Intelligent image analysis for retrieval of leaf chlorophyll content of rice from digital images of smartphone under natural light

The present study describes a new imaging method to acquire rice leaf images under field conditions using a smartphone and modeling approaches to retrieve the leaf chlorophyll (Chl) content from digitized images. Pearson's correlation of image-based color indices of the relative Chl content measured with Soil Plant Analysis Development (SPAD) indicated the suitability of the color models RGB, rgb, and DGCI-rgb. Among the linear regression models, the models based on mean brightness ratio (rgb) alone or in combination with a dark green color index (DGCI-rgb) show a good correlation between the predicted Chl content and relative Chl content. A feed-forward backpropagation-type network was also developed following the optimization of hidden neurons, training, and transfer functions. The predicted Chl contents showed a good correlation with SPAD values. Compared to the linear regression model, the developed artificial neural network model was found to be more efficient in predicting the Chl content, particularly with RGB index.

[1]  M. Agnusdei,et al.  Leaf nitrogen concentration and chlorophyll meter readings as predictors of tall fescue nitrogen nutrition status , 2012 .

[2]  Hao Hu,et al.  Estimation of leaf chlorophyll content of rice using image color analysis , 2013 .

[3]  Luis Miguel Contreras-Medina,et al.  A Review of Methods for Sensing the Nitrogen Status in Plants: Advantages, Disadvantages and Recent Advances , 2013, Sensors.

[4]  Meiling Liu,et al.  Neural-network model for estimating leaf chlorophyll concentration in rice under stress from heavy metals using four spectral indices , 2010 .

[5]  Bhartendu Nath Mishra,et al.  Machine Learning Techniques in Plant Biology , 2015 .

[6]  M. A. Bacarin,et al.  An evaluation of non-destructive methods to estimate total chlorophyll content , 2008, Photosynthetica.

[7]  Mahmoud Omid,et al.  Development of an android app to estimate chlorophyll content of corn leaves based on contact imaging , 2015, Comput. Electron. Agric..

[8]  Douglas E. Karcher,et al.  The Assessment of Leaf Nitrogen in Corn from Digital Images , 2011 .

[9]  Alberto J. Palma,et al.  Using the mobile phone as Munsell soil-colour sensor: An experiment under controlled illumination conditions , 2013 .

[10]  T. Tuong,et al.  Chlorophyll meter-based nitrogen management of rice grown under alternate wetting and drying irrigation , 2011 .

[11]  Lefeng Qiu,et al.  Investigation of SPAD meter-based indices for estimating rice nitrogen status , 2010 .

[12]  Ž. Živković,et al.  ARTIFICIAL NEURAL NETWORK METHOD APPLIED ON THE NONLINEAR MULTIVARIATE PROBLEMS , 2009 .

[13]  Avinash Agarwal,et al.  Assessment of spinach seedling health status and chlorophyll content by multivariate data analysis and multiple linear regression of leaf image features , 2018, Comput. Electron. Agric..

[14]  M. Omid,et al.  Feasibility of using smart phones to estimate chlorophyll content in corn plants , 2017, Photosynthetica.

[15]  Y. Wang,et al.  Estimating nitrogen status of rice using the image segmentation of G-R thresholding method , 2013 .

[16]  Douglas E. Karcher,et al.  Association of “Greenness” in Corn with Yield and Leaf Nitrogen Concentration , 2011 .

[17]  Marcelo Schramm Mielke,et al.  Relationships between reflectance and absorbance chlorophyll indices with RGB (Red, Green, Blue) image components in seedlings of tropical tree species at nursery stage , 2018, New Forests.

[18]  Satya Prakash Yadav,et al.  Estimation of the chlorophyll content of micropropagated potato plants using RGB based image analysis , 2010, Plant Cell, Tissue and Organ Culture (PCTOC).

[19]  Nuntaporn Moonrungsee,et al.  Colorimetric analyzer based on mobile phone camera for determination of available phosphorus in soil. , 2015, Talanta.

[20]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[21]  D. Haboudane,et al.  New spectral indicator assessing the efficiency of crop nitrogen treatment in corn and wheat , 2010 .

[22]  J. Markwell,et al.  Calibration of the Minolta SPAD-502 leaf chlorophyll meter , 2004, Photosynthesis Research.

[23]  Oliver Zielinski,et al.  SmartFluo: A Method and Affordable Adapter to Measure Chlorophyll a Fluorescence with Smartphones , 2017, Sensors.

[24]  Paul Jarvis,et al.  Use of a SPAD-502 meter to measure leaf chlorophyll concentration in Arabidopsis thaliana , 2011, Photosynthesis Research.

[25]  A. K. Pattanayak,et al.  Intelligent image analysis (IIA) using artificial neural network (ANN) for non-invasive estimation of chlorophyll content in micropropagated plants of potato , 2017, In Vitro Cellular & Developmental Biology - Plant.

