Effective Data Augmentation and Training Techniques for Improving Deep Learning in Plant Leaf Disease Recognition

Plant Leaf ◽

Training Techniques ◽

Leaf Disease ◽

Training Technique ◽

Augmentation Techniques ◽

And Training

Plant disease is the most common problem in agriculture. Usually, the symptoms appear on leaves of the plants which allow farmers to diagnose and prevent the disease from spreading to other areas. An accurate and consistent plant disease recognition system can help prevent the spread of diseases and save maintenance costs. In this research, we present a plant leaf disease recognition system using two deep convolutional neural networks (CNNs); MobileNetV2 and NasNetMobile. These CNN architectures are designed to be suitable for smartphones due to the models being small. We have experimented on training techniques; online, offline, and mixed training techniques on two plant leaf diseases. As for data augmentation techniques, we found that the combination of rotation, shift, and zoom techniques significantly increases the performance of the CNN architectures. The experimental results show that the most accurate algorithm for plant leaf disease recognition is NASNetMobile architecture using transfer learning. Additionally, the most accurate result is obtained when combining the offline training technique with data augmentation techniques.

Using Deep Learning for Image-Based Different Degrees of Ginkgo Leaf Disease Classification

Information ◽

10.3390/info11020095 ◽

2020 ◽

Vol 11 (2) ◽

pp. 95 ◽

Cited By ~ 1

Author(s):

Kaizhou Li ◽

Jianhui Lin ◽

Jinrong Liu ◽

Yandong Zhao

Keyword(s):

Deep Learning ◽

Ginkgo Biloba ◽

Plant Disease ◽

Disease Classification ◽

Field Conditions ◽

Laboratory Conditions ◽

Leaf Disease ◽

And Training ◽

Ginkgo Leaf

Diseases from Ginkgo biloba have brought great losses to medicine and the economy. Therefore, if the degree of disease can be automatically identified in Ginkgo biloba leaves, people will take appropriate measures to avoid losses in advance. Deep learning has made great achievements in plant disease identification and classification. For this paper, the convolution neural network model was used to classify the different degrees of ginkgo leaf disease. This study used the VGGNet-16 and Inception V3 models. After preprocessing and training 1322 original images under laboratory conditions and 2408 original images under field conditions, 98.44% accuracy was achieved under laboratory conditions and 92.19% under field conditions with the VGG model. The Inception V3 model achieved 92.3% accuracy under laboratory conditions and 93.2% under field conditions. Thus, the Inception V3 model structure was more suitable for field conditions. To our knowledge, there is very little research on the classification of different degrees of the same plant disease. The success of this study will have a significant impact on the prediction and early prevention of ginkgo leaf blight.

Detection of Plant Leaf Diseases by Applying Image Processing Schemes

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2019.8241 ◽

2019 ◽

Vol 16 (9) ◽

pp. 3728-3734

Author(s):

Navneet Kaur ◽

V. Devendran ◽

Sahil Verma

Keyword(s):

Image Processing ◽

Yield Loss ◽

Early Stage ◽

Crop Protection ◽

Recognition System ◽

Assessment System ◽

Plant Leaf ◽

Detection Techniques ◽

Leaf Disease ◽

Key Factor

Timely diagnosis of the disease is the key factor in agricultural productivity. If timely detection of the disease is not taken into account, it may lead to crop yield loss. Hence, agriculturists and agronomists face troubles to detect diseases successfully at an early stage or later stage. To support these personnels to diagnose disease syndromes in infected plants, deep learning plays an important role. The machine based recognition system based on image processing not only saves time but also is more robust and efficient in comparison to manual assessment system. It helps the growers to take timely steps involved in the judicious treatment of the concerned leaf diseases for crop protection. Maximizing the production or minimizing the production loss is the primary goal of automatic plant leaf disease recognition system. Following review presents some leaf disease detection techniques.

Efficient-CapsNet: capsule network with self-attention routing

Scientific Reports ◽

10.1038/s41598-021-93977-0 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Vittorio Mazzia ◽

Francesco Salvetti ◽

Marcello Chiaberge

Keyword(s):

Architectural Design ◽

Data Augmentation ◽

Routing Algorithm ◽

Affine Transformations ◽

Design Strategies ◽

Feature Maps ◽

Convolutional Networks ◽

Use Of Data ◽

AbstractDeep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient and for large datasets implies a massive redundancy of features detectors. Even though capsules networks are still in their infancy, they constitute a promising solution to extend current convolutional networks and endow artificial visual perception with a process to encode more efficiently all feature affine transformations. Indeed, a properly working capsule network should theoretically achieve higher results with a considerably lower number of parameters count due to intrinsic capability to generalize to novel viewpoints. Nevertheless, little attention has been given to this relevant aspect. In this paper, we investigate the efficiency of capsule networks and, pushing their capacity to the limits with an extreme architecture with barely 160 K parameters, we prove that the proposed architecture is still able to achieve state-of-the-art results on three different datasets with only 2% of the original CapsNet parameters. Moreover, we replace dynamic routing with a novel non-iterative, highly parallelizable routing algorithm that can easily cope with a reduced number of capsules. Extensive experimentation with other capsule implementations has proved the effectiveness of our methodology and the capability of capsule networks to efficiently embed visual representations more prone to generalization.

