Accuracy of a Smartphone-Based Object Detection Model, PlantVillage Nuru, in Identifying the Foliar Symptoms of the Viral Diseases of Cassava–CMD and CBSD

Abstract

Nuru is a deep learning object detection model for diagnosing plant diseases and pests developed as a public good by PlantVillage (Penn State University), FAO, IITA, CIMMYT, and others. It provides a simple, inexpensive and robust means of conducting in-field diagnosis without requiring an internet connection. Diagnostic tools that do not require the internet are critical for rural settings, especially in Africa where internet penetration is very low. An investigation was conducted in East Africa to evaluate the effectiveness of Nuru as a diagnostic tool by comparing the ability of Nuru, cassava experts (researchers trained on cassava pests and diseases), agricultural extension officers and farmers to correctly identify symptoms of cassava mosaic disease (CMD), cassava brown streak disease (CBSD) and the damage caused by cassava green mites (CGM). The diagnosis capability of Nuru and that of the assessed individuals was determined by inspecting cassava plants and by using the cassava symptom recognition assessment tool (CaSRAT) to score images of cassava leaves, based on the symptoms present. Nuru could diagnose symptoms of cassava diseases at a higher accuracy (65% in 2020) than the agricultural extension agents (40–58%) and farmers (18–31%). Nuru’s accuracy in diagnosing cassava disease and pest symptoms, in the field, was enhanced significantly by increasing the number of leaves assessed to six leaves per plant (74–88%). Two weeks of Nuru practical use provided a slight increase in the diagnostic skill of extension workers, suggesting that a longer duration of field experience with Nuru might result in significant improvements. Overall, these findings suggest that Nuru can be an effective tool for in-field diagnosis of cassava diseases and has the potential to be a quick and cost-effective means of disseminating knowledge from researchers to agricultural extension agents and farmers, particularly on the identification of disease symptoms and their management practices.

Integration of dilated convolution with residual dense block network and multi‐level feature detection network for cassava plant leaf disease identification

“…Identifies disease and classifies the image under the specified category with the accuracy score of 93%. A deep learning based object detection model namely Nuru 28 is developed to diagnose the symptoms of the cassava plant diseases with great accuracy and the performance is compared with the experts, agricultural officers and farmers. The novel deep learning based method is proposed in which it integrates the deep residual convolutional neural network and distinct block processing 29 for classifying the cassava mosaic disease and it is analyzed with plain convolutional neural network by using various performance metrics.…”

Plant pest surveillance: from satellites to molecules

“…Conditions such as the quality and quantity of images used to train the model and the variation and complexity of the disease symptoms can influence the accuracy (sensitivity and specificity) of the diagnostic system [47]. In-field conditions, such as sunlight, wind and rain, can also affect the accuracy of the diagnosis system.…”

“…In-field conditions, such as sunlight, wind and rain, can also affect the accuracy of the diagnosis system. Mrisho et al [47] and Ramcharan et al [45] showed that the in-field accuracy of PlantVillage Nuru using one leaf (21-59%) was lower than the on-screen accuracy (43-81%). When the number of leaves inspected by PlantVillage Nuru was increased to six per plant, however, accuracy increased to 93% for cassava mosaic disease, 73% for cassava brown streak disease and 93% for cassava green mite [47].…”

“…There is limited information on the comparison of digital diagnostic apps to other diagnostic methods, however; the main alternative diagnostic method for plant diseases is through visual inspection of the plant either by farmers or agricultural extension officers. Using a standard set of 170 single cassava leaf images, Mrisho et al [47] showed that PlantVillage Nuru could diagnose symptoms of diseases at an accuracy (64%) higher than that of agricultural extension officers (50%) and cassava farmers (42%), suggesting that diagnostic apps such as this could offer a means to improve the diagnostic capability of users. Nevertheless, compared with other testing approaches, large amounts of data can be collected without significantly adding to the cost of surveillance.…”

A Deep Learning-based Mobile Application for Segmenting Tuta Absoluta’s Damage on Tomato Plants

“…In this work, the classification was based on Artificial Neural Networks (ANNs). In a recent study, researchers reported the performance of a deep learning object detection model for diagnosing plant diseases and pests [30]. The model was trained on 2756 images of cassava leaves exhibiting pest and disease symptoms.…”