Plant Disease Detection and Classification Method Based on the Optimized Lightweight YOLOv5 Model

Wang, Haiqing; Shang, Shuo; Wang, Dongwei; He, Xiaoning; Feng, Kai; Zhu, Hao

doi:10.3390/agriculture12070931

Cited by 57 publications

(34 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MobileNetv2-YOLOv3 is a lightweight leaf disease detection network employed by Liu and Wang (2020). The disease detection method of Wang et al (2022b) is an optimized lightweight YOLOv5 (OL-YOLOv5). EADD-YOLO is the efficient and accurate network for detecting apple leaf disease proposed in this study.…”

Section: Discussionmentioning

confidence: 99%

“…However, the large number of convolution and bottleneck modules in the neck network results in the model still having many parameters. Wang et al (2022b) introduced the BiFPN structure to alleviate the low detection accuracy of the modified YOLOv5 but inevitably raised computational costs, which led to higher complexity. Although these crop leaf disease detection methods have attempted to optimize the structure of the network to improve computational efficiency, they do not make efficient measures to cope with the reduction in precision, resulting in low detection performance or only a slight decrease in model complexity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

EADD-YOLO: An efficient and accurate disease detector for apple leaf using improved lightweight YOLOv5

Zhu

Ma²,

Wang³

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionCurrent detection methods for apple leaf diseases still suffer some challenges, such as the high number of parameters, low detection speed and poor detection performance for small dense spots, which limit the practical applications in agriculture. Therefore, an efficient and accurate model for apple leaf disease detection based on YOLOv5 is proposed and named EADD-YOLO.MethodsIn the EADD-YOLO, the lightweight shufflenet inverted residual module is utilized to reconstruct the backbone network, and an efficient feature learning module designed through depthwise convolution is proposed and introduced to the neck network. The aim is to reduce the number of parameters and floating point of operations (FLOPs) during feature extraction and feature fusion, thus increasing the operational efficiency of the network with less impact on detection performance. In addition, the coordinate attention module is embedded into the critical locations of the network to select the critical spot information and suppress useless information, which is to enhance the detection accuracy of diseases with various sizes from different scenes. Furthermore, the SIoU loss replaces CIoU loss as the bounding box regression loss function to improve the accuracy of prediction box localization.ResultsThe experimental results indicate that the proposed method can achieve the detection performance of 95.5% on the mean average precision and a speed of 625 frames per second (FPS) on the apple leaf disease dataset (ALDD). Compared to the latest research method on the ALDD, the detection accuracy and speed of the proposed method were improved by 12.3% and 596 FPS, respectively. In addition, the parameter quantity and FLOPs of the proposed method were much less than other relevant popular algorithms.DiscussionIn summary, the proposed method not only has a satisfactory detection effect, but also has fewer parameters and high calculation efficiency compared with the existing approaches. Therefore, the proposed method provides a high-performance solution for the early diagnosis of apple leaf disease and can be applied in agricultural robots. The code repository is open-sourced at https://github.com/AWANWY/EADD-YOLO.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

EADD-YOLO: An efficient and accurate disease detector for apple leaf using improved lightweight YOLOv5

Zhu

Ma²,

Wang³

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…However, the study provides no details regarding the number of the samples in the dataset. Another study published in [33], reported an accuracy of 92.57% using YOLOv5 model for classifying 61 categories of plant diseases that hit ten different plant species. The dataset consisted of 36,258 images.…”

Section: A Related Workmentioning

confidence: 99%

A Machine Learning Hybrid Approach for Diagnosing Plants Bacterial and Fungal Diseases

BaniMustafa¹,

Qattous²,

Ghabeish³

et al. 2023

IJACSA

View full text Add to dashboard Cite

Bacterial and Fungal diseases may affect the yield of stone fruit and cause damage to the Chlorophyll synthesis process, which is crucial for tree growth and fruiting. However, due to their similar visual shot-hole symptoms, novice agriculturalists and ordinary farmers usually cannot identify and differentiate these two diseases. This work investigates and evaluates the use of machine learning for diagnosing these two diseases. It aims at paving the way toward creating a generic deep learning-based model that can be embedded in a mobile phone application or in a web service to provide a fast, reliable, and cheap diagnosis for plant diseases which help reduce the excessive, unnecessary, or improper use of pesticides, which can harm public health and the environment. The dataset consists of hundreds of samples collected from stone fruit farms in the north of Jordan under normal field conditions. The image features were extracted using a CNN algorithm that was pre-trained with millions of images, and the diseases were identified using three machine learning classification algorithms: (1) K-nearest neighbour (KNN); (2) Stochastic Gradient Descent (SGD); and (3) Random Forests (RF). The resulting models were evaluated using 10-fold crossvalidation, with CNN-KNN achieving the best AUC performance with a score of 98.5%. On the other hand, the CNN-SGD model performed best in Classification Accuracy (CA) with a score of 93.7%. The results shown in the Confusion Matrix, ROC, Lift, and Calibration curves also confirmed the validity and robustness of the constructed models.

show abstract

“…7 of YOLOv5 models. There are mainly three parts in the YOLOv5 object detecting models Backbone, Neck, and Head [23] which are already mentioned in Fig. 9 of the YOLOv5 architecture diagram.…”

Section: Object Detection Algorithms Yolov5mentioning

confidence: 99%

Comprehensive Analysis of CNN and YOLOv5 Object Detection Model to Classify Phytomedicine Tree’s Leaf Disease

Islam

Haque

Rahaman

et al. 2022

Preprint

View full text Add to dashboard Cite

Phytomedicine is not only known to the poor people of East Bengal and West Bengal as a medicine but also as a beacon of hope for survival in a diseased life. In this approach, Terminalia Arjuna, Lawsonia inermis, Azadirachta indica, and Ocimum tenuiflorum Phytomedicine tree datasets. Terminalia Arjuna mainly protects gastric mucosa from oxidative damage and it makes it strong so that the stomach gets protection against ulcers. It also exhibits strong antibacterial and antimicrobial properties which help to fight against stomach infections like gastric, diarrhea, and dysentery. There are various uses of Lawsonia inermis. It is known as a powerful detoxifier and it helps to prefer healthy gum, and healthy hair and reduces arthritis pain. The flower of Lawsonia inermis can be used for headaches due to the heat of the sun. Neem is known as Phytomedicine for all diseases and the most common diseases are treated with acne, nourishing the skin, treating wounds, use to reduce dandruff and joint pain, etc. Mainly it increases immunity and provides a healthy life. Another famous Phytomedicine known as Ocimum tenuiflorum is used to treat kidney stones, alleviate fever and headaches, provide a healthy heart, healthy eye, healthy oral, and fight against acne, etc. It is also known as a big source of vitamin K. The most famous and fast object detection algorithms as YOLOv5 and Keras pre-trained models as Xception, ResNet152V2, VGG19, and InceptionResNetV2 have been developed to predict disease-affected or disease-free leaves. The implemented approach has gained a height accuracy of 97.00% from Xception and 95% accuracy from YOLOv5.

show abstract

Plant Disease Detection and Classification Method Based on the Optimized Lightweight YOLOv5 Model

Cited by 57 publications

References 49 publications

EADD-YOLO: An efficient and accurate disease detector for apple leaf using improved lightweight YOLOv5

EADD-YOLO: An efficient and accurate disease detector for apple leaf using improved lightweight YOLOv5

A Machine Learning Hybrid Approach for Diagnosing Plants Bacterial and Fungal Diseases

Comprehensive Analysis of CNN and YOLOv5 Object Detection Model to Classify Phytomedicine Tree’s Leaf Disease

Contact Info

Product

Resources

About