Figure - uploaded by Weihui Zeng
Content may be subject to copyright.
Source publication
Fast1 and robust recognition of crop diseases is the basis for crop disease prevention and control. It is also an important guarantee for crop yield and quality. Most crop disease recognition methods focus on improving the recognition accuracy on public datasets, but ignoring the anti-interference ability of the methods, which result in poor recogn...
Contexts in source publication
Context 1
... on PlantVillage dataset [11]: Table 6-Table 8 show the experimental results of noise level vs. recognition accuracy on PlantVillage dataset. When adding Gaussian noise and hybrid noise (both Gaussian and Salt& Pepper noises), our approach achieves better performance than other methods. ...Context 2
... on PlantVillage dataset [11]: Table 6-Table 8 show the experimental results of noise level vs. recognition accuracy on PlantVillage dataset. When adding Gaussian noise and hybrid noise (both Gaussian and Salt& Pepper noises), our approach achieves better performance than other methods. ...Similar publications
Recently, deep learning methods are widely used in the rice diseases identification. However, the actual image background of rice disease is complex, the classification performance is not ideal. Therefore, this paper proposed a multi-scale feature extraction method based on stacked autoencoder, named the multi-scale stacked autoencoder (MSSAE), to...
Citations
... 18,160 images from the PlantVillage dataset, achieving 94.85% accuracy in just 30 iterations. Additionally, in [49], the high-order residual CNN (HOResNet) architecture was proposed to detect diseases in six categories with 10,478 PlantVillage images, reaching an accuracy of 91.79% after 100 iterations. Furthermore, in [50], SqueezeNet and AlexNet networks were tested on Nvidia Jetson Tx1 with PlantVillage images, where AlexNet achieved 95.65% accuracy. ...
Recognition of leaf diseases in agriculture is considered a significant aspect of ensuring food quantity, quality, and production. In general, crop leaves are susceptible and fragile to various diseases such as leaf mold, target spot, late blight, bacterial spot or early blight of tomato plants. However, these tomato plant diseases are challenging to recognize, and early diagnosis is vital. At the same time, the continuous growth of convolutional neural network (CNN) approaches has significantly assisted plant disease diagnosis, providing a robust mechanism with highly accurate results. On the other hand, the number of unhealthy leaf images collected is often unbalanced, and diagnosing diseases with such an unbalanced data set is complicated. So, numerous models for tomato disease diagnosis based on CNN models have been proposed. However, none overcomes the class imbalance problem and, as a result, does not generate findings with impartial accuracy. This article presents an efficient and robust solution for the heterogeneous PYNQ-Z1 board. Optimization techniques-including loop unrolling, pipelining, array partitioning, and loop flattening-enhance the computation speed across the network’s convolutional, fully connected, and max-pooling layers. The presented CNN approach comprises an 8-layer network termed MiniTomatoNet. This network is characterized by its streamlined structure, possessing only under 23 K parameters with all weights and biases and occupying a memory of 89.51 KB. In addition, the model trains with a re-weighted focal loss function and achieves 97.63% accuracy and 98.51% AUC score; the inference rate speed is 0.068 s per frame, and the power consumption is 2.35 W. Finally, the model is efficient, low power, robust, high accuracy and fast speed, making it a promising solution for diagnosing tomato diseases.
... The majority of crop disease identification techniques concentrate on enhancing the accuracy of recognition on datasets that are publicly accessible while neglecting the techniques anti-interference capability, which leads to subpar recognition accuracy when applied d to actual scenes. A high-order residual convolutional neural network (HOResNet) has been recommended in [8] for accurate and successful agricultural disease identification. To increase the anti-interferenceability, the HOResNet can simultaneously exploit high level characteristics with abstract models and low-level characteristics with object details. ...
