I-LDD: an interpretable leaf disease detector.

A rapid expansion in the world's population needs an enormous supply of food grains to satisfy agricultural needs. Unfortunately, crop diseases adversely impact food production and disrupt the supply chain. To circumvent the limitations of continuous human monitoring, machine learning techniques can automatically diagnose leaf diseases in their early stages based on image data. In this paper, an Interpretable Leaf Disease Detector (I-LDD) framework for image-based leaf disease detection using Extreme Learning Machine (ELM) is proposed. The choice of ELM for this work has been motivated by its quicker convergence, good generalization capability, and shorter learning time compared to the standard gradient-based learning algorithms. Experiments have been carried out using a publicly available PlantVillage dataset comprising healthy and diseased leaf images for 32 categories. In the first phase, the leaf images are preprocessed and segmented using the k-means clustering algorithm. In the second phase, textural and frequency-based features are extracted from the segmented images. In the third phase, several machine learning classifiers are trained using tenfold cross-validation. It is observed that I-LDD achieves an accuracy of 0.9322 ± 0.0088 at a 95% confidence level, outperforming the state-of-the-art methods. Moreover, a statistical significance test on the classification performance metrics also revealed the superiority of I-LDD over the state-of-the-art classifiers. Further, Local Interpretable Model-agnostic Explanations (LIME) is used to obtain the top 10 superpixels that contributed most to the class predicted by I-LDD. [ABSTRACT FROM AUTHOR]