Crop disease monitoring and recognizing system by soft computing and image processing models

Zhang, Shanwen; Huang, Wenzhun; Wang, Haoxiang

doi:10.1007/s11042-020-09577-z

Cited by 18 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, time constraints and other commitments are considered. Convolutional networks (CNNs), occupying state of the art for various tasks in computer vision, have proven to be successful for a wide range of applications, including image classification [ 14 , 18 ], image segmentation, the alignment of images [ 16 ], the detection of facial points [ 4 ], the estimation of human postures [ 21 ], and the detection of lines on roads [ 11 , 12 ], among other tasks. Currently, it is in the field of medicine that a great trend has been seen in the use of CNN to automate the process of detecting and diagnosing diseases [ 6 , 17 , 7 , 5 ].…”

Section: Introductionmentioning

confidence: 99%

Automation of Cephalometrics Using Machine Learning Methods

Alshamrani

Alqahtani

Alshehri

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Cephalometry is a medical test that can detect teeth, skeleton, or appearance problems. In this scenario, the patient’s lateral radiograph of the face was utilised to construct a tracing from the tracing of lines on the lateral radiograph of the face of the soft and hard structures (skin and bone, respectively). Certain cephalometric locations and characteristic lines and angles are indicated after the tracing is completed to do the real examination. In this unique study, it is proposed that machine learning models be employed to create cephalometry. These models can recognise cephalometric locations in X-ray images, allowing the study’s computing procedure to be completed faster. To correlate a probability map with an input image, they combine an Autoencoder architecture with convolutional neural networks and Inception layers. These innovative architectures were demonstrated. When many models were compared, it was observed that they all performed admirably in this task.

show abstract

Section: Introductionmentioning

confidence: 99%

Automation of Cephalometrics Using Machine Learning Methods

Alshamrani

Alqahtani

Alshehri

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…proposed a method based on Ensemble Particle Swarm Optimization, which achieved 96% classification accuracy after 10-fold cross-validation in a recognition classification task for 12 vegetables. Zhang et al (Zhang et al, 2020b) segmented diseased leaf images using the K-mean clustering algorithm, which extracts the feature vectors of the difference histogram from each segmented defect image based on the intensity values of adjacent pixels and achieves a parity accuracy of 94.4% for the identification of five diseases of cucumber. Li et al (Li et al, 2020b) proposed shallow CNN with kernel support vector machine and shallow CNN with random forest to discriminate plant diseases, respectively.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Dual-branch collaborative learning network for crop disease identification

et al. 2023

View full text Add to dashboard Cite

Crop diseases seriously affect the quality, yield, and food security of crops. redBesides, traditional manual monitoring methods can no longer meet intelligent agriculture’s efficiency and accuracy requirements. Recently, deep learning methods have been rapidly developed in computer vision. To cope with these issues, we propose a dual-branch collaborative learning network for crop disease identification, called DBCLNet. Concretely, we propose a dual-branch collaborative module using convolutional kernels of different scales to extract global and local features of images, which can effectively utilize both global and local features. Meanwhile, we embed a channel attention mechanism in each branch module to refine the global and local features. Whereafter, we cascade multiple dual-branch collaborative modules to design a feature cascade module, which further learns features at more abstract levels via the multi-layer cascade design strategy. Extensive experiments on the Plant Village dataset demonstrated the best classification performance of our DBCLNet method compared to the state-of-the-art methods for the identification of 38 categories of crop diseases. Besides, the Accuracy, Precision, Recall, and F-score of our DBCLNet for the identification of 38 categories of crop diseases are 99.89%, 99.97%, 99.67%, and 99.79%, respectively. 811

show abstract

“…Then, texture and shape features are extracted by statistical methods, such as GLCM (Fulari et al, 2020 ; Jan and Ahmad, 2020 ) and KPCA. Finally, machine learning-based models, such as the Support Vector Machine (SVM), random forests, and decision trees (Zhang et al, 2020 ), are used as classifiers to identify crop leaf diseases. However, such methods are time-consuming and are unable to cope with complex image features, which result in unsatisfactory efficiency and accuracy.…”

Section: Related Workmentioning

confidence: 99%

MGA-YOLO: A lightweight one-stage network for apple leaf disease detection

Wang

Zhao

2022

Front. Plant Sci.

View full text Add to dashboard Cite

Apple leaf diseases seriously damage the yield and quality of apples. Current apple leaf disease diagnosis methods primarily rely on human visual inspection, which often results in low efficiency and insufficient accuracy. Many computer vision algorithms have been proposed to diagnose apple leaf diseases, but most of them are designed to run on high-performance GPUs. This potentially limits their application in the field, in which mobile devices are expected to be used to perform computer vision-based disease diagnosis on the spot. In this paper, we propose a lightweight one-stage network, called the Mobile Ghost Attention YOLO network (MGA-YOLO), which enables real-time diagnosis of apple leaf diseases on mobile devices. We also built a dataset, called the Apple Leaf Disease Object Detection dataset (ALDOD), that contains 8,838 images of healthy and infected apple leaves with complex backgrounds, collected from existing public datasets. In our proposed model, we replaced the ordinary convolution with the Ghost module to significantly reduce the number of parameters and floating point operations (FLOPs) due to cheap operations of the Ghost module. We then constructed the Mobile Inverted Residual Bottleneck Convolution and integrated the Convolutional Block Attention Module (CBAM) into the YOLO network to improve its performance on feature extraction. Finally, an extra prediction head was added to detect extra large objects. We tested our method on the ALDOD testing set. Results showed that our method outperformed other state-of-the-art methods with the highest mAP of 89.3%, the smallest model size of only 10.34 MB and the highest frames per second (FPS) of 84.1 on the GPU server. The proposed model was also tested on a mobile phone, which achieved 12.5 FPS. In addition, by applying image augmentation techniques on the dataset, mAP of our method was further improved to 94.0%. These results suggest that our model can accurately and efficiently detect apple leaf diseases and can be used for real-time detection of apple leaf diseases on mobile devices.

show abstract

Crop disease monitoring and recognizing system by soft computing and image processing models

Cited by 18 publications

References 16 publications

Automation of Cephalometrics Using Machine Learning Methods

Automation of Cephalometrics Using Machine Learning Methods

Dual-branch collaborative learning network for crop disease identification

MGA-YOLO: A lightweight one-stage network for apple leaf disease detection

Contact Info

Product

Resources

About