scholarly journals One-dimensional DCNN Feature Selective Transformation with LSTM-RDN for Image Classification

2021 ◽  
Author(s):  
li chaorong ◽  
Yuanyuan Huang ◽  
WEI HUANG ◽  
Fengqing Qin
Keyword(s):  
Feature Selection ◽  
Image Classification ◽  
Short Term Memory ◽  
Feature Learning ◽  
Network Models ◽  
Transformation Method ◽  
Deep Convolutional Neural Networks ◽  
One Dimensional ◽  
Selective Transformation ◽  
Image Datasets

Feature selection and transformation are the important techniques in machine learning field. A good feature selection / transformation method will greatly improve the performance of classification algorithm. In this work, we proposed a simple but efficient image classification method which is based on two-stage processing strategy. In the first processing stage, the one-dimensional features are obtained from image by transfer learning with the pre-trained Deep Convolutional Neural Networks (DCNN). These one-dimensional DCNN features still have the shortcomings of information redundancy and weak distinguishing ability. Therefore, it is necessary to use feature transformation to continue to obtain more distinguishable features. We propose a feature learning and selective transformation network based on Long Short-Term Memory (LSTM) combing ReLU and Dropout layers (called LSTM-RDN) to further process DCNN one-dimensional features. . The verification experiments were conducted on three public object image datasets(Cifar10, Cifar100 and Fashion-MNIST), three fine-grained image datasets(CUB200-2011, Stanford-Cars, FGVC-Aircraft) and a COVID-19 dataset. In the experiments, we used several backbone network models, including AlexNet, VGG16, ResNet18, ResNet101, InceptionV2 and EfficientNet-b0. Experimental results have shown that through feature selective transformation, the recognition accuracy of these DCNN models can significantly exceed the classification accuracies of the state-of-the-art methods.

scholarly journals One-dimensional DCNN Feature Selective Transformation with LSTM-RDN for Image Classification

2021 ◽  
Author(s):  
li chaorong ◽  
Yuanyuan Huang ◽  
WEI HUANG ◽  
Fengqing Qin
Keyword(s):  
Feature Selection ◽  
Image Classification ◽  
Short Term Memory ◽  
Feature Learning ◽  
Network Models ◽  
Transformation Method ◽  
Deep Convolutional Neural Networks ◽  
One Dimensional ◽  
Selective Transformation ◽  
Image Datasets

Feature selection and transformation are the important techniques in machine learning field. A good feature selection / transformation method will greatly improve the performance of classification algorithm. In this work, we proposed a simple but efficient image classification method which is based on two-stage processing strategy. In the first processing stage, the one-dimensional features are obtained from image by transfer learning with the pre-trained Deep Convolutional Neural Networks (DCNN). These one-dimensional DCNN features still have the shortcomings of information redundancy and weak distinguishing ability. Therefore, it is necessary to use feature transformation to continue to obtain more distinguishable features. We propose a feature learning and selective transformation network based on Long Short-Term Memory (LSTM) combing ReLU and Dropout layers (called LSTM-RDN) to further process DCNN one-dimensional features. . The verification experiments were conducted on three public object image datasets(Cifar10, Cifar100 and Fashion-MNIST), three fine-grained image datasets(CUB200-2011, Stanford-Cars, FGVC-Aircraft) and a COVID-19 dataset. In the experiments, we used several backbone network models, including AlexNet, VGG16, ResNet18, ResNet101, InceptionV2 and EfficientNet-b0. Experimental results have shown that through feature selective transformation, the recognition accuracy of these DCNN models can significantly exceed the classification accuracies of the state-of-the-art methods.

scholarly journals One-dimensional DCNN Feature Selective Transformation with LSTM-RDN for Image Classification

2021 ◽  
Author(s):  
li chaorong ◽  
Yuanyuan Huang ◽  
WEI HUANG ◽  
Fengqing Qin
Keyword(s):  
Feature Selection ◽  
Image Classification ◽  
Large Scale ◽  
Short Term Memory ◽  
Recognition Performance ◽  
Classification Method ◽  
Deep Convolutional Neural Networks ◽  
One Dimensional ◽  
Selective Transformation ◽  
Image Datasets

