Image classifiers and image deep learning classifiers evolved in detection of Oryza sativa diseases: survey

Goluguri, N. V. Raja Reddy; Devi, K. Suganya; Vadaparthi, Nagesh

doi:10.1007/s10462-020-09849-y

Cited by 18 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When they complete this tutorial experience, they should be in a position to ask biological questions, analyze available resources, and approach several types of plant image datasets using various AI algorithms. Although a single workflow cannot be considered the best choice as different algorithms are to be assessed for different tasks and objectives, our approach is in agreement with common image-based analytical methods, along the lines of those described elsewhere, 36,37,75 as essential key steps in the workflow of image analysis. The four steps of this workflow are illustrated in Figure 2.…”

Section: Going Aimentioning

confidence: 64%

Ready, Steady, Go AI: A practical tutorial on fundamentals of artificial intelligence and its applications in phenomics image analysis

Nakhle

Harfouche

2021

Patterns

View full text Add to dashboard Cite

Summary High-throughput image-based technologies are now widely used in the rapidly developing field of digital phenomics and are generating ever-increasing amounts and diversity of data. Artificial intelligence (AI) is becoming a game changer in turning the vast seas of data into valuable predictions and insights. However, this requires specialized programming skills and an in-depth understanding of machine learning, deep learning, and ensemble learning algorithms. Here, we attempt to methodically review the usage of different tools, technologies, and services available to the phenomics data community and show how they can be applied to selected problems in explainable AI-based image analysis. This tutorial provides practical and useful resources for novices and experts to harness the potential of the phenomic data in explainable AI-led breeding programs.

show abstract

Section: Going Aimentioning

confidence: 64%

Ready, Steady, Go AI: A practical tutorial on fundamentals of artificial intelligence and its applications in phenomics image analysis

Nakhle

Harfouche

2021

Patterns

View full text Add to dashboard Cite

show abstract

“…Several image processing methodologies and machinelearning classifiers involved in the identification of Oryza Sativa plant disease have been reviewed [20]. It was inferred from the study that all the study presented was largely limited to Rice blasts or Brown spots.…”

Section: Related Workmentioning

confidence: 99%

ATRLeNet: A Deep Learning Model for Enhanced Classification of Oryza Sativa Pathologies

Goluguri,

Gogula

et al. 2023

View full text Add to dashboard Cite

Diseases affecting the Oryza Sativa (rice) plant result in substantial agricultural losses, leading to a decline in crop productivity by up to 25% and posing a significant threat to global food security. Hence, the rapid and accurate diagnosis of such diseases is paramount to ensure effective treatment and to enhance overall plant health. This has led to an increased interest among plant pathologists in developing reliable methods for identifying diseases in Oryza Sativa crops. In this study, an innovative disease classification model for the Oryza Sativa plant is proposed, leveraging the Optimal Adaptive Boosting Cascade Classifier (OABCC) and the efficient-artificial fish swarm optimization (EAFSO). A weighted image fusion technique is utilized in the pre-processing stage for image denoising, combining the outcomes of homomorphic filtering (HAF), Laplace filtering (LAF), and the Kuwahara Filter (KF). The diseased portions of the Oryza Sativa plant leaf are localized using the OABCC, while Soft Non-Maximum Suppression (SN-MS) is deployed to select the optimal detection box for each item. The LeNet model, bolstered with an atrous-convolution layer, is integrated into the OABCC for improved disease classification. Further enhancement in model accuracy is achieved through the application of the EAFSO optimization strategy. When applied to the OABCC-ATRLeNet model for rice disease classification, the EAFSO optimization strategy outperforms other strategies such as WSSO, CSO, AFSO, and PSO. This research underscores the potential of deep learning approaches for robust and accurate classification of plant diseases, contributing significantly to the efforts in securing global food resources.

show abstract

“…A support vector machine-based computer vision system for identifying Chlorosis in plant leaves was suggested and achieved a 95.69 percent accuracy rate. Machine learning and other statistical approaches suffer from a lack of performance since they require manual characteristics for their operation [20]. This led to the development of NN-based approaches with a diagnosis of crop diseases in big datasets.…”

Section: Literature Surveymentioning

confidence: 99%

“…The model achieved a 97.403% accuracy value for different images. Transfer learning was utilised to train the EfficientNet architecture with a disease classifier, and numerous images were used for the training process in the experimentation [20,21].…”

Section: Literature Surveymentioning

confidence: 99%

Utilizing Deep Convolutional Neural Networks for Multi-Classification of Plant Diseases from Image Data

Elumalai,

Jahir Hussain

2023

View full text Add to dashboard Cite

The economic health of a nation is significantly influenced by the productivity of its agricultural sector. Enhancing this productivity is directly linked to the early detection and management of plant diseases. Automated classification methodologies are instrumental in the early diagnosis of these diseases, offering improved precision over traditional methods. These automated systems initiate disease detection as soon as symptoms begin to manifest on plant leaves, following a four-step process involving pre-processing, segmentation, feature extraction, and classification. In this study, we present an automated methodology for the detection and classification of plant diseases using a deep-learning approach applied to varying quality leaf images. A deep convolutional neural network architecture was trained utilizing an image dataset. The proposed Deep Neural Network Plant Disease Classifier (DNN-PDC) was specifically designed for the multi-categorization of plant diseases. Tomato leaf images from the PlantVillage dataset on Kaggle were selected for the experiments. The proposed deep learning system demonstrated a high level of accuracy in the classification of various tomato leaf diseases, including Early Blight, Septoria Leaf Spot, and Late Blight. Experimental results indicate that the proposed method surpasses existing approaches in the image-based classification of tomato plant diseases. This study underscores the potential of the DNN-PDC model as a highly effective tool for plant disease detection and classification.

show abstract

Image classifiers and image deep learning classifiers evolved in detection of Oryza sativa diseases: survey

Cited by 18 publications

References 26 publications

Ready, Steady, Go AI: A practical tutorial on fundamentals of artificial intelligence and its applications in phenomics image analysis

Ready, Steady, Go AI: A practical tutorial on fundamentals of artificial intelligence and its applications in phenomics image analysis

ATRLeNet: A Deep Learning Model for Enhanced Classification of Oryza Sativa Pathologies

Utilizing Deep Convolutional Neural Networks for Multi-Classification of Plant Diseases from Image Data

Contact Info

Product

Resources

About