Agriculture is an essential sector that plays a necessary role in the economic improvement of a country. Prediction of plant diseases at the earliest stage may result in better yield and sustainable for growing population. The conventional method necessitates highly skilled inspectors to identify the phenotypic expression of different diseases. Alternatively, biochemical technologies offer more precise means of obtaining crop disease information by analyzing susceptible rice. However, these methods are time-consuming, expensive, reliant on laboratories, and require skilled professionals, rendering them unaffordable for most farmers. The paper aims to propose a solution to prevent infection at the earliest stage for the benefit of farmers. A novel crop disease detection model deploying a deep convolutional generative adversarial network (DC-GAN) and with multidimensional feature compensation Residual Neural Network (MDFC-ResNet) and named as DC-GAN-MDFC–ResNet, which aims at fine grained disease identification system detects from three aspects, bacterial leaf blight, leaf streak and panicle blight. Initially the input data undergone preprocessing using the several processes like data improvement, data normalization, and Singular value decomposition (SVD) to reduce the negative influence that the data set has on the training of the model. When compared to traditional convolution models, the suggested DC-GAN-MDFC–ResNet architecture exhibits in terms of highest classification accuracy, Segmentation free methodology and training stability. The experiments done in this work using Plant Village dataset which show the proposed technique offering improved recognition with the rate of 95.99% accuracy and generating higher quality samples compared to other well-known deep learning models.
... Making your own dataset is a time-consuming and expensive process, but it is more in line with what happens in a real environment. A large number of studies have demonstrated that when models trained on controlled images are used to predict images collected from real-world environments, their accuracy is significantly reduced [56][57][58] . If a public dataset does not meet the needs of a particular study, self-made datasets must be produced. ...
... images with uniform backgrounds taken under controlled conditions and images with complex backgrounds taken in natural environments. CNN models are more generalized by using images taken in a natural environment for training compared to a uniform background [56][57][58] . At the same time, complex backgrounds in images can cause other negative problems. ...
In modern agricultural production, the severity of diseases is an important factor that directly affects the yield and quality of plants. In order to effectively monitor and control the entire production process of plants, not only the type of disease, but also the severity of the disease must be clarified. In recent years, deep learning for plant disease species identification has been widely used. In particular, the application of convolutional neural network (CNN) to plant disease images has made breakthrough progress. However, there are relatively few studies on disease severity assessment. The group first traced the prevailing views of existing disease researchers to provide criteria for grading the severity of plant diseases. Then, depending on the network architecture, this study outlined 16 studies on CNN-based plant disease severity assessment in terms of classical CNN frameworks, improved CNN architectures and CNN-based segmentation networks, and provided a detailed comparative analysis of the advantages and disadvantages of each. Common methods for acquiring datasets and performance evaluation metrics for CNN models were investigated. Finally, this study discussed the major challenges faced by CNN-based plant disease severity assessment methods in practical applications, and provided feasible research ideas and possible solutions to address these challenges.
... The loss function is the crucial component of the CNN to predict error through gradient calculation. Most of the studies on CNNs employ softmax or cross-entropy loss as the encoded output [126,127]. ...
The implementation of intelligent technology in agriculture is seriously investigated as a way to increase agriculture production while reducing the amount of human labor. In agriculture, recent technology has seen image annotation utilizing deep learning techniques. Due to the rapid development of image data, image annotation has gained a lot of attention. The use of deep learning in image annotation can extract features from images and has been shown to analyze enormous amounts of data successfully. Deep learning is a type of machine learning method inspired by the structure of the human brain and based on artificial neural network concepts. Through training phases that can label a massive amount of data and connect them up with their corresponding characteristics, deep learning can conclude unlabeled data in image processing. For complicated and ambiguous situations, deep learning technology provides accurate predictions. This technology strives to improve productivity, quality and economy and minimize deficiency rates in the agriculture industry. As a result, this article discusses the application of image annotation in the agriculture industry utilizing several deep learning approaches. Various types of annotations that were used to train the images are presented. Recent publications have been reviewed on the basis of their application of deep learning with current advancement technology. Plant recognition, disease detection, counting, classification and yield estimation are among the many advancements of deep learning architecture employed in many applications in agriculture that are thoroughly investigated. Furthermore, this review helps to assist researchers to gain a deeper understanding and future application of deep learning in agriculture. According to all of the articles, the deep learning technique has successfully created significant accuracy and prediction in the model utilized. Finally, the existing challenges and future promises of deep learning in agriculture are discussed.