Feature selection and transformation are the important techniques in machine learning field. A good feature selection or transformation will greatly improve the performance of classification method. In this work, we proposed a simple but efficient image classification method which is based on two-stage processing strategy. In the first stage, the one-dimensional features are obtained from image by transfer learning with the pre-trained Deep Convolutional Neural Networks (DCNN). These one-dimensional DCNN features still have the shortcomings of information redundancy and weak distinguishing ability. Therefore, it is necessary to use feature transformation to further obtain more discriminative features. We propose a feature learning and selective transformation network based on Long Short-Term Memory (LSTM) combing ReLU and Dropout layers (called LSTM-RDN) to further process one-dimensional DCNN features. The verification experiments were conducted on three public object image datasets (Cifar10, Cifar100 and Fashion-MNIST), three fine-grained image datasets (CUB200-2011, Stanford-Cars, FGVC-Aircraft) and a COVID-19 dataset, and several backbone network models were used, including AlexNet, VGG16, ResNet18, ResNet101, InceptionV2 and EfficientNet-b0. Experimental results have shown that the recognition performance of the proposed method can significantly exceed the performance of existing state-of-the-art methods. The level of machine vision classification has reached the bottleneck, it is difficult to solve this problem by using a large-scale network model which has huge parameters that need to be optimized. We present an effective approach for breaking through the bottleneck of visual classification task by feature extraction with backbone DCNN and feature selective transformation with LSTM-RDN, separately. The code and pre-trained models are available from: https://github.com/lillllllll/LSTM-RDN

scholarly journals Comparison of Convolutional Neural Network Models for Mobile Devices

2021 ◽  
Author(s):  
Vivian Kimie Isuyama ◽  
Bruno De Carvalho Albertini
Keyword(s):  
Neural Network ◽  
Image Classification ◽  
Mobile Devices ◽  
Network Models ◽  
Model Complexity ◽  
Accuracy Rate ◽  
Deep Convolutional Neural Networks ◽  
Neural Network Models ◽  
Daily Lives ◽  
And Storage

In recent years mobile devices have become an important part of our daily lives and Deep Convolutional Neural Networks have been performing well in the task of image classification. Some considerations have to be made when running a Neural Network inside a mobile device such as computational complexity and storage size. In this paper, common architectures for image classification were analyzed to retrieve the values of accuracy rate, model complexity, memory usage, and inference time. Those values were compared and it was possible to show which architecture to choose from considering mobile restrictions.

CNN-based Classification of Degraded Images

2020 ◽  
Vol 2020 (10) ◽  
pp. 28-1-28-7 ◽  
Author(s):  
Kazuki Endo ◽  
Masayuki Tanaka ◽  
Masatoshi Okutomi
Keyword(s):  
Neural Networks ◽  
Image Restoration ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Deep Convolutional Neural Networks ◽  
Alternative Approach ◽  
Degraded Image ◽  
Degraded Images ◽  
Straightforward Approach

Classification of degraded images is very important in practice because images are usually degraded by compression, noise, blurring, etc. Nevertheless, most of the research in image classification only focuses on clean images without any degradation. Some papers have already proposed deep convolutional neural networks composed of an image restoration network and a classification network to classify degraded images. This paper proposes an alternative approach in which we use a degraded image and an additional degradation parameter for classification. The proposed classification network has two inputs which are the degraded image and the degradation parameter. The estimation network of degradation parameters is also incorporated if degradation parameters of degraded images are unknown. The experimental results showed that the proposed method outperforms a straightforward approach where the classification network is trained with degraded images only.

