Deep transfer learning model for disease identification in wheat crop

Nigam, Sapna; Jain, Rajni; Marwaha, Sudeep; Arora, Alka; Haque, Md. Ashraful; Dheeraj, Akshay; Singh, Vaibhav K.

doi:10.1016/j.ecoinf.2023.102068

Cited by 40 publications

(20 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset named WheatRust21 contains 6556 healthy and diseased leaf images. The Models such as VGG19, ResNet152, DenseNet169, InceptionNetV3, and MobileNetV2 were experimented with but achieved lesser accuracy than EfficientNet architecture, which reached an accuracy of 99.35% [39]. In this study by M.P.…”

Section: Related Workmentioning

confidence: 89%

High-performance deep transfer learning model with batch normalization based on multiscale feature fusion for tomato plant disease identification and categorization

Ramya,

Kumar

2023

Environ. Res. Commun.

View full text Add to dashboard Cite

Deep learning and machine learning are cutting-edge methods for analysing images that have considerable potential. Artificial Neural Networks (A-NNs), one of the most well-known methods of computer intelligence, are now used in machine learning (ML) and deep transfer learning (DL) to raise plant production and quality. Identification and primary prevention of plant diseases at the appropriate time are essential for boosting productivity. Due to the phenomenon of minimally intense data in the background and foreground areas of the image, the extensive colour similarity between regions of unhealthy and normal leaves, the presence of noise in the sampling data, and changes in the location, size, and shape of plant leaf, it is difficult to correctly identify and classify plant diseases. In an effort to address these issues, a reliable technique for classifying plant diseases was developed by using a deep AlexNet CNN architecture as the main network with batch normalisation. In the three-step process, the first annotation is made to obtain the RoI (region of interest). The AlexNet CNN is therefore suggested for deep primary feature extraction in a constructed efficient network. The research demonstrates that the existing strategy is superior to more recent ones in terms of accuracy and dependability in recognising diseases in plants. Based on a deep transfer AlexNet CNN model, this research work developed a model for diseases identification and classification in plant leaves. It is trained using additional datasets that include a variety of plant leaf classifications and background images. From Plant Village and Kaggle, we gathered data on healthy and diseased tomato plant leaves. We are obtaining a near-balanced dataset containing ten different leaf disease kinds, such as bacterial, fungal, viral, and nutrient insufficiency. Ten classes have been considered for this research by gathering a dataset with associated images of the typical and abnormal tomato plant leaves. Considered in this work were the various labels for healthy and diseased tomato leaves, such as early blight, Bacterial spot, late bright mold, healthy, etc. Since deep CNN models have shown notable machine vision results, they are used in this case to diagnose and categorise plant illnesses from their leaves. As a result, the proposed CNN models can thus now be evaluated from confusion matrix using data analysis criteria, primarily focusing on metrics for evaluation like training and validation accuracy, loss, Recall, Precision, F1 score, processing speed, and performance.

show abstract

Section: Related Workmentioning

confidence: 89%

High-performance deep transfer learning model with batch normalization based on multiscale feature fusion for tomato plant disease identification and categorization

Ramya,

Kumar

2023

Environ. Res. Commun.

View full text Add to dashboard Cite

show abstract

“…Next was the pre-trained ResNet152V2 model (He et al, 2016), which is the most complex and recent model architectures available of their respective model series. The ResNet152V2 model was selected due to its prevalence in image classification literature in a variety of different fields from disease ratings in agriculture (Kanchanadevi & Sandhia, 2023;Nigam et al, 2023) to medical research (Sulaiman et al, 2023). The final model was the pre-trained EfficientNetV2L model (Tan & Le, 2021), which was selected due to its recent use in plant disease detection (Shovon et al, 2023;Ulutaş & Aslantaş, 2023).…”

Section: Deep Learningmentioning

confidence: 99%

“…Some well‐known architectures include VGG16, ResNet models, and EfficientNet models. Many studies utilize these complex models in lieu of generating a new model from scratch (Kanchanadevi & Sandhia, 2023; Khaki et al., 2020; Nigam et al., 2023; Rao et al., 2022).…”

Section: Introductionmentioning

confidence: 99%

Phenotyping and predicting wheat spike characteristics using image analysis and machine learning

