A Hybrid Residual Wide-Kernel Auto-Encoder With Vision Transformer for Plant Disease Detection

Abstract

Plant disease diagnosis is an important aspect of managing and producing crops. Recent developments in deep-learning models provide robust performance in detecting plant disease with improved accuracy. Several methods have been devised to detect plant disease, but inaccurate disease detection and computational complexity still limit the performance. Hence, this work proposes a hybrid residual wide-kernel auto-encoder with a vision transformer (HRWKAE-VT) for Plant disease detection. The images are collected from the plant disease dataset, and pre-processing is employed based on resizing and augmentation. Then, the dimension of the leaf images is decreased by using the proposed residual wide-kernel convolutional auto-encoder. Subsequently, the healthy and unhealthy leaves are categorised by the proposed Vision transformer-based deep-learning (VT-DL) model. The VT-DL model contains an alternating multiple-head self-attention layer and a multiple-layer perceptron (MLP) block for extracting local and global features. The performance of the proposed work is evaluated over the existing models in terms of accuracy, precision, recall, f-measure and prediction loss. The proposed model achieves 99.89% accuracy and a specificity of 98.72% on the plant disease dataset. It is observed that the performance of the proposed model improved over the conventional approaches with reduced loss of prediction.