Nondestructive measurement of total nitrogen in lettuce by integrating spectroscopy and computer vision

Abstract This study was conducted to develop and assess a method of estimating the nitrogen (N) content of lettuce ( Lactuca sativa ) canopy using a combination of spectroscopy and computer vision for nondestructive N detection. In the experiment, 90 lettuce samples with five N treatments were collected for data acquisition by two different techniques. On the spectroscopy side, canopy spectral reflectance was measured in the wavelength range of 350 to 2500 nm at 1-nm increments. Four spectral intervals (376 variables) were selected by synergy interval partial least squares and were further reduced to 73 wavelength variables, chosen using a genetic algorithm applied to first-order derivatives of the canopy reflectance. On the computer vision side, 11 plant features were extracted from images, including top projected canopy area as a morphological feature; red, green, blue, hue, saturation, and intensity values as color features; and contrast, entropy, energy, and homogeneity as textural features. Next, principal component analysis was implemented on the spectral variables and on the image features, and extreme learning machine modeling was used to fuse the two kinds of data and construct a model. For the optimum model achieved, the root-mean-square error of prediction = 0.3231% and the correlation coefficient of prediction = 0.8864. This work demonstrates that integrating spectroscopy and computer vision with suitable efficient algorithms has high potential for use in the nondestructive measurement of N content in lettuce, considerably improving accuracy over that using a single sensor modality.

[1]  Elfatih M. Abdel-Rahman,et al.  Estimation of sugarcane leaf nitrogen concentration using in situ spectroscopy , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[2]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[3]  Eric O. Postma,et al.  Dimensionality Reduction: A Comparative Review , 2008 .

[4]  Y. Wang,et al.  Estimating nitrogen concentration in rape from hyperspectral data at canopy level using support vector machines , 2012, Precision Agriculture.

[5]  M. Bilgen,et al.  Use of Spectral Reflectance Values for Determining Nitrogen, Phosphorus, and Potassium Contents of Rangeland Plants , 2013 .

[6]  P P Ling,et al.  An automated plant monitoring system using machine vision. , 1996, Acta horticulturae.

[7]  J. F. Reid,et al.  MODELING AND CALIBRATION OF A MULTI-SPECTRAL IMAGING SENSOR FOR IN-FIELD CROP NITROGEN ASSESSMENT , 2006 .

[8]  O. Bruno,et al.  Use of artificial vision techniques for diagnostic of nitrogen nutritional status in maize plants , 2014 .

[9]  René Gislum,et al.  Quantification of nitrogen concentration in perennial ryegrass and red fescue using near-infrared reflectance spectroscopy (NIRS) and chemometrics , 2004 .

[10]  Roman M. Balabin,et al.  Variable selection in near-infrared spectroscopy: benchmarking of feature selection methods on biodiesel data. , 2011, Analytica chimica acta.

[11]  H. Kende,et al.  The Five "Classical" Plant Hormones. , 1997, The Plant cell.

[12]  Ali Akoglu,et al.  Morphological and textural plant feature detection using machine vision for intelligent plant health, growth and quality monitoring , 2011 .

[13]  J. F. Reid,et al.  Evaluation of Colour Representations for Maize Images , 1996 .

[14]  Nancy F. Glenn,et al.  Remote sensing of sagebrush canopy nitrogen , 2012 .

[15]  Vijaya Gopal Kakani,et al.  Nitrogen deficiency effects on plant growth, leaf photosynthesis, and hyperspectral reflectance properties of sorghum , 2005 .

[16]  Jaco Kole,et al.  Determining Nutrient Stress in Lettuce Plants with Machine Vision Technology , 1998 .

[17]  John A. Raven,et al.  Do plants need nitrate? The mechanisms by which nitrogen form affects plants , 2013 .

[18]  Javier Pacheco-Labrador,et al.  Understanding the optical responses of leaf nitrogen in Mediterranean Holm oak (Quercus ilex) using field spectroscopy , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[19]  Ali Akoglu,et al.  Original paper: Lettuce calcium deficiency detection with machine vision computed plant features in controlled environments , 2010 .

[20]  R. Clark,et al.  Reflectance spectroscopy: Quantitative analysis techniques for remote sensing applications , 1984 .

[21]  Masahiko Nagai,et al.  Estimating Canopy Nitrogen Concentration in Sugarcane Using Field Imaging Spectroscopy , 2012, Remote. Sens..

[22]  Federico Pallottino,et al.  Nitrogen Concentration Estimation in Tomato Leaves by VIS-NIR Non-Destructive Spectroscopy , 2011, Sensors.

[23]  G. Meyer,et al.  Color indices for weed identification under various soil, residue, and lighting conditions , 1994 .

[24]  Hirokazu Fukuda,et al.  Non-destructive sensing and its inverse model for canopy parameters using texture analysis and artificial neural network , 2007 .

[25]  Jiewen Zhao,et al.  Nondestructive measurement of total volatile basic nitrogen (TVB-N) content in salted pork in jelly using a hyperspectral imaging technique combined with efficient hypercube processing algorithms , 2013 .

[26]  Francisco M. Padilla,et al.  Evaluation of optical sensor measurements of canopy reflectance and of leaf flavonols and chlorophyll contents to assess crop nitrogen status of muskmelon , 2014 .

[27]  Riccardo Leardi,et al.  Application of genetic algorithm–PLS for feature selection in spectral data sets , 2000 .

[28]  Yongqiang Ye,et al.  Use of leaf color images to identify nitrogen and potassium deficient tomatoes , 2011, Pattern Recognit. Lett..

[29]  Daniel Cozzolino,et al.  Multivariate data analysis applied to spectroscopy: Potential application to juice and fruit quality , 2011 .

[30]  S. Bajwa,et al.  Canopy reflectance response to plant nitrogen accumulation in rice , 2010, Precision Agriculture.

[31]  S. Engelsen,et al.  Interval Partial Least-Squares Regression (iPLS): A Comparative Chemometric Study with an Example from Near-Infrared Spectroscopy , 2000 .

[32]  O. Bruno,et al.  A Diagnostic Tool for Magnesium Nutrition in Maize Based on Image Analysis of Different Leaf Sections , 2014 .

[33]  Fei Liu,et al.  Detecting macronutrients content and distribution in oilseed rape leaves based on hyperspectral imaging , 2013 .

[34]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[35]  Won Suk Lee,et al.  Nondestructive Detection of Nitrogen in Chinese Cabbage Leaves Using VIS–NIR Spectroscopy , 2006 .

[36]  M. D. Craig,et al.  Analysis of aircraft spectrometer data with logarithmic residuals , 1985 .

[37]  G. Neumann,et al.  Rapid effects of nitrogen form on leaf morphogenesis in tobacco. , 2000, Journal of experimental botany.

[38]  Andrew K. Skidmore,et al.  Savanna grass nitrogen to phosphorous ratio estimation using field spectroscopy and the potential for estimation with imaging spectroscopy , 2013, Int. J. Appl. Earth Obs. Geoinformation.