... They have used pre-trained CNN and applied transfer learning to classify plants into 38 classes. Zeng et al. [28] have presented a high-order residual CNN architecture that extracts low-level details as well as high-level abstract representation simultaneously to improve classification performance and provided 91.3% classification accuracy with good generalization performance. ...
Identification of plant disease is usually done through visual inspection or during laboratory examination which causes delays resulting in yield loss by the time identification is complete. On the other hand, complex deep learning models perform the task with reasonable performance but due to their large size and high computational requirements, they are not suited to mobile and handheld devices. Our proposed approach contributes automated identification of plant diseases which follows a sequence of steps involving pre-processing, segmentation of diseased leaf area, calculation of features based on the Gray-Level Co-occurrence Matrix (GLCM), feature selection and classification. In this study, six color features and twenty-two texture features have been calculated. Support vector machines is used to perform one-vs-one classification of plant disease. The proposed model of disease identification provides an accuracy of 98.79% with a standard deviation of 0.57 on tenfold cross-validation. The accuracy on a self-collected dataset is 82.47% for disease identification and 91.40% for healthy and diseased classification. The reported performance measures are better or comparable to the existing approaches and highest among the feature-based methods, presenting it as the most suitable method to automated leaf-based plant disease identification. This prototype system can be extended by adding more disease categories or targeting specific crop or disease categories.
... They have used pre-trained CNN and applied transfer learning to classify plants into 38 classes. Zeng et al. [28] have presented a high-order residual CNN architecture that extracts low-level details as well as high-level abstract representation simultaneously to improve classification performance and provided 91.3% classification accuracy with good generalization performance. The proposed approach has targeted the problem through a more suitable two-step approach. ...
Identification of plant disease is usually done through visual inspection or during laboratory examination which causes delays resulting in yield loss by the time identification is complete. On the other hand, complex deep learning models perform the task with reasonable performance but due to their large size and high computational requirements, they are not suited to mobile and handheld devices. Our proposed approach contributes automated identification of plant diseases which follows a sequence of steps involving pre-processing, segmentation of diseased leaf area, calculation of features based on the Gray-Level Co-occurrence Matrix (GLCM), feature selection and classification. In this study, six color features and twenty-two texture features have been calculated. Support vector machines is used to perform one-vs-one classification of plant disease. The proposed model of disease identification provides an accuracy of 98.79% with a standard deviation of 0.57 on 10-fold cross-validation. The accuracy on a self-collected dataset is 82.47% for disease identification and 91.40% for healthy and diseased classification. The reported performance measures are better or comparable to the existing approaches and highest among the feature-based methods, presenting it as the most suitable method to automated leaf-based plant disease identification. This prototype system can be extended by adding more disease categories or targeting specific crop or disease categories.
... They have used pre-trained CNN and applied transfer learning to classify plants into 38 classes. Zeng et al. [28] has presented a high-order residual CNN architecture which extracts low level details as well as high-level abstract representation simultaneously to improve classification performance and provided 91.3% classification accuracy with good generalization performance. ...
Identification of plant disease is usually done through visual inspection or during laboratory examination which causes delays resulting in yield loss by the time identification is complete. On the other hand, complex deep learning models perform the task with reasonable performance but due to their large size and high computational requirements, they are not suited to mobile and handheld devices. Our proposed approach contributes automated identification of plant diseases which follows a sequence of steps involving pre-processing, segmentation of diseased leaf area, calculation of features based on the Gray-Level Co-occurrence Matrix (GLCM), feature selection and classification. In this study, six color features and twenty-two texture features have been calculated. Support vector machines is used to perform one-vs-one classification of plant disease. The proposed model of disease identification provides an accuracy of 98.79% with a standard deviation of 0.57 on 10-fold cross-validation. The accuracy on a self-collected dataset is 82.47% for disease identification and 91.40% for healthy and diseased classification. The reported performance measures are better or comparable to the existing approaches and highest among the feature-based methods, presenting it as the most suitable method to automated leaf-based plant disease identification. This prototype system can be extended by adding more disease categories or targeting specific crop or disease categories.
... Their classifier reached an overall accuracy of 98.00%. Zhang et al. (2018) suggested an enhanced CNN for the identifica- (Zeng et al., 2018). Although many useful results have been achieved in the literature, the image database used has a limited diversity; most of the images are photographed in laboratory environments instead of in practical application scenarios. ...
