Classification and characterization of blueberry mechanical damage with time evolution using reflectance, transmittance and interactance imaging spectroscopy

Comparative study on reflectance, transmittance and interactance was conducted.Transmittance-based classifiers classified blueberry mechanical damage well.Fresh mechanical damage was hard to identify by spectral data.Two days aged damage could be identified by spectral data. The aim of this work was to evaluate the performance of hyperspectral data coupled with chemometrics methods in characterizing and detecting the non-visible mechanical damage of blueberries with time evolution. Reflectance and transmittance as well as interactance hypercubes were automatically segmented by the region growing based algorithms. The maximum-normalized spectra were pretreated by the Standard Normal Variate algorithm, and subsequently the Competitive Adaptive Reweighted Sampling algorithm was applied to extract the damage-specific wavelengths. Based on confusion matrices and area under Receiver Operating Characteristics curves, transmittance showed relatively superior performance to reflectance and interactance. Application of new sample set subjected to impact tests with time evolution, results demonstrated that it was especially difficult to distinguish fresh damage in blueberry. At 2days after impacted, several transmittance-based classifiers obtained satisfactory accuracies for classifying damaged (sound) blueberries: logistic regression 79.1% (85.7%), multilayer perceptron-back propagation 74.4% (92.1%) and logistic function tree 72.1% (95.2%). Furthermore, the physical property preliminarily proved to be more pronounced than the absorbed impact energy for damage incidence and severity of blueberry via the use of multiple comparison.

[1]  Fred Godtliebsen,et al.  Automatic nematode detection in cod fillets (Gadus morhua L.) by hyperspectral imaging , 2012 .

[2]  Ghasem Abedi,et al.  Bruise susceptibilities of Golden Delicious apples as affected by mechanical impact and fruit properties , 2013, The Journal of Agricultural Science.

[3]  Veerle Van linden,et al.  Impact damage of apples during transport and handling , 2007 .

[4]  Abhijit Kar,et al.  Recent developments in applications of MRI techniques for foods and agricultural produce—an overview , 2013, Journal of Food Science and Technology.

[5]  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.

[6]  Gui-fang Wu,et al.  Investigating the effects of simulated transport vibration on tomato tissue damage based on vis/NIR spectroscopy , 2014 .

[7]  Umezuruike Linus Opara,et al.  Estimating blueberry mechanical properties based on random frog selected hyperspectral data , 2015 .

[8]  Daniel Sbarbaro,et al.  Hyperspectral transmittance imaging of the shell-free cooked clam Mulinia edulis for parasite detection , 2013 .

[9]  Renfu Lu,et al.  Assessment of internal quality of blueberries using hyperspectral transmittance and reflectance images with whole spectra or selected wavelengths , 2014 .

[10]  Francisco Jiménez-Jiménez,et al.  Non-destructive determination of impact bruising on table olives using Vis–NIR spectroscopy , 2012 .

[11]  V. Wu,et al.  Antimicrobial effect of blueberry (Vaccinium corymbosum L.) extracts against the growth of Listeria monocytogenes and Salmonella Enteritidis , 2014 .

[12]  P. Baranowski,et al.  Supervised classification of bruised apples with respect to the time after bruising on the basis of hyperspectral imaging data , 2013 .

[13]  Hongdong Li,et al.  Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. , 2009, Analytica chimica acta.

[14]  Wenqian Huang,et al.  Development of a multispectral imaging system for online detection of bruises on apples , 2015 .

[15]  Daniel E. Guyer,et al.  Detecting internal insect infestation in tart cherry using transmittance spectroscopy , 2008 .

[16]  Gabriel A. Leiva-Valenzuela,et al.  Automatic detection of orientation and diseases in blueberries using image analysis to improve their postharvest storage quality , 2013 .

[17]  Zhiguo Li,et al.  Quantitative evaluation of mechanical damage to fresh fruits , 2014 .

[18]  Won Suk Lee,et al.  Identifying blueberry fruit of different growth stages using natural outdoor color images , 2014 .

[19]  Min Zhang,et al.  Detection of insect-damaged vegetable soybeans using hyperspectral transmittance image , 2013 .

[20]  S. Cessie,et al.  Ridge Estimators in Logistic Regression , 1992 .

[21]  João Gama,et al.  Functional Trees , 2001, Machine Learning.

[22]  Stephen R. Delwiche,et al.  Hyperspectral near-infrared imaging for the detection of physical damages of pear , 2014 .

[23]  A. Peirs,et al.  Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A review , 2007 .

[24]  Renfu Lu,et al.  Hyperspectral Imaging-Based Classification and Wavebands Selection for Internal Defect Detection of Pickling Cucumbers , 2013, Food and Bioprocess Technology.

[25]  Jorge Chanona-Pérez,et al.  Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning , 2014 .

[26]  Qibing Zhu,et al.  Automatic threshold method and optimal wavelength selection for insect-damaged vegetable soybean detection using hyperspectral images , 2014 .

[27]  Michael Knee,et al.  Fruit quality and its biological basis. , 2002 .

[28]  Di Wu,et al.  Advanced applications of hyperspectral imaging technology for food quality and safety analysis and assessment: A review — Part II: Applications , 2013 .

