Thermal and hyperspectral imaging for Norway spruce (Picea abies) seeds screening

Hyperspectral and thermal lifetime imaging were used to assess spruce seed quality.Viable, empty and infested seeds were resolved with high accuracy with both methods.400-1000nm data was not as informative as 1000-2500nm and thermal decay data.Classification of 93% accuracy was obtained using three wavelengths in SWIR range.The results suggest that high-throughput spruce seed quality testing is possible. The quality of seeds used in agriculture and forestry is tightly linked to the plant productivity. Thus, the development of high-throughput nondestructive methods to classify the seeds is of prime interest. Visible and near infrared (VNIR, 400-1000nm range) and short-wave infrared (SWIR, 1000-2500nm range) hyperspectral imaging techniques were compared to an infrared lifetime imaging technique to evaluate Norway spruce (Picea abies (L.) Karst.) seed quality. Hyperspectral image and thermal data from 1606 seeds were used to identify viable seeds, empty seeds and seeds infested by Megastigmus sp. larvae. The spectra of seeds obtained from hyperspectral imaging, especially in SWIR range and the thermal signal decay of seeds following an exposure to a short light pulse were characteristic of the seed status. Classification of the seeds to three classes was performed with a Support Vector Machine (nu-SVM) and sparse logistic regression based feature selection. Leave-One-Out classification resulted to 99% accuracy using either thermal or spectral measurements compared to radiography classification. In spectral imaging case, all important features were located in the SWIR range. Furthermore, the classification results showed that accurate (93.8%) seed sorting can be achieved with a simpler method based on information from only three hyperspectral bands at 1310nm, 1710nm and 1985nm locations, suggesting a possibility to build an inexpensive screening device. The results indicate that combined classification methods with hyperspectral imaging technique and infrared lifetime imaging technique constitute practically high performance fast and non-destructive techniques for high-throughput seed screening.

[1]  Mahfuza Begum,et al.  Pathogenicity of Colletotrichum truncatum and its influence on soybean seed quality. , 2008 .

[2]  Noel D.G. White,et al.  Identification of insect-damaged wheat kernels using short-wave near-infrared hyperspectral and digital colour imaging , 2010 .

[3]  Mahesh Pal,et al.  Multinomial logistic regression-based feature selection for hyperspectral data , 2012, Int. J. Appl. Earth Obs. Geoinformation.

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

[5]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[6]  Mulualem Tigabu,et al.  Application of near-infrared spectroscopy for the detection of internal insect infestation in Picea abies seed lots , 2004 .

[7]  John Chambers,et al.  Detection of external and internal insect infestation in wheat by near-infrared reflectance spectroscopy , 1996 .

[8]  W. Fred McClure,et al.  Near-Infrared Spectroscopy of Biomaterials , 2006 .

[9]  P. Curran.  Remote sensing of foliar chemistry , 1989 .

[10]  Manfred Hartbauer,et al.  Noninvasive diagnosis of seed viability using infrared thermography , 2010, Proceedings of the National Academy of Sciences.

[11]  Rasmus Bro,et al.  Finding relevant spectral regions between spectroscopic techniques by use of cross model validation and partial least squares regression. , 2007, Analytica chimica acta.

[12]  S. Sathiya Keerthi,et al.  A simple and efficient algorithm for gene selection using sparse logistic regression , 2003, Bioinform..

[13]  M. Choung,et al.  Nondestructive determination of oil content and fatty acid composition in perilla seeds by near-infrared spectroscopy. , 2007, Journal of agricultural and food chemistry.

[14]  Erkki Pulliainen,et al.  Chemical composition of Piceaabies and Pinussylvestris seeds under subarctic conditions , 1984 .

[15]  Jerome J. Workman,et al.  Application of NIR spectroscopy to agricultural products. In 'Handbook of Near-infrared Analysis'.(E , 1992 .

[16]  Ville Heikkinen,et al.  Logistic Regression-Based Spectral Band Selection for Tree Species Classification: Effects of Spatial Scale and Balance in Training Samples , 2014, IEEE Geoscience and Remote Sensing Letters.

