Plant Leaf Recognition Using a Convolution Neural Network

Jeon, Wang-Su; Rhee, Sang-Yong

doi:10.5391/ijfis.2017.17.1.26

Cited by 122 publications

(48 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For further analysis of the performance of DMS-Robust Alexnet, a comparison is performed with GA-SVM [51], SEG-KNN [20], SIMPLE-CNN [33], VGGNet [40], GoogleNet [52] and ResNet [53], maize disease recognition baselines. The comparison results are indicated in Table 7.…”

Section: ) Comparison With Baseline Methodsmentioning

confidence: 99%

Maize Leaf Disease Identification Based on Feature Enhancement and DMS-Robust Alexnet

Zhou

et al. 2020

IEEE Access

150

View full text Add to dashboard Cite

The identification of maize leaf diseases will meet great challenges because of the difficulties in extracting lesion features from the constant-changing environment, uneven illumination reflection of the incident light source and many other factors. In this paper, a novel maize leaf disease recognition method is proposed. In this method, we first designed a maize leaf feature enhancement framework with the capability of enhancing the features of maize under the complex environment. Then a novel neural network is designed based on backbone Alexnet architecture, named DMS-Robust Alexnet. In the DMS-Robust Alexnet, dilated convolution and multi-scale convolution are combined to improve the capability of feature extraction. Batch normalization is performed to prevent network over-fitting while enhancing the robustness of the model. PRelu activation function and Adabound optimizer are employed to improve both convergence and accuracy. In experiments, it is validated from different perspectives that the maize leaf disease feature enhancement algorithm is conducive to improving the capability of the DMS-Robust Alexnet identification. Our method demonstrates strong robustness for maize disease images collected in the natural environment, providing a reference for the intelligent diagnosis of other plant leaf diseases. INDEX TERMS Image enhancement, dilated convolution, multi-scale convolution, maize leaf disease, convolutional neural network.

show abstract

Section: ) Comparison With Baseline Methodsmentioning

confidence: 99%

Maize Leaf Disease Identification Based on Feature Enhancement and DMS-Robust Alexnet

Zhou

et al. 2020

IEEE Access

150

View full text Add to dashboard Cite

show abstract

“…Liu et al used convolutional neural network (CNN) for analyzing hyperspectral data, and their results indicated that the deep learning framework can give excellent performance for detection of defect regions on surface-defective cucumbers [ 21 ]. Jeon and Rhee also used CNN model to classify leaves, and the recognition rate was greater than 94% [ 22 ]. Similar CNN models were also used for tomato disease recognition [ 23 ] and melon lesion detection [ 24 ].…”

Section: Introductionmentioning

confidence: 99%

Application of Deep Learning Architectures for Accurate and Rapid Detection of Internal Mechanical Damage of Blueberry Using Hyperspectral Transmittance Data

Wang

Zhai

2018

Sensors

126

View full text Add to dashboard Cite

Deep learning has become a widely used powerful tool in many research fields, although not much so yet in agriculture technologies. In this work, two deep convolutional neural networks (CNN), viz. Residual Network (ResNet) and its improved version named ResNeXt, are used to detect internal mechanical damage of blueberries using hyperspectral transmittance data. The original structure and size of hypercubes are adapted for the deep CNN training. To ensure that the models are applicable to hypercube, we adjust the number of filters in the convolutional layers. Moreover, a total of 5 traditional machine learning algorithms, viz. Sequential Minimal Optimization (SMO), Linear Regression (LR), Random Forest (RF), Bagging and Multilayer Perceptron (MLP), are performed as the comparison experiments. In terms of model assessment, k-fold cross validation is used to indicate that the model performance does not vary with the different combination of dataset. In real-world application, selling damaged berries will lead to greater interest loss than discarding the sound ones. Thus, precision, recall, and F1-score are also used as the evaluation indicators alongside accuracy to quantify the false positive rate. The first three indicators are seldom used by investigators in the agricultural engineering domain. Furthermore, ROC curves and Precision-Recall curves are plotted to visualize the performance of classifiers. The fine-tuned ResNet/ResNeXt achieve average accuracy and F1-score of 0.8844/0.8784 and 0.8952/0.8905, respectively. Classifiers SMO/ LR/RF/Bagging/MLP obtain average accuracy and F1-score of 0.8082/0.7606/0.7314/0.7113/0.7827 and 0.8268/0.7796/0.7529/0.7339/0.7971, respectively. Two deep learning models achieve better classification performance than the traditional machine learning methods. Classification for each testing sample only takes 5.2 ms and 6.5 ms respectively for ResNet and ResNeXt, indicating that the deep learning framework has great potential for online fruit sorting. The results of this study demonstrate the potential of deep CNN application on analyzing the internal mechanical damage of fruit.

show abstract

“…A deep convolution neural network (DCNN) is a multilayer neural network that is performed as a deep supervised learning method [15]. The DCNN has achieved excellent performances on image recognition tasks for the last few years [7,8,16,17]. It can perform both feature extraction and image classification tasks [15].…”

Section: Dcnn Classifiermentioning

confidence: 99%

An automated eye disease recognition system from visual content of facial imagesusing machine learning techniques

Akram¹,

Debnath²

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Many eye diseases like cataracts, trachoma, or corneal ulcer can cause vision problems. Progression of these eye diseases can only be prevented if they are recognized accurately at the early stage. Visually observable symptoms differ a lot among these eye diseases. However, a wide variety of symptoms is necessary to be analyzed for the accurate detection of eye diseases. In this paper, we propose a novel approach to provide an automated eye disease recognition system using visually observable symptoms applying digital image processing techniques and machine learning techniques such as deep convolution neural network (DCNN) and support vector machine (SVM). We apply the principal component analysis and t-distributed stochastic neighbor embedding methods for better feature selection. The proposed system automatically divides the facial components from the frontal facial image and extracts the eye part. The proposed method analyzes and classifies seven eye diseases including cataracts, trachoma, conjunctivitis, corneal ulcer, ectropion, periorbital cellulitis, and Bitot's spot of vitamin A deficiency. From the experimental results, we see that the DCNN model outperforms SVM models. We also compare our method with some other existing methods. Our method shows improved accuracy compared to other methods. The average accuracy rate of our DCNN model is 98.79% with sensitivity of 97% and specificity of 99%.

show abstract

Plant Leaf Recognition Using a Convolution Neural Network

Cited by 122 publications

References 8 publications

Maize Leaf Disease Identification Based on Feature Enhancement and DMS-Robust Alexnet

Maize Leaf Disease Identification Based on Feature Enhancement and DMS-Robust Alexnet

Application of Deep Learning Architectures for Accurate and Rapid Detection of Internal Mechanical Damage of Blueberry Using Hyperspectral Transmittance Data

An automated eye disease recognition system from visual content of facial imagesusing machine learning techniques

Contact Info

Product

Resources

About