Feature Selection for Histopathological Image Classification using levy Flight Salp Swarm Optimizer

2019 ◽  
Vol 12 (4) ◽  
pp. 329-337 ◽  
Author(s):  
Venubabu Rachapudi ◽  
Golagani Lavanya Devi
Keyword(s):  
Feature Selection ◽  
Image Classification ◽  
Feature Selection Method ◽  
Selection Method ◽  
Lévy Flight ◽  
Levy Flight ◽  
Local Optima ◽  
Histopathological Image ◽  
Surf Features ◽  
Histopathological Image Classification

Background: An efficient feature selection method for Histopathological image classification plays an important role to eliminate irrelevant and redundant features. Therefore, this paper proposes a new levy flight salp swarm optimizer based feature selection method. Methods: The proposed levy flight salp swarm optimizer based feature selection method uses the levy flight steps for each follower salp to deviate them from local optima. The best solution returns the relevant and non-redundant features, which are fed to different classifiers for efficient and robust image classification. Results: The efficiency of the proposed levy flight salp swarm optimizer has been verified on 20 benchmark functions. The anticipated scheme beats the other considered meta-heuristic approaches. Furthermore, the anticipated feature selection method has shown better reduction in SURF features than other considered methods and performed well for histopathological image classification. Conclusion: This paper proposes an efficient levy flight salp Swarm Optimizer by modifying the step size of follower salp. The proposed modification reduces the chances of sticking into local optima. Furthermore, levy flight salp Swarm Optimizer has been utilized in the selection of optimum features from SURF features for the histopathological image classification. The simulation results validate that proposed method provides optimal values and high classification performance in comparison to other methods.

scholarly journals Data Independent Acquisition Based Bi-Directional Deep Networks for Biometric ECG Authentication

2021 ◽  
Vol 11 (3) ◽  
pp. 1125
Author(s):  
Htet Myet Lynn ◽  
Pankoo Kim ◽  
Sung Bum Pan
Keyword(s):  
Short Term Memory ◽  
Feature Learning ◽  
Biometric Authentication ◽  
Qrs Complex ◽  
Data Types ◽  
Ecg Signals ◽  
Data Independent Acquisition ◽  
Deep Networks ◽  
Classification Tasks ◽  
Electrocardiogram Ecg

In this report, the study of non-fiducial based approaches for Electrocardiogram(ECG) biometric authentication is examined, and several excessive techniques are proposed to perform comparative experiments for evaluating the best possible approach for all the classification tasks. Non-fiducial methods are designed to extract the discriminative information of a signal without annotating fiducial points. However, this process requires peak detection to identify a heartbeat signal. Based on recent studies that usually rely on heartbeat segmentation, QRS detection is required, and the process can be complicated for ECG signals for which the QRS complex is absent. Thus, many studies only conduct biometric authentication tasks on ECG signals with QRS complexes, and are hindered by similar limitations. To overcome this issue, we proposed a data-independent acquisition method to facilitate highly generalizable signal processing and feature learning processes. This is achieved by enhancing random segmentation to avoid complicated fiducial feature extraction, along with auto-correlation to eliminate the phase difference due to random segmentation. Subsequently, a bidirectional recurrent neural network (RNN) with long short-term memory (LSTM) deep networks is utilized to automatically learn the features associated with the signal and to perform an authentication task. The experimental results suggest that the proposed data-independent approach using a BLSTM network achieves a relatively high classification accuracy for every dataset relative to the compared techniques. Moreover, it exhibited a significantly higher accuracy rate in experiments using ECG signals without the QRS complex. The results also revealed that data-dependent methods can only perform well for specified data types and amendments of data variations, whereas the presented approach can also be considered for generalization to other quasi-periodical biometric signal-based classification tasks in future studies.

scholarly journals Cystoscopic image classification by unsupervised feature learning and fusion of classifiers

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Seyyed Mohammad Reza Hashemi ◽  
Hamid Hassanpour ◽  
Ehsan Kozegar ◽  
Tao Tan
Keyword(s):  
Image Classification ◽  
Feature Learning ◽  
Unsupervised Feature Learning ◽  
Fusion Of Classifiers
Sign in / Sign up

Export Citation Format

Share Document