Journal of Spectral Imaging,   Volume 7   Article ID a8   (2018)

Peer reviewed paper

Near infrared hyperspectral images and pattern recognition techniques used to identify etiological agents of cotton anthracnose and ramulosis

Priscila S.R. Aires,a Francisco F. Gambarra-Neto,b Wirton M. Coutinho,c Alderi E. Araujo,dGilvan Ferreira da Silva,e Josivanda P.G. Gouveiaf and Everaldo P. Medeirosg,*
aFederal University of Campina Grande, Post-graduate Program in Agricultural Engineering, CEP 58.429-140, Campina Grande-PB, Brazil
bFederal University of Paraiba, Graduate Program in Agronomy, CEP 58.397-000, Areia, PB, Brazil
cEmbrapa Algodão, CEP 58428-095, Campina Grande, PB, Brazil
dEmbrapa Algodão, CEP 58428-095, Campina Grande, PB, Brazil
eEmbrapa Amazônia Ocidental, CEP 69010-970, Manaus, AM, Brazil
fFederal University of Campina Grande, Post-graduate Program in Agricultural Engineering, CEP 58.429-140, Campina Grande-PB, Brazil
gEmbrapa Algodão, CEP 58428-095, Campina Grande, PB, Brazil. E-mail: [email protected]

Hyperspectral imaging near infrared (HSI-NIR) has the potential to be used as a non-destructive approach for the analysis of new microbiological matrices of agriculture interest. This article describes a new method for accurately and rapidly classifying the etiological agents Colletotrichum gossypii (CG) and C. gossypii var. cephalosporioides (CGC) grown in a culture medium, using scattering reflectance HSI-NIR and multivariate pattern recognition analysis. Five strains of CG and 46 strains of CGC were used. CG and CGC strains were grown on Czapek-agar medium at 25 °C under a 12-hour photoperiod for 15 days. Molecular identification was performed as a reference for the CG and CGC classes by polymerase chain reaction of the intergenic spacer region of rDNA. The scattering coefficient µs and the absorption coefficient µa were obtained, which resulted in a µs value for CG of 1.37 × 1019 and for CGC of 5.83 × 10–11. These results showed that the use of the standard normal variate was no longer essential and reduced the spectral range from 1000–2500 nm to 1000–1381 nm. The results evidenced two type II errors for the CG 457-2 and CGC 39 samples in the soft independent modelling model of the analogy model. There were no classification errors using the algorithm of the successive projections for variable selection in linear discriminant analysis (SPA-LDA). A parallel validation of the results obtained with SPA-LDA was performed using a box plot analysis with the 11 variables selected by SPA, in which there were no outliers for the HSI-NIR models. The new HSI-NIR and SPA-LDA procedures for the classification of CG and CGC etiological agents are noted for their greater analytical speed, accuracy, simplicity, lower cost and non-destructive nature.

Keywords: fungal identification, fungal taxonomy, non-destructive analysis, cotton crop, hyperspectral image