A novel deep learning method for detection and classification of plant diseases

Abstract

The agricultural production rate plays a pivotal role in the economic development of a country. However, plant diseases are the most significant impediment to the production and quality of food. The identification of plant diseases at an early stage is crucial for global health and wellbeing. The traditional diagnosis process involves visual assessment of an individual plant by a pathologist through on-site visits. However, manual examination for crop diseases is restricted because of less accuracy and the small accessibility of human resources. To tackle such issues, there is a demand to design automated approaches capable of efficiently detecting and categorizing numerous plant diseases. Precise identification and classification of plant diseases is a tedious job due because of the occurrence of low-intensity information in the image background and foreground, the huge color resemblance in the healthy and diseased plant areas, the occurrence of noise in the samples, and changes in the position, chrominance, structure, and size of plant leaves. To tackle the above-mentioned problems, we have introduced a robust plant disease classification system by introducing a Custom CenterNet framework with DenseNet-77 as a base network. The presented method follows three steps. In the first step, annotations are developed to get the region of interest. Secondly, an improved CenterNet is introduced in which DenseNet-77 is proposed for deep keypoints extraction. Finally, the one-stage detector CenterNet is used to detect and categorize several plant diseases. To conduct the performance analysis, we have used the PlantVillage Kaggle database, which is the standard dataset for plant diseases and challenges in terms of intensity variations, color changes, and differences found in the shapes and sizes of leaves. Both the qualitative and quantitative analysis confirms that the presented method is more proficient and reliable to identify and classify plant diseases than other latest approaches.

Detecting Asymptomatic Infections of Rice Bacterial Leaf Blight Using Hyperspectral Imaging and 3-Dimensional Convolutional Neural Network With Spectral Dilated Convolution

“…Where R f represents the receptive field of a single convolution kernel; r SDR represents the spectral dilation ratio; k represents the size of convolution kernels. Here k was set to 3 ( Mohanty et al, 2016 ; Albattah et al, 2022 ).…”

AI-CenterNet CXR: An artificial intelligence (AI) enabled system for localization and classification of chest X-ray disease

“…While for the one-stage object detection methods, the position and class of RoI are determined in a single step. In the case of two-stage approaches, we have chosen the Fast-RCNN ( 53 ), Faster-RCNN ( 4 , 54 ), and Mask-RCNN ( 55 ) models, while for the other, we have taken the RetinaNet ( 56 ) and conventional CenterNet ( 21 ) models.…”

“…The CNN models are inspired by the working of human brains to visualize and recall several objects. The well-known CNN models i.e., VGG ( 19 ), ResNet ( 20 ), DenseNet ( 21 ), and EfficientNet ( 22 ) are highly used for several image classification tasks. Such methods can exhibit reliable performance with minimum processing time ( 23 – 25 ).…”

Artificial Intelligence-Based Drone System for Multiclass Plant Disease Detection Using an Improved Efficient Convolutional Neural Network

“…To evaluate the plant disease detection and classification performance of our approach, we have employed the PlantVillage database ( Albattah et al, 2022 ). The PlantVillage dataset is a large and online accessible standard database of crop leaf disease classification, which is extensively explored by several techniques from the past for performance assessment.…”