Hammers,

Winn,

Ben‐Hur

et al. 2023

The Plant Phenome Journal

View full text Add to dashboard Cite

Improvements in trait phenotyping are needed to increase the quantity and quality of data available for genetic improvement of crops. In this study, we used moderate throughput image analysis and machine learning as a pipeline for phenotyping a key wheat spike characteristic: spikelet number per spike. A population of 594 soft red winter wheat inbred lines was evaluated in the field for 2 years and images of wheat spikes were taken and used to train deep‐learning algorithms to predict spikelet number. A total of 12,717 images were used to train, test, and validate a basic regression convolutional neural network (CNN), a visual geometry group application regression model, VGG16, the ResNet152V2 model, and the EfficientNetV2L model. The EfficientNetV2L model was the most accurate, having the lowest mean absolute error, second lowest root mean square error, and highest coefficient of determination (mean absolute error [MAE] = 0.60, root mean square error [RMSE] = 0.79, and R2 = 0.90). The ResNet152V2 model was slightly less accurate with a slightly better fit (MAE = 0.61,m RMSE = 0.78, and R2 = 0.87), followed by the basic CNN (MAE = 0.75, RMSE = 1.00, and R2 = 0.74) and finally by the VGG16 (MAE = 1.51, RMSE = 1.29, and R2 = 0.076). With an average error of just above one half of a spikelet, utilizing image analysis and machine learning counting methods could be used for multiple breeding applications, including direct selection of spikelet number, to provide data to identify quantitative trait loci, or for training whole genome selection models.

show abstract

“…The proposed CA_DenseNet_BC_40 lightweight network model demonstrated remarkable accuracy, achieving a rate of 97.3% in classifying the severity of aphid damage under natural field conditions. Nigam et al 8 proposed a wheat disease recognition model based on fine-tuning the EfficientNet architecture, achieving exceptional identification accuracy rates of 99.35% for wheat stripe rust, leaf rust, and stem rust diseases. Yu et al 9 pioneered the integration of the Transformer structure into convolutional architectures, crafting an Inception Convolution Visual Transformer (ICVT) tailored for diverse plant disease recognition tasks.…”

Section: Introductionmentioning

confidence: 99%

ITFNet-API: Image and Text Based Multi-Scale Cross-Modal Feature Fusion Network for Agricultural Pest Identification

Yu,

Xu,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

In agricultural production, pest problems are inevitable. In recent years, China has suffered annual losses of up to 40 million tons of grain due to various pests and diseases. There are over one million known insect species in the natural world, exhibiting complex and diverse morphologies, making manual identification costly. With the advancement of deep learning technologies, methods relying solely on image data for crop pest identification have achieved some success. However, these methods heavily depend on numerous high-quality annotated images. Many existing approaches overlook the role and value of other modalities beyond images and rely solely on low-level image features for recognition. They fail to fully exploit semantic correlations between multimodal data, leading to poor reliability and interpretability of the recognition results. Moreover, in real-world scenarios, pest habitats are complex and diverse, with varying scales, imposing high demands on the practical application of models. To address these challenges, this paper proposes a Multi-Scale Cross-Modal Feature Fusion Model (ITFNet-API) utilizing multi-scale visual features and textual features for cross-modal attention learning. Super-resolution reconstruction techniques are introduced to restore high-frequency information in low-quality images. To avoid altering low-frequency information during the reconstruction process, the reconstructed high-quality images are combined with the original images and fed into the model for feature learning to enrich pest features. The proposed Image and Text Fusion Module (ITFM) performs multi-scale cross-modal information fusion and an Inverse Transpose Convolution (ITC) network module is introduced to restore multi-scale visual features. The obtained visual features are input into the neck and head networks of the YOLOv4 (You Only Look Once version 4) model to obtain pest category and location information in each image. Finally, to verify the model’s practical application capability, this paper introduces an Arbitrary Combination Image Enhancement (ACIE) data augmentation method which generates a batch of complex multi-target, multi-scale pest images in challenging scenarios for data augmentation and model training. We conducted extensive comparative experiments based on the IP102 dataset to validate the effectiveness of the proposed method. The experimental results indicate that our method achieved an accuracy rate of 82.15% in pest recognition, outperforming other advanced methods significantly with an AP50 of 92.18%. Moreover, in multi-target recognition,the accuracy rate reached 45.24% with an AP50 of 43.04%.

show abstract

Deep transfer learning model for disease identification in wheat crop

Cited by 40 publications

References 26 publications

High-performance deep transfer learning model with batch normalization based on multiscale feature fusion for tomato plant disease identification and categorization

High-performance deep transfer learning model with batch normalization based on multiscale feature fusion for tomato plant disease identification and categorization

Phenotyping and predicting wheat spike characteristics using image analysis and machine learning

ITFNet-API: Image and Text Based Multi-Scale Cross-Modal Feature Fusion Network for Agricultural Pest Identification

Contact Info

Product

Resources

About