Automatic plant disease diagnosis using mobile capture devices, applied on a wheat use case

Abstract

Automatic Plant disease diagnosis for early disease symptoms.Novel image processing algorithm in combination with machine learning inference methods.A performance testing on wheat was done with 7 mobile devices over 3 seasons.Obtained results reveal AuC metrics higher than 0.80 for all the analyzed diseases. Disease diagnosis based on the detection of early symptoms is a usual threshold taken into account for integrated pest management strategies. Early phytosanitary treatment minimizes yield losses and increases the efficacy and efficiency of the treatments. However, the appearance of new diseases associated to new resistant crop variants complicates their early identification delaying the application of the appropriate corrective actions. The use of image based automated identification systems can leverage early detection of diseases among farmers and technicians but they perform poorly under real field conditions using mobile devices. A novel image processing algorithm based on candidate hot-spot detection in combination with statistical inference methods is proposed to tackle disease identification in wild conditions. This work analyses the performance of early identification of three European endemic wheat diseases septoria, rust and tan spot. The analysis was done using 7 mobile devices and more than 3500 images captured in two pilot sites in Spain and Germany during 2014, 2015 and 2016. Obtained results reveal AuC (Area under the Receiver Operating CharacteristicROCCurve) metrics higher than 0.80 for all the analyzed diseases on the pilot tests under real conditions.