[17]  M. Choung,et al.  Nondestructive determination of lignans and lignan glycosides in sesame seeds by near infrared reflectance spectroscopy. , 2006, Journal of agricultural and food chemistry.

[18]  A. Roques,et al.  Multinucleate storage cells in Douglas-fir (Pseudotsuga menziesii (Mirbel) Franco) and the effect of seed parasitism by the chalcid Megastigmus spermotrophus Wachtl , 2005, Heredity.

[19]  J. Baker,et al.  Automated Nondestructive Detection of Internal Insect Infestation of Wheat Kernels by Using Near-Infrared Reflectance Spectroscopy , 1998 .

[20]  Noel D.G. White,et al.  Detection of insect-damaged wheat kernels using near-infrared hyperspectral imaging , 2009 .

[21]  Margarita Ruiz-Altisent,et al.  Review: Sensors for product characterization and quality of specialty crops-A review , 2010 .

[22]  Floyd E. Dowell,et al.  AUTOMATED DETECTION OF SINGLE WHEAT KERNELS CONTAINING LIVE OR DEAD INSECTS USING NEAR–INFRARED REFLECTANCE SPECTROSCOPY , 2003 .

[23]  D. B. Egli,et al.  Temperature during seed filling and soybean seed germination and vigour , 1997 .

[24]  Reza Ehsani,et al.  Review: A review of advanced techniques for detecting plant diseases , 2010 .

[25]  Gavin C. Cawley,et al.  Gene Selection in Cancer Classification using Sparse Logistic Regression with Bayesian Regularisation , 2006 .

[26]  James W. McNicol,et al.  Reconstruction of constituent spectra for individual samples through principal component analysis of near-infrared spectra , 1989 .

[27]  Yasumaru Hirai,et al.  Evaluation of an analytical method to identify determinants of rice yield components and protein content , 2012 .

[28]  S. Lazzari,et al.  Correlation between the infestation level of Sitophilus zeamais Motschulsky, 1855 (Coleoptera, Curculionidae) and the quality factors of stored corn, Zea mays L. (Poaceae) , 2003 .

[29]  Toshikazu Morishita,et al.  Nondestructive estimation of fatty acid composition in seeds of Brassica napus L. by near-infrared spectroscopy , 1998 .

[30]  Geon-Hee Kim,et al.  Mid-Infrared Lifetime Imaging for Viability Evaluation of Lettuce Seeds Based on Time-Dependent Thermal Decay Characterization , 2013, Sensors.

[31]  S. Bregaglio,et al.  A software component implementing a library of models for the simulation of pre-harvest rice grain quality , 2014 .

[32]  Heikki Kallio,et al.  Triacylglycerols in the seeds of northern Scots pine, Pinus sylvestris L., and Norway spruce, Picea abies (L.) Karst. , 1995, Trees.

[33]  Floyd E. Dowell,et al.  Comparison of Three near Infrared Spectrophotometers for Infestation Detection in Wild Blueberries Using Multivariate Calibration Models , 2009 .

[34]  Floyd E. Dowell,et al.  Detection of Parasitized Rice Weevils in Wheat Kernels with Near-Infrared Spectroscopy1☆ , 1999 .

[35]  Chu Zhang,et al.  Rice Seed Cultivar Identification Using Near-Infrared Hyperspectral Imaging and Multivariate Data Analysis , 2013, Sensors.

[36]  J. Shenk,et al.  Application of NIR Spectroscopy to Agricultural Products , 1992 .

[37]  Stephen R. Delwiche,et al.  Multiple view image analysis of freefalling U.S. wheat grains for damage assessment , 2013 .

[38]  Yong He,et al.  Application of Hyperspectral Imaging and Chemometric Calibrations for Variety Discrimination of Maize Seeds , 2012, Sensors.

[39]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[40]  Fengle Zhu,et al.  Application of hyperspectral imaging technology to discriminate different geographical origins of Jatropha curcas L. seeds , 2013 .

[41]  Yong He,et al.  Theory and application of near infrared reflectance spectroscopy in determination of food quality , 2007 .