A Transfer Learning-Based Framework: MobileNet-SVM for Efficient Tomato Leaf Disease Classification

Abstract

In the face of a burgeoning global population exceeding seven billion and dwindling agricultural land, plants remain pivotal for sustaining human civilization's food needs. However, plant health is threatened by various diseases, particularly leaf ailments like spots, bacterial infections, and black spots. These afflictions, predominantly caused by bacteria and fungi, jeopardize crop yields. Timely disease detection is imperative for safeguarding productivity. This study introduces a novel hybrid approach amalgamating MobileNet, a transfer learning-based model, with SVM (Support Vector Machine) hinge loss. Leveraging MobileNet's pre-trained capabilities, features are extracted and fed into an SVM classifier to discern nine distinct types of tomato leaf diseases and healthy leaves. Statistical analysis underscores the efficacy of this hybrid model, surpassing previous benchmarks. Notably, it achieves exceptional classification accuracy, precision, recall, and AUC values, culminating in an impressive overall accuracy of 99.37%.