Comparison of convolution neural networks for smartphone image based real time classification of citrus leaf disease

Barman, Utpal; Choudhury, Ridip Dev; Sahu, Diganto; Barman, Golap Gunjan

doi:10.1016/j.compag.2020.105661

Cited by 98 publications

(59 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature extraction in traditional ML techniques mainly relies on user-specified features that may cause the loss of some important information, due to which researchers are then faced with difficulty in getting accurate results. Deep learning techniques determine the features of the images in different layers instead of relying on the self-made features of the images [2]. For example, in a study by Rozman and Stajnko [9], the quality of tomato seeds was reported in terms of their vigour and germination.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Convolution Neural Network-Based Seed Classification System

Hamid²,

et al. 2020

View full text Add to dashboard Cite

Over the last few years, the research into agriculture has gained momentum, showing signs of rapid growth. The latest to appear on the scene is bringing convenience in how agriculture can be done by employing various computational technologies. There are lots of factors that affect agricultural production, with seed quality topping the list. Seed classification can provide additional knowledge about quality production, seed quality control and impurity identification. The process of categorising seeds has been traditionally done based on characteristics like colour, shape and texture. Generally, this is performed by specialists by visually inspecting each sample, which is a very tedious and time-consuming task. This procedure can be easily automated, providing a significantly more efficient method for seed sorting than having them be inspected using human labour. In related areas, computer vision technology based on machine learning (ML), symmetry and, more particularly, convolutional neural networks (CNNs) have been generously applied, often resulting in increased work efficiency. Considering the success of the computational intelligence methods in other image classification problems, this research proposes a classification system for seeds by employing CNN and transfer learning. The proposed system contains a model that classifies 14 commonly known seeds with the implication of advanced deep learning techniques. The techniques applied in this research include decayed learning rate, model checkpointing and hybrid weight adjustment. This research applies symmetry when sampling the images of the seeds during data formation. The application of symmetry generates homogeneity with regards to resizing and labelling the images to extract their features. This resulted in 99% classification accuracy during the training set. The proposed model produced results with an accuracy of 99% for the test set, which contained 234 images. These results were much higher than the results reported in related research.

show abstract

Section: Related Workmentioning

confidence: 99%

“…This field is considered one of the most challenging research fields, and technology has massive potential to be incorporated into it to increase the mass and quality of agricultural products. The incorporation of AI, particularly deep learning perceptions, can be used to make advances in the agricultural sector [2].…”

Section: Introductionmentioning

confidence: 99%

A Convolution Neural Network-Based Seed Classification System

Hamid²,

et al. 2020

View full text Add to dashboard Cite

show abstract

“…As NASNetMobile requires little computing power to classify the given images, it can run on mobile devices such as smartphones, drones, or automatic agricultural vehicles for real-time monitoring and disease identification of large open-air crops. At present, due to the large-scale application of 5G, high-efficiency transmission, and improvements to the hardware configuration of mobile terminal equipment, it is possible to upload images locally to the cloud server for processing, and then return the identification and classification results to the terminal (Johannes et al, 2017 ; Toseef and Khan, 2018 ; Picon et al, 2019 ), or to use a GPU/CPU at the terminal to process and display the results (Barman et al, 2020 ). For growers in remote areas, real-time detection and diagnosis can be carried out through mobile terminals, thus solving the practical problems of obtaining technical crop disease diagnosis and finding experts in the production process.…”

Section: Discussionmentioning

confidence: 99%

Fine-Grained Image Classification for Crop Disease Based on Attention Mechanism

Yang

et al. 2020

Front. Plant Sci.

View full text Add to dashboard Cite

Fine-grained image classification is a challenging task because of the difficulty in identifying discriminant features, it is not easy to find the subtle features that fully represent the object. In the fine-grained classification of crop disease, visual disturbances such as light, fog, overlap, and jitter are frequently encountered. To explore the influence of the features of crop leaf images on the classification results, a classification model should focus on the more discriminative regions of the image while improving the classification accuracy of the model in complex scenes. This paper proposes a novel attention mechanism that effectively utilizes the informative regions of an image, and describes the use of transfer learning to quickly construct several fine-grained image classification models of crop disease based on this attention mechanism. This study uses 58,200 crop leaf images as a dataset, including 14 different crops and 37 different categories of healthy/diseased crops. Among them, different diseases of the same crop have strong similarities. The NASNetLarge fine-grained classification model based on the proposed attention mechanism achieves the best classification effect, with an F1 score of up to 93.05%. The results show that the proposed attention mechanism effectively improves the fine-grained classification of crop disease images.

show abstract

“…The method can provide stable recognition results and is easily deployed in mobile devices. Utpal Barman [42] compared MobileNet CNN and Self-Structured CNN (SSCNN) based on citrus disease dataset from smartphone images. The experiments show that SSCNN is more accurate in classifying citrus leaf diseases based on smartphone images and takes less computation time.…”

Section: Related Workmentioning

confidence: 99%

DBA_SSD ： A Novel End-to-End Object Detection Using Deep Attention Module for Helping Smart Device with Vegetable and Fruit Leaf Plant Disease Detection

Wang¹,

Yang²,

Yu³

et al. 2021

Preprint

View full text Add to dashboard Cite

In response to the difficulty of detecting and classifying pests and vegetable and fruit leaves with pests and diseases, this study proposes a novel vegetable and fruit leaf pest detection method called deep block attention SSD (DBA_SSD) for the identification of pests and diseases and classification of the degree of pests and diseases of vegetable and fruit leaves. We propose three vegetable and fruit leaf pest detection methods, namely, squeeze-and excitation SSD (Se_SSD), DB_SSD, and DBA_SSD. Se_SSD fuses SSD feature extraction network and attention mechanism channel, DB_SSD improves VGG feature extraction network, and DBA_SSD fuses the improved VGG network and channel attention mechanism. To reduce the training time and accelerate the training process, the convolutional layers trained in the Image Net image dataset by the VGG model are migrated to this model, whereas the collected vegetable and fruit disease image dataset is randomly divided into training set, validation set, and test set in the ratio of 8:1:1. In addition, data enhancement methods, such as histogram equalization and horizontal flip were used to expand the image data. The performance of the three improved algorithms is compared and analyzed in the same environment and with the classical target detection algorithms YOLOv4, YOLOv3, Faster RCNN, and YOLOv4 tiny. Experiments show that DBA_SSD outperforms the two other improved algorithms, and its performance in comparative analysis is superior to other target detection algorithms.

show abstract

Comparison of convolution neural networks for smartphone image based real time classification of citrus leaf disease

Cited by 98 publications

References 22 publications

A Convolution Neural Network-Based Seed Classification System

A Convolution Neural Network-Based Seed Classification System

Fine-Grained Image Classification for Crop Disease Based on Attention Mechanism

DBA_SSD ： A Novel End-to-End Object Detection Using Deep Attention Module for Helping Smart Device with Vegetable and Fruit Leaf Plant Disease Detection

Contact Info

Product

Resources

About