Improved contourlet-based steganalysis using binary particle swarm optimization and radial basis neural networks

Sheikhan, Mansour; Pezhmanpour, Mansoureh; Moin, Mohammad Shahram

doi:10.1007/s00521-011-0729-9

Cited by 40 publications

(7 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally speaking, plant leaves are primary information for the recognition of crop diseases because most of the symptoms of diseases first appear on leaves. In the past few decades, the recognition and classification of major diseases have been widely used in plants, including K-Nearest Neighbor (KNN) [5], Support Vector Machine (SVM) [6], Fisher Linear Discriminant (FLD) [7], Artificial Neural Network (ANN) [8], Random Forest (RF) [9], etc. The disease recognition rate of classical methods largely depends on the lesion segmentation of various algorithms and hand-crafted features, such as seven invariant moments, scale-invariant feature transform (SIFT), Gabor transform, global-local singular values and sparse representation [10][11][12].…”

Section: Traditional Image Processing Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Residual Self-Calibration and Self-Attention Aggregation Network for Crop Disease Recognition

Zhang

Sun

Cheng

et al. 2021

IJERPH

View full text Add to dashboard Cite

The correct diagnosis and recognition of crop diseases play an important role in ensuring crop yields and preventing food safety. The existing methods for crop disease recognition mainly focus on accuracy while ignoring the algorithm’s robustness. In practice, the acquired images are often accompanied by various noises. These noises lead to a huge challenge for improving the robustness and accuracy of the recognition algorithm. In order to solve this problem, this paper proposes a residual self-calibration and self-attention aggregation network (RCAA-Net) for crop disease recognition in actual scenarios. The proposed RCAA-Net is composed of three main modules: (1) multi-scale residual module, (2) feedback self-calibration module, and (3) self-attention aggregation module. Specifically, the multi-scale residual module is designed to learn multi-scale features and provide both global and local information for the appearance of the disease to improve the performance of the model. The feedback self-calibration is proposed to improve the robustness of the model by suppressing the background noise in the original deep features. The self-attention aggregation module is introduced to further improve the robustness and accuracy of the model by capturing multi-scale information in different semantic spaces. The experimental results on the challenging 2018ai_challenger crop disease recognition dataset show that the proposed RCAA-Net achieves state-of-the-art performance on robustness and accuracy for crop disease recognition in actual scenarios.

show abstract

Section: Traditional Image Processing Methodsmentioning

confidence: 99%

“…Generally, after 50 iterations of training, RCAA-Net can output satisfactory accuracy. In this paper, the Adam optimization algorithm is used to optimize the loss function of Equation (8), and the initial learning rate is 3 × 10 −3 . The batch size is set to 128.…”

Section: Implementation Detailsmentioning

confidence: 99%

Residual Self-Calibration and Self-Attention Aggregation Network for Crop Disease Recognition

Zhang

Sun

Cheng

et al. 2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…After studying numerous published works in the domain of plant disease detection, a lot of interesting facts came to the fore. Before the evolution of Deep Learning, the popular classification approaches that were used for disease detection in plants include Random Forest (Simonyan & Zisserman, 2014), Artificial Neural Network (ANN) (Sheikhan et al, 2012), k-Nearest Neighbor (KNN) (Guettari et al, 2016), and Support Vector Machine (SVM) (Deepa & Umarani, 2017). However, these approaches were dependent on the extraction and selection of visible disease features.…”

Section: Previous Related Workmentioning

confidence: 99%

Agrijaanch

Das¹,

Singh²,

Gupta³

2022

Preprint

View full text Add to dashboard Cite

With the advancement in agricultural technology and the use of Artificial Intelligence in diagnosing plant diseases, it becomes important to make pertinent research for sustainable agricultural development. We have proposed and built a Webbased system to spread awareness amongst Farmers and Agro-companies about various diseases that plants are infected with and also their possible remedies. Different diseases have different causes and thus different solutions and mitigation strategies need to be adopted. If the diseases are misjudged or mismanaged, then they can get spread profusely and wreck havoc on the soil. So we came up with a potential approach for effective, efficient and automated detection of the prevalent diseases during the budding phase of the agricultural products to assist the farmers in employing preventive measure on time. We have developed a set of both Machine Learning Models and Deep Learning Models to detect diseases in the potato plant. The models are deployed on our website and when the image of a Potato plant is uploaded, the result that whether there is any disease in the plant or not will be generated. Amongst all models trained and tested in this work, Convolutional Neural Network yields the best classification accuracy of 99.30%.

show abstract

“…With the development of computer vision, machine learning techniques have been widely used in the agricultural field in recent years, and a series of approaches have been achieved in crop disease identification (Aravind et al, 2018 ; Kour and Arora, 2019 ; Mohammadpoor et al, 2020 ). In recent years, the main techniques, which are widely used in crop disease identification include artificial neural network (ANN) (Sheikhan et al, 2012 ), the K Nearest Neighbors (KNN) algorithm (Guettari et al, 2016 ), random forests (RF) (Kodovsky et al, 2012 ), and so on. For example, Wang et al ( 2019 ) proposed a method for identifying cucumber powdery mildew based on a visible spectrum by extracting the spectral features and training a Support Vector Machine (SVM) classifier to establish a classification model, optimizing the radial basis kernel function, and the recognition accuracy of the method reached 98.13%.…”

Section: Introductionmentioning

confidence: 99%

Identification of Apple Leaf Diseases by Improved Deep Convolutional Neural Networks With an Attention Mechanism

et al. 2021

View full text Add to dashboard Cite

The accurate identification of apple leaf diseases is of great significance for controlling the spread of diseases and ensuring the healthy and stable development of the apple industry. In order to improve detection accuracy and efficiency, a deep learning model, which is called the Coordination Attention EfficientNet (CA-ENet), is proposed to identify different apple diseases. First, a coordinate attention block is integrated into the EfficientNet-B4 network, which embedded the spatial location information of the feature by channel attention to ensure that the model can learn both the channel and spatial location information of important features. Then, a depth-wise separable convolution is applied to the convolution module to reduce the number of parameters, and the h-swish activation function is introduced to achieve the fast and easy to quantify the process. Afterward, 5,170 images are collected in the field environment at the apple planting base of the Northwest A&F University, while 3,000 images are acquired from the PlantVillage public data set. Also, image augmentation techniques are used to generate an Apple Leaf Disease Identification Data set (ALDID), which contains 81,700 images. The experimental results show that the accuracy of the CA-ENet is 98.92% on the ALDID, and the average F1-score reaches .988, which is better than those of common models such as the ResNet-152, DenseNet-264, and ResNeXt-101. The generated test dataset is used to test the anti-interference ability of the model. The results show that the proposed method can achieve competitive performance on the apple disease identification task.

show abstract

Improved contourlet-based steganalysis using binary particle swarm optimization and radial basis neural networks

Cited by 40 publications

References 59 publications

Residual Self-Calibration and Self-Attention Aggregation Network for Crop Disease Recognition

Residual Self-Calibration and Self-Attention Aggregation Network for Crop Disease Recognition

Agrijaanch

Identification of Apple Leaf Diseases by Improved Deep Convolutional Neural Networks With an Attention Mechanism

Contact Info

Product

Resources

About