Spectral-Based Diagnosis of Cassava Diseases with Crop Leaves

We propose a spectral-based approach for diagnosis of cassava crop diseases. Previously, this diagnosis has been done using plant images taken with a smartphone. For this method disease symptoms need to be visible, but once symptoms have manifested, the root of the plant is already affected and cannot be used for food consumption anymore.

This research presented here is based on the assumption that diseased crops without visible symptoms can be detected using spectral information, allowing for early action measures. In this work we analyze visible and near infrared spectra that were captured on two common cassava diseases found in sub-Saharan Africa as well as from healthy plants. Different bandwidths of wavelengths are analyzed in order to identify the most relevant spectral bands.

To cope with the nominally high number of input dimensions of the data, functional expansion of the spectra is considered. The outlined classification task is addressed using Generalized Matrix Relevance Learning Vector Quantization (GMLVQ) performed in the space of expansion coefficients.