Crop disease has a negative impact on food security. If diverse crop diseases are not identified in time, they can spread and influence the quality, quantity, and production of grain. Severe crop diseases can even result in complete failure of the harvest. Recent developments in deep learning, particularly convolutional neural networks (CNNs), have exhibited impressive performance in both image recognition and classification. In this study, we propose a novel network architecture, namely Mobile‐DANet, to identify maize crop diseases. Based on DenseNet, we retained the structure of the transition layers and used the depthwise separable convolution in dense blocks instead of the traditional convolution layers, and then embedded the attention module to learn the importance of interchannel relationship and spatial points for input features. In addition, transfer learning was used in model training. By this means, we improved the accuracy of the model while saving more computational power than deep CNNs. This model achieved an average accuracy of 98.50% on the open maize data set, and even with complicated backdrop conditions, Mobile‐DANet realized an average accuracy of 95.86% for identifying maize crop diseases on a local data set. The experimental findings show the effectiveness and feasibility of the Mobile‐DANet. Our data set is available at https://github.com/xtu502/maize‐disease‐identification. The proposed procedure accomplished identification tasks on both the open and local maize image data sets, and achieved excellent performance compared with other state‐of‐the‐art methods.
... When being tested on 62 images from different illumination conditions, this deep CNN model exhibited good robustness by achieving 90.3% stress identification accuracy. Another study proposed a high-order residual CNN model (HOResNet) with improved anti-interference ability, which is more practical with realscene data (Zeng et al., 2018). Comparing to conventional network and feedback network, this HOResNet model revealed nontrivial gains in robustness on recognizing a new dataset with varied image sizes, different capturing angles or poses, diverse backgrounds and illuminations, or different noise levels. ...
Iron deficiency chlorosis (IDC) is a major yield-limiting factor for soybean production in the mid-western USA. The most practical solution in mitigating losses due to IDC is the development and characterization of IDC tolerant varieties. Leveraging the advanced technique of unmanned aircraft system (UAS) and the thriving deep learning methodology, a convolutional neural network (CNN) could be trained to assist breeders with IDC resistance selection. However, a known difficulty in IDC screening is that the symptoms often vary across diverse genetic backgrounds and spatial or temporal soil heterogeneities. A robust CNN model is desired to mitigate such difficulty. While high robustness usually relies on a sufficiently large labeled training data, the available labeled samples in most breeding programs are normally not enough. Under this limitation, it is critical to find an alternative way to train a robust model. The solution proposed in this study was to apply unsupervised pre-training on the unlabeled aerial images that are much easier to obtain by the UAS. Specifically, a convolutional autoencoder (CAE) was pre-trained on unlabeled sub-images clipped from aerial RGB images; then, the pre-trained weights were reused to initialize the CNN model that was trained on labeled plot-wise sub-images clipped from stitched RGB maps. To test the robustness of this CAE initialized model (CAE1-CNN), two baseline models were equally trained: the first was CAE2-CNN, where the CAE2 was pre-trained with three times of unlabeled data as that of CAE1, by adding wniter wheat and sorghum aerial images; the second was Ran-CNN where the CNN was randomly initialized. Three conditions were considered for testing model robustness: different soybean trials, field locations and vegetative growth stages. Results revealed that both the CAE1-CNN and the CAE2-CNN had relatively better robustness than the Ran-CNN model, i.e., higher R² and lower RMSE values, especially on different soybean trials and growth stages, which proved that the unsupervised pre-training added gains to the model robustness across diverse trials and growth stages. Similar performances were found between the CAE1-CNN andthe CAE2-CNN model, suggesting that augmenting the unlabled data did not bring significant improvement to model robustness. Additionally, during robustness test on different soybean trials, the unsupervised pre-training seemly showed the potential of alleviating the required number of labeled training samples. These promising findings could contribute to the research on crop stresses by providing a potential path towards developing a robust system for classifying or predicting stress severities under more varied conditions.
List of Papers in the Proceedings of CSAE (Computer Science and Application Engineering)conferences, Edited by Ali Emrouznejad