An Algorithm for Plant Disease Visual Symptom Detection in Digital Images Based on Superpixels

Abstract

Quantifying diseased areas in plant leaves is an important procedure in agriculture, as it contributes to crop monitoring and decision-making for crop protection. It is, however, a time-consuming and very subjective manual procedure whose automation is, therefore, highly expected. This work proposes a new method for the automatic segmentation of diseased leaf areas. The method used the Simple Linear Iterative Clustering (SLIC) algorithm to group similar-color pixels together into regions called superpixels. The color features of superpixel clusters were used to train artificial neural networks (ANNs) for the classification of superpixels as healthy or not healthy. These network parameters were heuristically tuned by choosing the network with the best classification performance to obtain the automatic segmentation of the diseased areas. The performance of the classifier was measured by comparing its automatic segmentations with those manually made from a database with public and private images divided into nine groups by visual symptom and plant. The mean error of the area obtained was always below 11%, and the average F-score was 0.67, which is higher than that found by the other two approaches reported in the literature (0.57 and 0.58) and used here for comparison.

Evolutionary Feature Optimization for Plant Leaf Disease Detection by Deep Neural Networks

“…The developed approach seems an efficient tool to detect the disease using the Spectral Disease Index (SDI). Salazar-Reque et al [12] have proposed a novel crop protection method in the agriculture industry. It is, however, a time-consuming and very subjective procedure, which automation is therefore highly anticipated.…”

“…To achieve only the desired features from the whole leaf image, we will apply SURF as a feature extraction technique on the ROI of leaf image [12]. This technique extracts only those parts of the leaf, which is affected by the disease.…”

Enhanced disease detection in plant leaves using segmentation and feature extraction techniques

“…In [7], the authors demonstrated a framework for classifying images of using gradient-based features. In another work [8], Simple Iterative Linear Clustering Algorithm (SLIC) method is used group the color features (super pixels) which in turn are used to train the ANN to classify whether the super pixels that are neither healthy nor healthy. In [9], the authors recommended better method for diagnosing apple leaf diseases using Deep Neural Network (DNN).…”

Detection of Fusarium Head Blight in Wheat Using a Deep Neural Network and Color Imaging

“…Alternatively, color imaging is inexpensive and is easy to handle. Color imaging can capture the color and texture information of an object, and has been implemented to detect and assess plant diseases [18][19][20]. For Fusarium or FHB detection, researchers have explored the usefulness of color imaging.…”