摘要
In this paper,citrus brown spot,huanglongbing,canker,fuliginous,Cercospora sp. and healthy leaves were studied using Fourier transform infrared spectroscopy( FTIR) combined with statistical analysis. The results showed that the spectra of the samples were similar,whereas there were obvious differences in the second derivatives of infrared spectra in the range of 1 500- 700 cm- 1. The correlative analysis were evaluated,results showed that the correlation coefficients were larger than 0. 918 between healthy leaves,and between the same diseased leaves. However,the values were all decreased between healthy and diseased leaves,and among different diseased leaves. The preprocessed original,first derivative and second derivative spectra in the range of 1 200- 700 cm- 1were chosen to evaluated principal component analysis( PCA) and hierarchical cluster analysis( HCA),respectively. The performance of the overall accuracy of PCA was 92.5%,which were better than original dataset and first derivative dataset. HCA by selecting second derivative dataset yield about 90% accuracy. This study proved that FTIR spectroscopy could be detected citrus diseases quickly and accurately.
In this paper,citrus brown spot,huanglongbing,canker,fuliginous,Cercospora sp. and healthy leaves were studied using Fourier transform infrared spectroscopy( FTIR) combined with statistical analysis. The results showed that the spectra of the samples were similar,whereas there were obvious differences in the second derivatives of infrared spectra in the range of 1 500- 700 cm- 1. The correlative analysis were evaluated,results showed that the correlation coefficients were larger than 0. 918 between healthy leaves,and between the same diseased leaves. However,the values were all decreased between healthy and diseased leaves,and among different diseased leaves. The preprocessed original,first derivative and second derivative spectra in the range of 1 200- 700 cm- 1were chosen to evaluated principal component analysis( PCA) and hierarchical cluster analysis( HCA),respectively. The performance of the overall accuracy of PCA was 92.5%,which were better than original dataset and first derivative dataset. HCA by selecting second derivative dataset yield about 90% accuracy. This study proved that FTIR spectroscopy could be detected citrus diseases quickly and accurately.
