Hyperspectral imaging of blue stain fungi on coated and uncoated wooden surfaces.

摘要

Hyperspectral imaging has been applied on samples of coated and uncoated Norway spruce (Picea abies) to detect and quantify blue stain fungi that has colonized and grown on the surface of the samples. A clear visualization of the fungi was obtained through a Principal Component Analysis of the hyperspectral images and the amount of mould coverage could be estimated for each sample. The signal from the fungi on the hyperspectral images in near-infrared wavelengths could clearly be distinguished from water and moisture on the samples. The results indicate that NIR hyperspectral imaging can be used as a tool for assessing coverage of surface fungi and event spectral classification of the two fungal species Aureobasidium pullulans and Cladosporium cladosporioides. We suggest additional case studies both in laboratory and in outdoor environment for further optimization to encompass this method for a broader variety of fungal species and for different climatic conditions.