[29]  Da-Wen Sun,et al.  Recent Progress of Hyperspectral Imaging on Quality and Safety Inspection of Fruits and Vegetables: A Review. , 2015, Comprehensive reviews in food science and food safety.

[30]  Necla Demir,et al.  Classification of impacted blueberries during storage using an electronic nose. , 2011, Journal of the science of food and agriculture.

[31]  Changying Li,et al.  Gas sensor array for blueberry fruit disease detection and classification , 2010 .

[32]  S. Sathiya Keerthi,et al.  Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[33]  G. Blanco-Roldán,et al.  Isolation of table olive damage causes and bruise time evolution during fruit detachment with trunk shaker. , 2013 .

[34]  J P Wold,et al.  Feasibility of NIR interactance hyperspectral imaging for on-line measurement of crude composition in vacuum packed dry-cured ham slices. , 2013, Meat science.

[35]  Maohua Wang,et al.  Quantitative Determination of Onion Internal Quality Using Reflectance, Interactance, and Transmittance Modes of Hyperspectral Imaging , 2013 .

[36]  P. Baranowski,et al.  Detection of early apple bruises using pulsed-phase thermography , 2009 .

[37]  Tim Holmes,et al.  Quantifying the Diffuse Reflectance Change Caused by Fresh Bruises on Apples , 2014 .

[38]  Josse De Baerdemaeker,et al.  Detecting Bruises on ‘Golden Delicious’ Apples using Hyperspectral Imaging with Multiple Wavebands , 2005 .

[39]  M. Manley.  Near-infrared spectroscopy and hyperspectral imaging: non-destructive analysis of biological materials. , 2014, Chemical Society reviews.

[40]  K. Bunzl,et al.  In situ gamma-spectrometry several years after deposition of radiocesium. Part I. Approximation of depth distributions by the Lorentz function. , 1996, Radiation and environmental biophysics.

[41]  Gamal ElMasry,et al.  High-speed assessment of fat and water content distribution in fish fillets using online imaging spectroscopy. , 2008, Journal of agricultural and food chemistry.

[42]  Piotr Baranowski,et al.  Classification models of bruise and cultivar detection on the basis of hyperspectral imaging data , 2014 .

[43]  Harry Zhang,et al.  Learning probabilistic decision trees for AUC , 2006, Pattern Recognit. Lett..

[44]  D. Ingram,et al.  Overview of the Health Properties of Blueberries , 2013 .

[45]  Morteza Sadeghi,et al.  The effect of impact and fruit properties on the bruising of peach , 2010 .

[46]  Changying Li,et al.  Measurement of mechanical impacts created by rotary, slapper, and sway blueberry mechanical harvesters , 2014 .

[47]  Moon S. Kim,et al.  Detection of Cracks on Tomatoes Using a Hyperspectral Near-Infrared Reflectance Imaging System , 2014, Sensors.

[48]  D. Joyce,et al.  Non-destructive 1H-MRI assessment of flesh bruising in avocado (Persea americana M.) cv. Hass , 2015 .

[49]  Frederick E. Petry,et al.  Principles and Applications , 1997 .

[50]  P. Baranowski,et al.  Detection of early bruises in apples using hyperspectral data and thermal imaging , 2012 .

[51]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[52]  Paul D. Gader,et al.  Hyperspectral band selection for detecting different blueberry fruit maturity stages , 2014 .

[53]  Liang Gong,et al.  Computer vision detection of defective apples using automatic lightness correction and weighted RVM classifier , 2015 .

[54]  Ning Wang,et al.  Early detection of apple bruises on different background colors using hyperspectral imaging , 2008 .

[55]  H. Scherm,et al.  Postharvest Disease Development on Southern Highbush Blueberry Fruit in Relation to Berry Flesh Type and Harvest Method. , 2013, Plant disease.

[56]  D. Lorente,et al.  Development of a Hyperspectral Computer Vision System Based on Two Liquid Crystal Tuneable Filters for Fruit Inspection. Application to Detect Citrus Fruits Decay , 2014, Food and Bioprocess Technology.

[57]  Xiaojing Chen,et al.  Identification of heavy metal-contaminated Tegillarca granosa using infrared spectroscopy , 2015 .

[58]  Umezuruike Linus Opara,et al.  Prediction of mechanical properties of blueberry using hyperspectral interactance imaging , 2016 .

[59]  Yankun Peng,et al.  Hyperspectral Scattering for Assessing Peach Fruit Firmness , 2004 .

[60]  Yibin Ying,et al.  Comparison of diffuse reflectance and transmission mode of visible-near infrared spectroscopy for detecting brown heart of pear , 2007 .

[61]  P. Pathare,et al.  Bruise damage measurement and analysis of fresh horticultural produce-A review , 2014 .

[62]  Yong He,et al.  Identification of crack features in fresh jujube using Vis/NIR hyperspectral imaging combined with image processing , 2014 .

[63]  Yunfei Li,et al.  Effect of transport vibration levels on mechanical damage and physiological responses of Huanghua pears (Pyrus pyrifolia Nakai, cv. Huanghua) , 2007 .

[64]  Eibe Frank,et al.  Logistic Model Trees , 2003, ECML.

[65]  C. Forney,et al.  Microstructural Indicators of Quality-related Characteristics of Blueberries—An Integrated Approach , 2001 .