Cassava Spectral and Image Dataset
Owomugisha Godliver; Joyce, Nakatumba-Nabende; Ephraim Nuwamanya; Dalton Kanyesigye; Nicholas Muhumuza; Maurice Katusiime; Joshua Jeremy Dhikusooka; Tobius Saolo; Bamundaga Aloyzius; Joan Nabadda; Nakalyango Molly; Nahima Musa
About the Dataset
We present a spectral dataset, procedures and steps we adopted to collect disease data in a controlled environment aiming at early disease detection in cassava. As a baseline, we extended these procedures to an open field experiment and both dataset are provided. Crop disease diagnosis has been done in the past using plant image data taken with a smartphone camera. However for this method disease symptoms need to be visible. Unfortunately for some cassava diseases, once symptoms have manifested on the aerial part of the plant, the root which is the edible part of the plant has been totally destroyed. This approach is premised on the hypothesis that diseased crops without visible symptoms can be detected using spectral information, allowing for early interventions. We collected visible and near-infrared spectra captured from leaves infected with two common cassava diseases. Together we collected plant image data from leaves where spectral data was captured. In this experiment, biochemical data was collected and is taken as the ground truth. Finally, agricultural experts provided a disease score for each plant where data was collected. The process of disease monitoring and data collection took 19 and 15 consecutive weeks for screenhouse and open field respectively until disease symptoms were visibly seen by the human eye.