Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

Cotton seed purity is a critical factor influencing the cotton yield. In this study, near-infrared hyperspectral imaging was used to identify seven varieties of cotton seeds. Score images formed by pixel-wise principal component analysis (PCA) showed that there were differences among different varieties of cotton seeds. Effective wavelengths were selected according to PCA loadings. A self-design convolution neural network (CNN) and a Residual Network (ResNet) were used to establish classification models. Partial least squares discriminant analysis (PLS-DA), logistic regression (LR) and support vector machine (SVM) were used as direct classifiers based on full spectra and effective wavelengths for comparison. Furthermore, PLS-DA, LR and SVM models were used for cotton seeds classification based on deep features extracted by self-design CNN and ResNet models. LR and PLS-DA models using deep features as input performed slightly better than those using full spectra and effective wavelengths directly. Self-design CNN based models performed slightly better than ResNet based models. Classification models using full spectra performed better than those using effective wavelengths, with classification accuracy of calibration, validation and prediction sets all over 80% for most models. The overall results illustrated that near-infrared hyperspectral imaging with deep learning was feasible to identify cotton seed varieties.

[1]  Sung Soo Ahn,et al.  Deep-learned 3D black-blood imaging using automatic labelling technique and 3D convolutional neural networks for detecting metastatic brain tumors , 2018, Scientific Reports.

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

[3]  Chu Zhang,et al.  Detection of Subtle Bruises on Winter Jujube Using Hyperspectral Imaging With Pixel-Wise Deep Learning Method , 2019, IEEE Access.

[4]  R. Galvão,et al.  Classification of individual cotton seeds with respect to variety using near-infrared hyperspectral imaging , 2016 .

[5]  Heung-Il Suk,et al.  Deep Learning in Medical Image Analysis. , 2017, Annual review of biomedical engineering.

[6]  Marcin Pietrzykowski,et al.  Application of near infrared spectroscopy for authentication of Picea abies seed provenance , 2017, New Forests.

[7]  Thomas Arnold,et al.  Hyperspectral imaging: a novel approach for plant root phenotyping , 2018, Plant Methods.

[8]  Dehai Zhu,et al.  Identification of maize seed varieties based on near infrared reflectance spectroscopy and chemometrics , 2018 .

[9]  Xudong Jiang,et al.  Deep Coupled ResNet for Low-Resolution Face Recognition , 2018, IEEE Signal Processing Letters.

[10]  Ferhat Kurtulmuş,et al.  Classification of pepper seeds using machine vision based on neural network , 2016 .

[11]  Junwei Han,et al.  A Survey on Object Detection in Optical Remote Sensing Images , 2016, ArXiv.

[12]  Kamal El-Sankary,et al.  Impact of Approximate Multipliers on VGG Deep Learning Network , 2018, IEEE Access.

[13]  Ponnadurai Ramasami,et al.  Chemical and near-infrared determination of moisture, fat and protein in tuna fishes , 2007 .

[14]  Chu Zhang,et al.  Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network , 2018 .

[15]  Fengfeng Zhang,et al.  A deep learning based feature extraction method on hyperspectral images for nondestructive prediction of TVB-N content in Pacific white shrimp (Litopenaeus vannamei) , 2019, Biosystems Engineering.

[16]  Fang Cheng,et al.  Spectral and Image Integrated Analysis of Hyperspectral Data for Waxy Corn Seed Variety Classification , 2015, Sensors.

[17]  Michael H. Köhler,et al.  A review of hyperspectral imaging for nanoscale materials research , 2019 .

[18]  Yu Xue,et al.  Text classification based on deep belief network and softmax regression , 2016, Neural Computing and Applications.

[19]  Vasilis Valdramidis,et al.  Recent applications of hyperspectral imaging in microbiology. , 2015, Talanta.

[20]  D. Jayas,et al.  Identification of wheat classes using wavelet features from near infrared hyperspectral images of bulk samples. , 2009 .

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

[22]  Dehai Zhu,et al.  Variety identification method of coated maize seeds based on near-infrared spectroscopy and chemometrics , 2015 .

[23]  Yidan Bao,et al.  Hyperspectral imaging for seed quality and safety inspection: a review , 2019, Plant Methods.

[24]  Chen Wang,et al.  Plant variety and cultivar identification: advances and prospects , 2013, Critical reviews in biotechnology.

[25]  Abdul Aziz Jemain,et al.  Partial least squares-discriminant analysis (PLS-DA) for classification of high-dimensional (HD) data: a review of contemporary practice strategies and knowledge gaps. , 2018, The Analyst.

[26]  Andreas Kamilaris,et al.  Deep learning in agriculture: A survey , 2018, Comput. Electron. Agric..

[27]  J. Blasco,et al.  Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality Assessment , 2012, Food and Bioprocess Technology.

[28]  J. Wendel,et al.  Phylogenetics of the Cotton Genus (Gossypium): Character-State Weighted Parsimony Analysis of Chloroplast-DNA Restriction Site Data and Its Systematic and Biogeographic Implications , 1992 .

[29]  Hanping Mao,et al.  Classification of Black Beans Using Visible and Near Infrared Hyperspectral Imaging , 2016 .

[30]  Chu Zhang,et al.  Discrimination of Chrysanthemum Varieties Using Hyperspectral Imaging Combined with a Deep Convolutional Neural Network , 2018, Molecules.

[31]  Chu Zhang,et al.  Identification of Maize Kernel Vigor under Different Accelerated Aging Times Using Hyperspectral Imaging , 2018, Molecules.

[32]  Gang Wang,et al.  Deep Learning-Based Classification of Hyperspectral Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[33]  Bingquan Chu,et al.  Determination of Total Polysaccharides and Total Flavonoids in Chrysanthemum morifolium Using Near-Infrared Hyperspectral Imaging and Multivariate Analysis , 2018, Molecules.

[34]  Mohebbat Mohebbi,et al.  Pomegranate seed clustering by machine vision , 2017, Food science & nutrition.

[35]  Chu Zhang,et al.  Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine , 2016 .

[36]  Ranjithkumar Nagireddy,et al.  DNA Fingerprinting for Identification of Rice Varieties and Seed Genetic Purity Assessment , 2018, Agricultural Research.