[26]  Alexander F. H. Goetz,et al.  Remote sensing for exploration; an overview , 1983 .

[27]  Fei Li,et al.  Reflectance estimation of canopy nitrogen content in winter wheat using optimised hyperspectral spectral indices and partial least squares regression , 2014 .

[28]  Yasuomi Ibaraki,et al.  Development of a digital image analysis method for real-time estimation of chlorophyll content in micropropagated potato plants , 2012, Plant Biotechnology Reports.

[29]  C. Pulvento,et al.  Non-destructive evaluation of chlorophyll content in quinoa and amaranth leaves by simple and multiple regression analysis of RGB image components , 2014, Photosynthesis Research.

[30]  Kenji Omasa,et al.  Estimating rice chlorophyll content and leaf nitrogen concentration with a digital still color camera under natural light , 2014, Plant Methods.

[31]  Miguel Quemada,et al.  Use of a chlorophyll meter to assess nitrogen nutrition index during the growth cycle in winter wheat , 2017 .

[32]  Jian Yang,et al.  Using a chlorophyll meter to estimate tea leaf chlorophyll and nitrogen contents , 2012 .

[33]  Li Jinwen.  Determination of Canopys Average SPAD Readings Based on the Analysis ofDigital Images , 2014 .

[34]  Makoto Nakatani,et al.  An Algorithm for Estimating Chlorophyll Content in Leaves Using a Video Camera , 1998 .

[35]  H. Pleijel,et al.  Evaluating the relationship between leaf chlorophyll concentration and SPAD-502 chlorophyll meter readings , 2007, Photosynthesis Research.

[36]  Suporn Pongnumkul,et al.  Applications of Smartphone-Based Sensors in Agriculture: A Systematic Review of Research , 2015, J. Sensors.

[37]  A. Gitelson,et al.  Novel algorithms for remote estimation of vegetation fraction , 2002 .

[38]  Humberto Bustince,et al.  New method to assess barley nitrogen nutrition status based on image colour analysis , 2009 .

[39]  K. J. Goh,et al.  Rapid determination of leaf chlorophyll concentration, photosynthetic activity and NK concentration of Elaies guineensis via correlated SPAD-502 chlorophyll index. , 2015 .

[40]  M. Richardson,et al.  Quantifying Turfgrass Color Using Digital Image Analysis , 2003 .

[41]  V. Stoleru,et al.  Effects of inoculation with plant growth promoting rhizobacteria on photosynthesis, antioxidant status and yield of runner bean , 2013 .

[42]  V. S. S. Prasad,et al.  Applications And Potentials Of Artificial Neural Networks In Plant Tissue Culture , 2008 .

[43]  Anatoly A. Gitelson,et al.  A Comparison of Two Techniques for Nondestructive Measurement of Chlorophyll Content in Grapevine Leaves , 2008 .

[44]  A. Krogh.  What are artificial neural networks? , 2008, Nature Biotechnology.

[45]  J. Kurbatova,et al.  Use of the atLEAF+ chlorophyll meter for a nondestructive estimate of chlorophyll content , 2016, Photosynthetica.

[46]  Yong He,et al.  Citrus yield estimation based on images processed by an Android mobile phone , 2013 .

[47]  S. Capuani,et al.  A novel method for the estimation of soybean chlorophyll content using a smartphone and image analysis , 2016, Photosynthetica.

[48]  A. Wellburn,et al.  Determinations of total carotenoids and chlorophylls a and b of leaf extracts in different solvents , 1983 .

[49]  Taman Sains Selangor,et al.  Rapid Determination of Leaf Chlorophyll Concentration, Photosynthetic Activity and NK Concentration of Elaies guineensis Via Correlated SPAD-502 Chlorophyll Index , 2015 .

[50]  J. Dungan,et al.  Exploring the relationship between reflectance red edge and chlorophyll content in slash pine. , 1990, Tree physiology.

[51]  Byun-Woo Lee,et al.  Estimation of rice growth and nitrogen nutrition status using color digital camera image analysis , 2013 .

[52]  J. Vollmann,et al.  Original paper: Digital image analysis and chlorophyll metering for phenotyping the effects of nodulation in soybean , 2011 .

[53]  Li Jinwen.  Determination of Canopy’s Average SPAD Readings Based on the Analysis of Digital Images , 2014 .

[54]  Michael P. Pound,et al.  An introduction to images and image analysis , 2014 .

[55]  Howard B. Demuth,et al.  Neutral network toolbox for use with Matlab , 1995 .

[56]  Weixing Cao,et al.  Indicators for diagnosing nitrogen status of rice based on chlorophyll meter readings , 2016 .

[57]  D. Walvoort,et al.  A linear model to predict with a multi‐spectral radiometer the amount of nitrogen in winter wheat , 2006 .

[58]  Raffaele Casa,et al.  Development of an app for estimating leaf area index using a smartphone. Trueness and precision determination and comparison with other indirect methods , 2013 .