Identification of tomato leaf diseases based on combination of ABCK-BWTR and B-ARNet

Chen, Xiao; Zhou, Guofu; Chen, Aibin; Yi, Jizheng; Zhang, Wenzhuo; Hu, Yahui

doi:10.1016/j.compag.2020.105730

Cited by 92 publications

(34 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method proposed in the study using four-class PlantVillage dataset achieved 98% success. Chen et al 11 proposed a new framework for classifying tomato leaves. Images were removed with retinex and binary wavelet transform noise and edge points, and leaves were separated from the background using KSW optimized with artificial bee colony.…”

Section: Related Workmentioning

confidence: 99%

Hybrid convolutional neural network based classification of bacterial, viral, and fungal diseases on tomato leaf images

Cengil

Çınar

2021

Concurrency and Computation

View full text Add to dashboard Cite

Tomatoes can get many diseases at every stage of the cultivation process depending on environmental and climatic factors. Tomato growers sometimes struggle to monitor leaves in order to detect these diseases. As a result, deep learning-based systems for detecting diseases have been developed. It has demonstrated its worth by solving problems in a variety of fields, including classification. Convolutional neural network (CNN) is particularly effective in image classification, recognition, and detection. In this article, a hybrid-based CNN model for the classification of diseases on tomato leaf images is proposed. The performance of the method has been examined by the tomato leaf disease detection dataset and Taiwan datasets. For the extraction of features, well-known CNN architectures such as AlexNet, ResNet50, and VGG16 are used at first. The feature transfer method extracts features from the last fully connected layers of the architectures. After that, the minimum redundancy maximum relevance feature selection algorithm is applied to these features for optimization. The features gathered are concatenated. Concatenating features are classified by popular machine learning classification algorithms. With the proposed method, the highest performance values for the tomato leaf disease detection and Taiwan dataset show an accuracy of 98.3% and 96.3%, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Hybrid convolutional neural network based classification of bacterial, viral, and fungal diseases on tomato leaf images

Cengil

Çınar

2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Our previous work has achieved good results on the detection of a common gray leaf spot disease of tomato under natural conditions [ 37 ]. Chen et al [ 38 ] collected 8616 images containing five kinds of tomato diseases on the spot. The images were denoised and enhanced by combining the binary wavelet transform of Retinex (BWTR).…”

Section: Introductionmentioning

confidence: 99%

Early real-time detection algorithm of tomato diseases and pests in the natural environment

Wang

Zhu³

2021

Plant Methods

View full text Add to dashboard Cite

Background Research on early object detection methods of crop diseases and pests in the natural environment has been an important research direction in the fields of computer vision, complex image processing and machine learning. Because of the complexity of the early images of tomato diseases and pests in the natural environment, the traditional methods can not achieve real-time and accurate detection. Results Aiming at the complex background of early period of tomato diseases and pests image objects in the natural environment, an improved object detection algorithm based on YOLOv3 for early real-time detection of tomato diseases and pests was proposed. Firstly, aiming at the complex background of tomato diseases and pests images under natural conditions, dilated convolution layer is used to replace convolution layer in backbone network to maintain high resolution and receptive field and improve the ability of small object detection. Secondly, in the detection network, according to the size of candidate box intersection ratio (IOU) and linear attenuation confidence score predicted by multiple grids, the obscured objects of tomato diseases and pests are retained, and the detection problem of mutual obscure objects of tomato diseases and pests is solved. Thirdly, to reduce the model volume and reduce the model parameters, the network is lightweight by using the idea of convolution factorization. Finally, by introducing a balance factor, the small object weight in the loss function is optimized. The test results of nine common tomato diseases and pests under six different background conditions are statistically analyzed. The proposed method has a F1 value of 94.77%, an AP value of 91.81%, a false detection rate of only 2.1%, and a detection time of only 55 Ms. The test results show that the method is suitable for early detection of tomato diseases and pests using large-scale video images collected by the agricultural Internet of Things. Conclusions At present, most of the object detection of diseases and pests based on computer vision needs to be carried out in a specific environment (such as picking the leaves of diseases and pests and placing them in the environment with light supplement equipment, so as to achieve the best environment). For the images taken by the Internet of things monitoring camera in the field, due to various factors such as light intensity, weather change, etc., the images are very different, the existing methods cannot work reliably. The proposed method has been applied to the actual tomato production scenarios, showing good detection performance. The experimental results show that the method in this study improves the detection effect of small objects and leaves occlusion, and the recognition effect under different background conditions is better than the existing object detection algorithms. The results show that the method is feasible to detect tomato diseases and pests in the natural environment.

show abstract

“…In this method, the farmers use their extensive experience to make a rough identification of the disease. However, it is notable that this approach not only requires a lot of manual labor but is also susceptible to the subjective factors (Chen et al, 2020 ). In order to ensure the grape production and economic well-being of the farmers, rapid and effective detection of black rot on grape leaves is important for the farming industry.…”

Section: Introductionmentioning

confidence: 99%

Grape Leaf Black Rot Detection Based on Super-Resolution Image Enhancement and Deep Learning

et al. 2021

View full text Add to dashboard Cite

The disease spots on the grape leaves can be detected by using the image processing and deep learning methods. However, the accuracy and efficiency of the detection are still the challenges. The convolutional substrate information is fuzzy, and the detection results are not satisfactory if the disease spot is relatively small. In particular, the detection will be difficult if the number of pixels of the spot is <32 × 32 in the image. In order to effectively address this problem, we present a super-resolution image enhancement and convolutional neural network-based algorithm for the detection of black rot on grape leaves. First, the original image is up-sampled and enhanced with local details using the bilinear interpolation. As a result, the number of pixels in the image increase. Then, the enhanced images are fed into the proposed YOLOv3-SPP network for detection. In the proposed network, the IOU (Intersection Over Union, IOU) in the original YOLOv3 network is replaced with GIOU (Generalized Intersection Over Union, GIOU). In addition, we also add the SPP (Spatial Pyramid Pooling, SPP) module to improve the detection performance of the network. Finally, the official pre-trained weights of YOLOv3 are used for fast convergence. The test set test_pv from the Plant Village and the test set test_orchard from the orchard field were used to evaluate the network performance. The results of test_pv show that the grape leaf black rot is detected by the YOLOv3-SPP with 95.79% detection accuracy and 94.52% detector recall, which is a 5.94% greater in terms of accuracy and 10.67% greater in terms of recall as compared to the original YOLOv3. The results of test_orchard show that the method proposed in this paper can be applied in field environment with 86.69% detection precision and 82.27% detector recall, and the accuracy and recall were improved to 94.05 and 93.26% if the images with the simple background. Therefore, the detection method proposed in this work effectively solves the detection task of small targets and improves the detection effectiveness of the grape leaf black rot.

show abstract

Identification of tomato leaf diseases based on combination of ABCK-BWTR and B-ARNet

Cited by 92 publications

References 4 publications

Hybrid convolutional neural network based classification of bacterial, viral, and fungal diseases on tomato leaf images

Hybrid convolutional neural network based classification of bacterial, viral, and fungal diseases on tomato leaf images

Early real-time detection algorithm of tomato diseases and pests in the natural environment

Grape Leaf Black Rot Detection Based on Super-Resolution Image Enhancement and Deep Learning

Contact Info

Product

Resources

About