Analysis of transfer learning for deep neural network based plant classification models

https://ro.ecu.edu.au/cgi/viewcontent.cgi?article=6091&context=ecuworkspost2013

A comprehensive review of fruit and vegetable classification techniques

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.

/pdf/maize-leaf-disease-identification-based-on-feature-1khyejyygi.pdf

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

http://ijeais.org/wp-content/uploads/2019/01/IJAISR190102.pdf

Plant Seedlings Classification Using Deep Learning

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.

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

There are hundreds of kinds of trees in the natural ecosystem, and it can be very difficult to distinguish between them. Botanists and those who study plants however, are able to identify the type of tree at a glance by using the characteristics of the leaf. Machine learning is used to automatically classify leaf types. Studied extensively in 2012, this is a rapidly growing field based on deep learning. Deep learning is itself a self-learning technique used on large amounts of data, and recent developments in hardware and big data have made this technique more practical. We propose a method to classify leaves using the CNN model, which is often used when applying deep learning to image processing.

Plant Leaf Recognition Using a Convolution Neural Network

Fingerprint Pattern Classification Using Convolution Neural Network

/pdf/comparative-analysis-of-generalized-intersection-over-union-21b4fjh7yg.pdf

Comparative Analysis of Generalized Intersection over Union and Error Matrix for Vegetation Cover Classification Assessment

In this study, we propose a method to regulate parking violations using computer vision technology. A still color image of the parked vehicle under question is obtained by a camera mounted on enforcement vehicles. The acquired image is preprocessed through a morphological algorithm and binarized. The vehicle’s shadows are detected from the binarized image, and lanes are identified using the information from the yellow parking lines that are drawn on the load. Whether parking is illegal is determined by the conformity of the lanes and the vehicle’s shadow.

Lane Detection for Parking Violation Assessments

In this paper, we propose a method that gives motion command to a mobile robot to recognize human being`s hand gesture. Former way of the robot-controlling system with the movement of hand used several kinds of pre-arranged gesture, therefore the ordering motion was unnatural. Also it forced people to study the pre-arranged gesture, making it more inconvenient. To solve this problem, there are many researches going on trying to figure out another way to make the machine to recognize the movement of the hand. In this paper, we used third-dimensional camera to obtain the color and depth data, which can be used to search the human hand and recognize its movement based on it. We used HMM method to make the proposed system to perceive the movement, then the observed data transfers to the robot making it to move at the direction where we want it to be.

/pdf/recognition-of-natural-hand-gesture-by-using-hmm-x6hvyawxs0.pdf

Sang-Yong Rhee

Papers

Plant Leaf Recognition Using a Convolution Neural Network

Fingerprint Pattern Classification Using Convolution Neural Network

Comparative Analysis of Generalized Intersection over Union and Error Matrix for Vegetation Cover Classification Assessment

Lane Detection for Parking Violation Assessments

Recognition of Natural Hand Gesture by Using HMM