DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection

Abstract

In response to the difficulty of plant leaf disease detection and classification, this study proposes a novel plant leaf disease detection method called deep block attention SSD (DBA_SSD) for disease identification and disease degree classification of plant leaves. We propose three plant leaf detection methods, namely, squeeze-and-excitation SSD (Se_SSD), deep block SSD (DB_SSD), and DBA_SSD. Se_SSD fuses SSD feature extraction network and attention mechanism channel, DB_SSD improves VGG feature extraction network, and DBA_SSD fuses the improved VGG network and channel attention mechanism. To reduce the training time and accelerate the training process, the convolutional layers trained in the Image Net image dataset by the VGG model are migrated to this model, whereas the collected plant leaves disease image dataset is randomly divided into training set, validation set, and test set in the ratio of 8:1:1. We chose the PlantVillage dataset after careful consideration because it contains images related to the domain of interest. This dataset consists of images of 14 plants, including images of apples, tomatoes, strawberries, peppers, and potatoes, as well as the leaves of other plants. In addition, data enhancement methods, such as histogram equalization and horizontal flip were used to expand the image data. The performance of the three improved algorithms is compared and analyzed in the same environment and with the classical target detection algorithms YOLOv4, YOLOv3, Faster RCNN, and YOLOv4 tiny. Experiments show that DBA_SSD outperforms the two other improved algorithms, and its performance in comparative analysis is superior to other target detection algorithms.

Plant Disease Detection and Classification: A Systematic Literature Review

“…Abbas et al [ 28 ] acquired diseased and healthy tomato leaf images from the open-source PlantVillage dataset. Wang et al [ 53 ] acquired 3000 leaf images of various species, both healthy and disease-affected, that were gathered from the PlantVillage dataset. Divakar et al [ 29 ] acquired image data that contained images of both diseased and healthy apple leaves, which were downloaded from a publicly accessible dataset on Kaggle.…”

“…Bedi et al [ 73 ] employed the concept of early halting, and the patience value was set to 5 to prevent model overfitting. Wang et al [ 53 ] utilized 1 × 1 convolution to decrease overfitting. Chen et al [ 71 ] utilized forward propagation in order to avoid overfitting.…”

A Systematic Literature Review on Plant Disease Detection: Motivations, Classification Techniques, Datasets, Challenges, and Future Trends

“…Using the apple disease dataset, a CNN model for the apple disease localization was proposed and demonstrated a score of 83.12% mAP for the five-class [65]. Using an improved localization SSD method for the plant disease was proposed, and their model presented 92.2% mAP using PVD [112].…”

PDD-Net: Plant Disease Diagnoses Using Multilevel and Multiscale Convolutional Neural Network Features

“…Recently, with the advent of domain-specific architectures [18] (i.e., GPU, TPU, etc. ), deep learning (DL)-based classifiers, particularly CNN, are becoming increasingly popular [19][20][21][22][23][24][25][26][27][28][29][30][31][32][33]. A CNN-based classifier (i.e., VGG-Net [34], ImageNet [35], Inception-Net [36], DenseNet-121 [37], MobileNet [38], ResNet50 [39], etc.)…”