0.845 9^**	-0.783 6^**
蓝光标准化值NBI	0.051 6	-0.181 1

指标 Index	花青素含量Anthocyanin content
指标 Index	正Front	反Back
红光标准化值NRI	0.635 1^**	0.710 4^**
绿光标准化值NGI	-0.845 9^**	-0.783 6^**
蓝光标准化值NBI	0.051 6	-0.181 1

模型Model	公式Formula	决定系数R²
指数Exponent	y = 2.96×10²⁰×e^-137.89^x	0.755 0
线性Linear	y = -1 489.48x+495.24	0.728 0
对数Logarithm	y = -483.08ln（x）-531.81	0.728 0
多项式Polynomial	y = 4 915x²-4 677.72x+1 012.24	0.728 1
幂Power	y = 2.00×10^-21x^-44.68	0.753 6

模型Model	公式Formula	决定系数R²
指数Exponent	y = 2.96×10²⁰×e^-137.89^x	0.755 0
线性Linear	y = -1 489.48x+495.24	0.728 0
对数Logarithm	y = -483.08ln（x）-531.81	0.728 0
多项式Polynomial	y = 4 915x²-4 677.72x+1 012.24	0.728 1
幂Power	y = 2.00×10^-21x^-44.68	0.753 6

模型Model	公式Formula	决定系数R²
指数Exponent	y = 0.39e^0.76^x	0.679 5
线性Linear	y = 7.42x-20.57	0.541 1
对数Logarithm	y = 29.92ln（x）-31.95	0.524 8
多项式Polynomial	y = 1.83x²-7.85x+10.63	0.553 7
幂Power	y = 0.12x^3.1	0.679 8