Detection of Oil Chestnuts Infected by Blue Mold Using Near-Infrared Hyperspectral Imaging Combined with Artificial Neural Networks

Mildew damage is a major reason for chestnut poor quality and yield loss. In this study, a near-infrared hyperspectral imaging system in the 874–1734 nm spectral range was applied to detect the mildew damage to chestnuts caused by blue mold. Principal component analysis (PCA) scored images were firstly employed to qualitatively and intuitively distinguish moldy chestnuts from healthy chestnuts. Spectral data were extracted from the hyperspectral images. A successive projections algorithm (SPA) was used to select 12 optimal wavelengths. Artificial neural networks, including back propagation neural network (BPNN), evolutionary neural network (ENN), extreme learning machine (ELM), general regression neural network (GRNN) and radial basis neural network (RBNN) were used to build models using the full spectra and optimal wavelengths to distinguish moldy chestnuts. BPNN and ENN models using full spectra and optimal wavelengths obtained satisfactory performances, with classification accuracies all surpassing 99%. The results indicate the potential for the rapid and non-destructive detection of moldy chestnuts by hyperspectral imaging, which would help to develop online detection system for healthy and blue mold infected chestnuts.

[1]  Chu Zhang,et al.  Identification of coffee bean varieties using hyperspectral imaging: influence of preprocessing methods and pixel-wise spectra analysis , 2018, Scientific Reports.

[2]  Hanping Mao,et al.  Quantitative Determination of Rice Moisture Based on Hyperspectral Imaging Technology and BCC‐LS‐SVR Algorithm , 2017 .

[3]  D. Hatcher,et al.  ORIGINAL ARTICLE: Assessment of mildew levels in wheat samples based on spectral characteristics of bulk grains: Assessment of mildew levels in wheat samples , 2010 .

[4]  Lin Zhang,et al.  Study on the Methods of Detecting Cucumber Downy Mildew Using Hyperspectral Imaging Technology , 2012 .

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

[6]  Peter C. Jurs,et al.  QSAR/QSPR Studies Using Probabilistic Neural Networks and Generalized Regression Neural Networks , 2002, J. Chem. Inf. Comput. Sci..

[7]  Pedro Antonio Gutiérrez,et al.  Logistic Regression by Means of Evolutionary Radial Basis Function Neural Networks , 2011, IEEE Transactions on Neural Networks.

[8]  Yufeng Ge,et al.  Temporal dynamics of maize plant growth, water use, and leaf water content using automated high throughput RGB and hyperspectral imaging , 2016, Comput. Electron. Agric..

[9]  Ruiliang Pu,et al.  Detecting powdery mildew of winter wheat using leaf level hyperspectral measurements , 2012 .

[10]  Yufeng Ge,et al.  High Throughput In vivo Analysis of Plant Leaf Chemical Properties Using Hyperspectral Imaging , 2017, Front. Plant Sci..

[11]  N. Kalaiarasi,et al.  Internal Fault Identification and Classification of Transformer with the Aid of Radial Basis Neural Network (RBNN) , 2014 .

[12]  Tülay Yildirim,et al.  Genetic optimization of GRNN for pattern recognition without feature extraction , 2008, Expert Syst. Appl..

[13]  Yankun Peng,et al.  Hyperspectral Scattering Profiles for Prediction of Beef Tenderness , 2008 .

[14]  José María Valls,et al.  Evolving Generalized Euclidean Distances for Training RBNN , 2007, Comput. Artif. Intell..

[15]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[16]  Lorenzo Bruzzone,et al.  Kernel-based methods for hyperspectral image classification , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Paul Scheunders,et al.  Close range hyperspectral imaging of plants: A review , 2017 .

[18]  Jon Atli Benediktsson,et al.  Recent Advances in Techniques for Hyperspectral Image Processing , 2009 .

[19]  U. Knauer,et al.  Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images , 2017, Plant Methods.

[20]  Danilo Monarca,et al.  Detection of Mold-Damaged Chestnuts by Near-Infrared Spectroscopy , 2014 .

[21]  Dimitris G. Manolakis,et al.  Detection algorithms for hyperspectral imaging applications , 2002, IEEE Signal Process. Mag..

[22]  Santosh Lohumi,et al.  Nondestructive Evaluation for the Viability of Watermelon (Citrullus lanatus) Seeds Using Fourier Transform Near Infrared Spectroscopy , 2013 .

[23]  Stephen J. Symons,et al.  Quantification of Mildew Damage in Soft Red Winter Wheat Based on Spectral Characteristics of Bulk Samples: A Comparison of Visible-Near-Infrared Imaging and Near-Infrared Spectroscopy , 2013, Food and Bioprocess Technology.

[24]  Werner B. Herppich,et al.  Hyperspectral and Chlorophyll Fluorescence Imaging for Early Detection of Plant Diseases, with Special Reference to Fusarium spec. Infections on Wheat , 2014 .

[25]  T. Sieber,et al.  Influence of Fruit Treatments on Perishability During Cold Storage of Sweet Chestnuts , 2006 .

[26]  Noel D.G. White,et al.  Feasibility of near-infrared hyperspectral imaging to differentiate Canadian wheat classes , 2008 .

[27]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[28]  Hao Hu,et al.  Estimation of rice neck blasts severity using spectral reflectance based on BP-neural network , 2011, Acta Physiologiae Plantarum.

[29]  C. Gouveia,et al.  Assessment of weather-related risk on chestnut productivity , 2011 .

[30]  Q. Wang,et al.  Decay Mechanism of the Chestnut Stored in Low Temperature , 2012 .

[31]  D. W. Fulbright,et al.  Shell mold and kernel decay of fresh chestnuts in Michigan , 2010 .

[32]  Yi Yang,et al.  [Dynamic Detection of Fresh Jujube Based on ELM and Visible/Near Infrared Spectra]. , 2015, Guang pu xue yu guang pu fen xi = Guang pu.

[33]  A. Roli.  Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[34]  M. C. U. Araújo,et al.  The successive projections algorithm for variable selection in spectroscopic multicomponent analysis , 2001 .

[35]  Naif Alajlan,et al.  Differential Evolution Extreme Learning Machine for the Classification of Hyperspectral Images , 2014, IEEE Geoscience and Remote Sensing Letters.

[36]  Sun Jun,et al.  Detecting Nitrogen Content in Lettuce Leaves Based on Hyperspectral Imaging and Multiple Regression Analysis , 2013 .

[37]  Jun Wang,et al.  Prediction of egg storage time and yolk index based on electronic nose combined with chemometric methods , 2017 .