Laser-light backscattering imaging for early decay detection in citrus fruit using both a statistical and a physical model

Abstract The early detection of decay caused by fungi in citrus fruit is a primary concern in the post-harvest phase, the automation of this task still being a challenge. This work reports new progress in the automatic detection of early symptoms of decay in citrus fruit after infection with the pathogen Penicillium digitatum using laser-light backscattering imaging. Backscattering images of sound and decaying parts of the surface of oranges cv. ‘Valencia late’ were obtained using laser diode modules emitting at five wavelengths in the visible and near-infrared regions. The images of backscattered light captured by a camera had radial symmetry with respect to the incident point of the laser beam, these being reduced to a one-dimensional profile through radial averaging. Two models were used to characterise backscattering profiles: a statistical model using the Gaussian–Lorentzian cross product (GL) distribution function with five parameters and a physical approach calculating the absorption, μ a , and reduced scattering, μ s ′ , coefficients from Farrell’s diffusion theory. Models described radial profiles accurately, with slightly better curve-fitting results ( R 2  ⩾ 0.996) for the GL model compared to Farrell’s model ( R 2  ⩾ 0.982), both indicating significant differences in the parameters between sound and decaying orange skin at the five wavelengths. For dimensionality reduction purposes, feature selection methods were employed to select the most relevant backscattering profile parameters for the detection of early decay lesions. The feature vectors obtained were used to discriminate between sound and decaying skin using a supervised classifier based on linear discriminant analysis. The best classification results were achieved using a reduced set of GL parameters, yielding a maximum overall classification accuracy of 93.4%, with a percentage of well-classified sound and decaying samples of 92.5% and 94.3%, respectively. Results also pointed out application limits of Farrell’s diffusion theory at 532 nm laser wavelength, for which high absorption of pigments occurred.

[1]  R. Lu,et al.  Prediction of Apple Internal Quality Using Spectral Absorption and Scattering Properties , 2009 .

[2]  Renfu Lu,et al.  Hyperspectral and multispectral imaging for evaluating food safety and quality , 2013 .

[3]  Mahmoud Omid,et al.  Principles and Applications of Light Backscattering Imaging in Quality Evaluation of Agro-food Products: a Review , 2012, Food and Bioprocess Technology.

[4]  Jianwei Qin,et al.  Measurement of the Absorption and Scattering Properties of Turbid Liquid Foods Using Hyperspectral Imaging , 2007, Applied spectroscopy.

[5]  H. A. Ferwerda,et al.  Scattering and absorption of turbid materials determined from reflection measurements. 1: theory. , 1983, Applied optics.

[6]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  P. Williams,et al.  Near-Infrared Technology in the Agricultural and Food Industries , 1987 .

[8]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..

[9]  D. Bulanon,et al.  Classification of grapefruit peel diseases using color texture feature analysis , 2009 .

[10]  Shutao Li,et al.  Gene Feature Extraction Using T-Test Statistics and Kernel Partial Least Squares , 2006, ICONIP.

[11]  Andrew Gelman,et al.  Data Analysis Using Regression and Multilevel/Hierarchical Models , 2006 .

[12]  J. Fleiss.  Statistical methods for rates and proportions , 1974 .

[13]  V. Tuchin.  Tissue Optics: Light Scattering Methods and Instruments for Medical Diagnosis , 2000 .

[14]  J. Eckert.  Impact of fungicide resistance on citrus fruit decay control , 1990 .

[15]  M. Zude.  Comparison of indices and multivariate models to non-destructively predict the fruit chlorophyll by means of visible spectrometry in apple fruit , 2003 .

[16]  Yankun Peng,et al.  Prediction of apple fruit firmness and soluble solids content using characteristics of multispectral scattering images , 2007 .

[17]  José Blasco,et al.  Hyperspectral LCTF-based system for classification of decay in mandarins caused by Penicillium digitatum and Penicillium italicum using the most relevant bands and non-linear classifiers , 2013 .

[18]  Arthur R. Weeks.  Fundamentals of electronic image processing , 1996, SPIE/IEEE series on imaging science and engineering.

[19]  Milind S. Ladaniya,et al.  Citrus Fruit: Biology, Technology and Evaluation , 2008 .

[20]  Manuela Zude,et al.  Spectral shift as advanced index for fruit chlorophyll breakdown , 2014, Food and Bioprocess Technology.

[21]  J. Sim,et al.  The kappa statistic in reliability studies: use, interpretation, and sample size requirements. , 2005, Physical therapy.

[22]  G. E. Brown,et al.  Polygalacturonase from citrus fruit infected with Penicillium italicum. , 1981 .

[23]  Naoshi Kondo,et al.  Investigation of Excitation Wavelength for Fluorescence Emission of Citrus Peels based on UV-VIS Spectra , 2012 .