Augmentasi Data Pengenalan Citra Mobil Menggunakan Pendekatan Random Crop, Rotate, dan Mixup

Jurnal Teknik Informatika dan Sistem Informasi ◽

10.28932/jutisi.v6i2.2688 ◽

2020 ◽

Vol 6 (2) ◽

Author(s):

Joseph Sanjaya ◽

Mewati Ayub

Keyword(s):

Data Augmentation ◽

Learning System ◽

Training Data ◽

Two Dimensional ◽

Image Detection ◽

Geometric Transformations ◽

Car Model ◽

Augmentation Techniques ◽

Significant Generalization

Deep convolutional neural networks (CNNs) have achieved remarkable results in two-dimensional (2D) image detection tasks. However, their high expression ability risks overfitting. Consequently, data augmentation techniques have been proposed to prevent overfitting while enriching datasets. In this paper, a Deep Learning system for accurate car model detection is proposed using the ResNet-152 network with a fully convolutional architecture. It is demonstrated that significant generalization gains in the learning process are attained by randomly generating augmented training data using several geometric transformations and pixel-wise changes, such as image cropping and image rotation. We evaluated data augmentation techniques by comparison with competitive data augmentation techniques such as mixup. Data augmented ResNet models achieve better results for accuracy metrics than baseline ResNet models with accuracy 82.6714% on Stanford Cars Dataset.

Mass agnostic jet taggers

SciPost Physics ◽

10.21468/scipostphys.8.1.011 ◽

2020 ◽

Vol 8 (1) ◽

Cited By ~ 8

Author(s):

Layne Bradshaw ◽

Rashmish K. Mishra ◽

Andrea Mitridate ◽

Bryan Ostdiek

Keyword(s):

Data Augmentation ◽

Large Data ◽

New Physics ◽

Large Data Sets ◽

Data Sets ◽

Training Procedure ◽

Signal Identification ◽

Training Techniques ◽

Quantitative Metrics ◽

Searching for new physics in large data sets needs a balance between two competing effects—signal identification vs background distortion. In this work, we perform a systematic study of both single variable and multivariate jet tagging methods that aim for this balance. The methods preserve the shape of the background distribution by either augmenting the training procedure or the data itself. Multiple quantitative metrics to compare the methods are considered, for tagging 2-, 3-, or 4-prong jets from the QCD background. This is the first study to show that the data augmentation techniques of Planing and PCA based scaling deliver similar performance as the augmented training techniques of Adversarial NN and uBoost, but are both easier to implement and computationally cheaper.

Data Augmentation on Plant Leaf Disease Image Dataset Using Image Manipulation and Deep Learning Techniques

2019 IEEE 9th International Conference on Advanced Computing (IACC) ◽

10.1109/iacc48062.2019.8971580 ◽

2019 ◽

Cited By ~ 3

Author(s):

J Arun Pandian ◽

G Geetharamani ◽

B Annette

Keyword(s):

Deep Learning ◽

Data Augmentation ◽

Image Manipulation ◽

Plant Leaf ◽

Leaf Disease ◽

Learning Techniques ◽

Image Dataset

Plant Leaf Disease Detection and Classification using Optimized CNN Model

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.f5572.039621 ◽

2021 ◽

Vol 9 (6) ◽

pp. 233-238

Author(s):

Prabavathi S ◽

Kanmani P

Keyword(s):

Plant Disease ◽

Early Stage ◽

Disease Detection ◽

Severe Damage ◽

Plant Leaf ◽

Leaf Disease ◽

Accuracy Of Prediction ◽

Automatic Systems

Our economy depends on productivity in agriculture. The quantity and quality of the yield is greatly affected by various hazardous diseases. Early-stage detection of plant disease will be very helpful to prevent severe damage. Automatic systems to detect the changes in the plants by monitoring the abnormal symptoms in its growth will be more beneficial for the farmers. This paper presents a system for automatic prediction and classification of plant leaf diseases. The survey on various diseases classification techniques that can be used for plant leaf disease detection are also discussed. The proposed system will define the cropped image of a plant through image processing and feature extraction algorithms. Enhanced CNN model is designed and applied for about 20,600 images are collected as a dataset. Optimization is done to enhance the accuracy in the system prediction and to show the improvement in the true positive samples classification. The proposed system shows the improvement in the accuracy of prediction as 93.18% for three different species with twelve different diseases.

Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies ◽

RFaceID

10.1145/3494985 ◽

2021 ◽

Vol 5 (4) ◽

pp. 1-21

Author(s):

Chengwen Luo ◽

Zhongru Yang ◽

Xingyu Feng ◽

Jin Zhang ◽

Hong Jia ◽

...

Keyword(s):

Face Recognition ◽

Data Augmentation ◽

Negative Impact ◽

Facial Recognition ◽

Recognition System ◽

Privacy Leakage ◽

Multiple Data ◽

Extensive Evaluation ◽

Face Recognition System ◽

Face recognition (FR) has been widely used in many areas nowadays. However, the existing mainstream vision-based facial recognition has limitations such as vulnerability to spoofing attacks, sensitivity to lighting conditions, and high risk of privacy leakage, etc. To address these problems, in this paper we take a sparkly different approach and propose RFaceID, a novel RFID-based face recognition system. RFaceID only needs the users to shake their faces in front of the RFID tag matrix for a few seconds to get their faces recognized. Through theoretical analysis and experiment validations, the feasibility of the RFID-based face recognition is studied. Multiple data processing and data augmentation techniques are proposed to minimize the negative impact of environmental noises and user dynamics. A deep neural network (DNN) model is designed to characterize both the spatial and temporal feature of face shaking events. We implement the system and extensive evaluation results show that RFaceID achieves a high face recognition accuracy at 93.1% for 100 users, which shows the potential of RFaceID for future facial recognition applications.

A Study on Multiple Factors Affecting the Accuracy of Multiclass Skin Disease Classification

Applied Sciences ◽

10.3390/app11177929 ◽

2021 ◽

Vol 11 (17) ◽

pp. 7929

Author(s):

Jiayi Fan ◽

Jongwook Kim ◽

Insu Jung ◽

Yongkeun Lee

Keyword(s):

Transfer Learning ◽

Skin Disease ◽

Classification Accuracy ◽

Data Augmentation ◽

Skin Diseases ◽

Disease Classification ◽

Batch Size ◽

Multiple Factors ◽

Diagnosis of skin diseases by human experts is a laborious task prone to subjective judgment. Aided by computer technology and machine learning, it is possible to improve the efficiency and robustness of skin disease classification. Deep transfer learning using off-the-shelf deep convolutional neural networks (CNNs) has huge potential in the automation of skin disease classification tasks. However, complicated architectures seem to be too heavy for the classification of only a few skin disease classes. In this paper, in order to study potential ways to improve the classification accuracy of skin diseases, multiple factors are investigated. First, two different off-the-shelf architectures, namely AlexNet and ResNet50, are evaluated. Then, approaches using either transfer learning or trained from scratch are compared. In order to reduce the complexity of the network, the effects of shortening the depths of deep CNNs are investigated. Furthermore, different data augmentation techniques based on basic image manipulation are compared. Finally, the choice of mini-batch size is studied. Experiments were carried out on the HAM10000 skin disease dataset. The results show that the ResNet50-based model is more accurate than the AlexNet-based model. The transferred knowledge from the ImageNet database helps to improve the accuracy of the model. The reduction in stages of the ResNet50-based model can reduce complexity while maintaining good accuracy. Additionally, the use of different types of data augmentation techniques and the choice of mini-batch size can also affect the classification accuracy of skin diseases.

Review on Convolutional Neural Network (CNN) Applied to Plant Leaf Disease Classification

Agriculture ◽

10.3390/agriculture11080707 ◽

2021 ◽

Vol 11 (8) ◽

pp. 707

Author(s):

Jinzhu Lu ◽

Lijuan Tan ◽

Huanyu Jiang

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Plant Disease ◽

Plant Diseases ◽

Disease Classification ◽

Classification Methods ◽

Widespread Application ◽

Plant Leaf ◽

Leaf Disease ◽

Traditional Classification

Crop production can be greatly reduced due to various diseases, which seriously endangers food security. Thus, detecting plant diseases accurately is necessary and urgent. Traditional classification methods, such as naked-eye observation and laboratory tests, have many limitations, such as being time consuming and subjective. Currently, deep learning (DL) methods, especially those based on convolutional neural network (CNN), have gained widespread application in plant disease classification. They have solved or partially solved the problems of traditional classification methods and represent state-of-the-art technology in this field. In this work, we reviewed the latest CNN networks pertinent to plant leaf disease classification. We summarized DL principles involved in plant disease classification. Additionally, we summarized the main problems and corresponding solutions of CNN used for plant disease classification. Furthermore, we discussed the future development direction in plant disease classification.