N-CNN Based Transfer Learning Method for Classification of Powdery Mildew Wheat Disease
05 Mar 2021-pp 707-710
TL;DR: In this article, a pre-trained model is applied to the CIAGR images dataset via transfer learning method and achieved 89.9% classification accuracy for powdery wheat (PW) disease.
Abstract: Powdery wheat (PW) is one of the most common wheat diseases in northern India. It is the most damaging wheat disease and it is prevalent in April to May season. Several methods of machine learning (ML) and Deep Learning (DL) methods are used to do wheat disease classification. The previous DL techniques have not achieved higher accuracy during PW wheat disease classification. In the current study, 450 wheat images are collected from primary and secondary sources. The normalization technique is used for preprocessing. These normalized preprocessed images are input to CNN. The normalized images increase the training and testing accuracy of CNN. Then, this pre-trained model is applied to the CIAGR images dataset via transfer learning method. During testing with images, CNN achieves 89.9% classification accuracy for PW wheat disease. After these pre-trained model is applied to CIAGR dataset images and achieves 86.5% classification accuracy. Moreover, the result shows that pre-trained NCNN model achieves higher accuracy during transfer learning.
Citations
More filters
28 Apr 2022
TL;DR: In this paper , a Mask RCNN model was used to identify the location of each aphid in individual leaves automatically with the help of a Canon camera, a total of 6500 wheat images have been captured in the Punjab region with temperature 21-24° temperature.
Abstract: Wheat is one of the most common cereal crops in India. Aphids cause extensive damage to the whole wheat plant and lead to high yields loss. The aphid is transmitted on the summer day. Once the aphid is transmitted over the leave, the whole plant leave is damaged. Due to this, got damage whete plant and it also reduce the quality of wheat grain. Due to which the it is necessary to identify each aphid on wheat leaves. Only manual process is there to identify each aphid on wheat leave. Manually identification is a time-consuming and high laborious process. Therefore, the identification of wheat aphids through the Mask RCNN model can easily identify the location of each aphid in individual leave automatically. With the help of a Canon camera, a total of 6500 wheat images have been captured in the Punjab region with temperature 21–24° temperature. The Labelme software is used for the annotation of wheat leaves and wheat aphid. A total of 2300 and 1000 images have been randomly selected for training and testing purposes. The Mask scoring RCNN model is having a network capacity for learning the quality of predicted instance masks. Among all 1221 wheat leaves, a total number of 1021 wheat aphids have been found. The manually annotated ROI was compared to mask scoring ROI for wheat aphid identification and localization. Thus, the Mask scoring RCNN model has been achieved a high F1-score (96.66%) for wheat aphid detection in single wheat leave.
25 citations
26 Aug 2021
TL;DR: In this paper, a CNN-based deep learning (DL) multi-classification model was used to classify the potato crop plants having healthy and potato blight (PB) disease images based on their PB disease severity level, along with this binary classification has also been done to simply classify the healthy and disease crop leaf.
Abstract: Detection of plant crop diseases has become an active field of research day by day due to increasing the demand for such systems and techniques as crop diseases are now become a common part of agriculture. Focusing on this demand and need, we have developed a Convolutional neural network (CNN)-based Deep learning (DL) multi-classification model which classifies the total of 900 real-time collected images of potato crop plants having healthy and potato blight (PB) disease images based on their PB disease severity level, along with this binary classification has also been done to simply classify the healthy and disease crop leaf. A total of four disease severity levels have been taken into account which resulted in a binary classification accuracy of 90.77% and 94.77% of best multi-classification accuracy. This work will be a great contribution in the field of potato disease recognition and detection using DL approaches.
20 citations
26 Aug 2021
TL;DR: In this paper, a deep learning-based convolutional neural networks (CNN) model has been presented to detect and classify tomato spotted wilt (TSW) disease in real-time and self-captured images.
Abstract: The wide variety of diseases in the tomato plant affects the quality and quantity of the production. To counteract the problem of disease in tomato plants deep learning (DL) based convolutional neural networks (CNN) model has been presented in this paper that classify the real-time and self-captured 3000 images of healthy and tomato spotted wilt (TSW) disease plants. TSW is a type of infected virus that turns the upper sides of young tomato leaves as bronze and eventually acquires prominent, necrotic spots. Binary and multi-classification of the collected dataset have been made based on three different types of severity levels of TSW disease. In the case of binary classification, the accuracy is recorded at 91.56% and on the other hand, the best accuracy of multi-classification is recorded at 95.23% in the case of middle severity level. The model shows the least accuracy 94.5% and middle accuracy 95.2% in the case of early-stage severity and late severity level respectively. The proposed work will make a significant addition to the field of employing DL techniques to detect and classify tomato diseases.
18 citations
TL;DR: In this paper , an improved YoloV5 object detection network was employed to detect and record wheat ears in images collected from field plots at two locations over 2 years, which can be used as a quick, efficient, and convenient tool for assessment of the levels of damage caused by Fusarium head blight in wheat under field conditions.
16 citations
TL;DR: A comprehensive review of CNNs in computer vision for grain crop phenotyping is provided in this article , where the main results of recent studies on crop phenotype detection are discussed and summarized.
Abstract: Computer vision (CV) combined with a deep convolutional neural network (CNN) has emerged as a reliable analytical method to effectively characterize and quantify high-throughput phenotyping of different grain crops, including rice, wheat, corn, and soybean. In addition to the ability to rapidly obtain information on plant organs and abiotic stresses, and the ability to segment crops from weeds, such techniques have been used to detect pests and plant diseases and to identify grain varieties. The development of corresponding imaging systems to assess the phenotypic parameters, yield, and quality of crop plants will increase the confidence of stakeholders in grain crop cultivation, thereby bringing technical and economic benefits to advanced agriculture. Therefore, this paper provides a comprehensive review of CNNs in computer vision for grain crop phenotyping. It is meaningful to provide a review as a roadmap for future research in such a thriving research area. The CNN models (e.g., VGG, YOLO, and Faster R-CNN) used CV tasks including image classification, object detection, semantic segmentation, and instance segmentation, and the main results of recent studies on crop phenotype detection are discussed and summarized. Additionally, the challenges and future trends of the phenotyping techniques in grain crops are presented.
12 citations
References
More filters
TL;DR: In this paper, the difference in spectral reflectance between healthy and diseased wheat plants was investigated at an early stage in the development of the “yellow rust” disease, and a normalisation method based on reflectance and light intensity adjustments was developed.
267 citations
TL;DR: Experimental results demonstrate that the proposed system outperforms conventional CNN architectures on recognition accuracy under the same amount of parameters, meanwhile maintaining accurate localization for corresponding disease areas.
246 citations
TL;DR: A comprehensive review of recent studies carried out in the area of crop pest and disease recognition using image processing and machine learning techniques and reports that recent efforts have focused on the use of deep learning instead of training shallow classifiers using hand-crafted features.
176 citations
TL;DR: In this paper, two regression models: multivariate linear regression (MLR) and partial least square regression (PLSR) were developed for estimating the disease severity of powdery mildew.
147 citations
TL;DR: The work was funded by The Leverhulme Trust Research Project Grant RPG-2016-252 entitled “Novel Approaches for Constructing Optimised Multimodal Data Spaces”.
123 citations