[24]  Chulhee Lee,et al.  Feature extraction based on the Bhattacharyya distance , 2003, Pattern Recognit..

[25]  B. Wilson,et al.  A diffusion theory model of spatially resolved, steady-state diffuse reflectance for the noninvasive determination of tissue optical properties in vivo. , 1992, Medical physics.

[26]  Manuela Zude,et al.  Analysis of laser light propagation in kiwifruit using backscattering imaging and Monte Carlo simulation , 2009 .

[27]  David C. Slaughter,et al.  Non-destructive freeze damage detection in oranges using machine vision and ultraviolet fluorescence , 2008 .

[28]  José Blasco,et al.  Recognition and classification of external skin damage in citrus fruits using multispectral data and morphological features , 2009 .

[29]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[30]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[31]  Antonio M. López,et al.  Feature Selection Based on a New Formulation of the Minimal-Redundancy-Maximal-Relevance Criterion , 2007, IbPRIA.

[32]  Alan M. Lefcourt,et al.  A novel integrated PCA and FLD method on hyperspectral image feature extraction for cucumber chilling damage inspection , 2004 .

[33]  Nuria Aleixos,et al.  Erratum to: Advances in Machine Vision Applications for Automatic Inspection and Quality Evaluation of Fruits and Vegetables , 2011 .

[34]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[35]  José Blasco,et al.  Computer vision detection of peel defects in citrus by means of a region oriented segmentation algorithm , 2007 .

[36]  José Blasco,et al.  Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques , 2012, Expert Syst. Appl..

[37]  Hiroshi Shimizu,et al.  A Double Image Acquisition System with Visible and UV LEDs for Citrus Fruit , 2009, J. Robotics Mechatronics.

[38]  R. Lu,et al.  Measurement of the optical properties of fruits and vegetables using spatially resolved hyperspectral diffuse reflectance imaging technique , 2008 .

[39]  M Smith,et al.  Near infrared spectroscopy. , 1999, British journal of anaesthesia.

[40]  Klaus Gottschalk,et al.  An Approach for Monitoring the Moisture Content Changes of Drying Banana Slices with Laser Light Backscattering Imaging , 2008 .

[41]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[42]  Alessandro Torricelli,et al.  Optical properties of developing pip and stone fruit reveal underlying structural changes. , 2015, Physiologia plantarum.

[43]  J. Rodgers,et al.  Thirteen ways to look at the correlation coefficient , 1988 .

[44]  Lluís Palou,et al.  Control of Postharvest Blue and Green Molds of Oranges by Hot Water, Sodium Carbonate, and Sodium Bicarbonate. , 2001, Plant disease.

[45]  Renfu Lu,et al.  MODELING MULTISPECTRAL SCATTERING PROFILES FOR PREDICTION OF APPLE FRUIT FIRMNESS , 2005 .

[46]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[47]  C. Barmore.  Role of pectolytic enzymes and galacturonic acid in citrus fruit decay caused by Penicillium digitatum , 1979 .

[48]  J. Mourant,et al.  Predictions and measurements of scattering and absorption over broad wavelength ranges in tissue phantoms. , 1997, Applied optics.

[49]  José Blasco,et al.  Early decay detection in citrus fruit using laser-light backscattering imaging , 2013 .

[50]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[51]  Fast and accurate expression for the Voigt function. Application to the determination of uranium M linewidths , 2008 .

[52]  Nuria Aleixos,et al.  Selection of Optimal Wavelength Features for Decay Detection in Citrus Fruit Using the ROC Curve and Neural Networks , 2013, Food and Bioprocess Technology.

[53]  Stan Naydin,et al.  Topical delivery of lycopene using microemulsions: enhanced skin penetration and tissue antioxidant activity. , 2010, Journal of pharmaceutical sciences.

[54]  Vincent Baeten,et al.  On-line analysis of intact olive fruits by vis–NIR spectroscopy: Optimisation of the acquisition parameters , 2012 .

[55]  D. Aboutajdine,et al.  Feature Selection on Supervised Classification Using Wilks Lambda Statistic , 2007, 2007 International Symposium on Computational Intelligence and Intelligent Informatics.

[56]  Antonio J. Serrano,et al.  Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images , 2013, Food and Bioprocess Technology.

[57]  Manuela Zude,et al.  Predicting soluble solid content and firmness in apple fruit by means of laser light backscattering image analysis , 2007 .

[58]  Tomoo Shiigi,et al.  Evaluation of the reasons why freshly appearing citrus peel fluorescence during automatic inspection by fluorescent imaging technique , 2011, International Conference on Quality Control by Artificial Vision.

[59]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[60]  Renfu Lu,et al.  Spectral Absorption and Scattering Properties of Normal and Bruised Apple Tissue , 2010 .