A plant disease classification using one-shot learning technique with field images

Abstract

Abstract  Early diagnosis of plant diseases is crucial for preventing plagues and mitigating their effects on crops. The most precise automatic methods for identifying plant diseases using images of plant fields are powered by deep learning. Big image datasets should always be gathered and annotated for these methods to work, which is often not technically or financially feasible. This paper offers one-shot learning (OSL) techniques for plant disease classification with limited datasets utilizing Siamese Neural Network (SNN). There are five different crop kinds in the dataset: grape, wheat, cotton, cucumber, and corn. Five sets of images showing both healthy and diseased crops are used to represent each of the new crops. The dataset's includes 25 classes with 875 leaf images. Data augmentation techniques are used to enhance the size and dimension of the plant leaf disease image dataset. To provide effective segmentation, this paper provides a unique method for region-based image segmentation that divides an image into its most prominent regions. It also addresses issues with earlier region-based segmentation methods. SVM-based classifiers have better generalization properties as their efficiency does not depend on the number of features. Such merit is beneficial in primary diagnostics decisions to check if the input image is included in the database or not to reduce the consumed time. OSL was applied and compared to standard fine-tuning transfer learning utilizing Siamese networks and triplet loss. Siamese provides superior classification accuracy and localization accuracy with minimal errors than other approaches. The proposed approach has a total processing time of 5 ms, which makes it appropriate for real-time applications. In terms of specificity, sensitivity, precision, accuracy, MCC, and F-measure, the proposed approach beats all current machine learning algorithms for small training sets.