scholarly journals Classification of PolSAR Image Using Neural Nonlocal Stacked Sparse Autoencoders with Virtual Adversarial Regularization

2019 ◽  
Vol 11 (9) ◽  
pp. 1038 ◽  
Author(s):  
Ruichuan Wang ◽  
Yanfei Wang
Keyword(s):  
Spatial Information ◽  
Speckle Noise ◽  
Extraction Process ◽  
Negative Influence ◽  
Polarimetric Synthetic Aperture Radar ◽  
Softmax Classifier ◽  
Latent Space ◽  
Adversarial Training ◽  
Stacked Sparse Autoencoders

Polarimetric synthetic aperture radar (PolSAR) has become increasingly popular in the past two decades, for it can derive multichannel features of ground objects, which contains more discriminative information compared with traditional SAR. In this paper, a neural nonlocal stacked sparse autoencoders with virtual adversarial regularization (NNSSAE-VAT) is proposed for PolSAR image classification. The NNSSAE first extracts the nonlocal features by calculating pairwise similarity of each pixel and its surrounding pixels using a neural network, which contains a multiscale feature extractor and a linear embedding layer. The feature extraction process can relieve the negative influence of speckle noise and extract discriminative nonlocal spatial information without carefully designed parameters. Then, the SSAE maps the center pixel and the extracted nonlocal features into deep latent space in which a Softmax classifier is utilized to conduct classification. The virtual adversarial training is introduced to regularize the network, which tries to keep the network from being overfitting. The experimental results from three real PolSAR image show that the proposed NNSSAE-VAT method has proved its robustness and effectiveness and it can achieve competitive performance compared with related methods.

scholarly journals Auto Encoder Feature Learning with Utilization of Local Spatial Information and Data Distribution for Classification of PolSAR Image

2019 ◽  
Vol 11 (11) ◽  
pp. 1313
Author(s):  
Biao Hou ◽  
Jianlong Wang ◽  
Licheng Jiao ◽  
Shuang Wang
Keyword(s):  
Spatial Information ◽  
Data Distribution ◽  
Feature Learning ◽  
Classification Performance ◽  
Data Matrix ◽  
Post Processing ◽  
Softmax Classifier ◽  
Machine Learning Model ◽  
Processing Steps

The distribution of data plays a key role in the designing of a machine learning model. Therefore, this paper proposes a novel auto encoder network based on the distribution of polarimetric synthetic aperture radar (PolSAR) data matrix. Designed specifically for PolSAR data matrix, the proposed mixture auto encoder (MAE) feature learning method defines data error term in the loss function according to the data distribution. Instead of the pixel itself, all pixels in the neighborhood are used as input to train the proposed MAE. Then, a corresponding classification network is also given by discarding the decoder process of the proposed MAE and connecting with a Softmax classifier. The MAE is trained using the unlabeled data, while the training process of the classification network is completed with the help of a small number of labeled pixels. In view of the phenomenon of misclassification in the predicted result image, two post-processing steps acting on local spatial are also given, which accomplished by the proposed two filters. Extensive experiments by four methods were made over three real PolSAR images including the proposed classification network. The experimental results show that introducing data distribution into the auto encoder network leads to an average 4% improvement in overall accuracy for three PolSAR images. Moreover, the post-processing steps with the proposed filters bring a new level of discrimination on the classification performance of PolSAR images.

scholarly journals Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Network

2019 ◽  
Vol 11 (22) ◽  
pp. 2653 ◽  
Author(s):  
Yice Cao ◽  
Yan Wu ◽  
Peng Zhang ◽  
Wenkai Liang ◽  
Ming Li
Keyword(s):  
Image Classification ◽  
Spatial Information ◽  
Speckle Noise ◽  
Classification Performance ◽  
Feature Maps ◽  
Convolutional Network ◽  
Polarimetric Synthetic Aperture Radar ◽  
Initialization Scheme ◽  
Novel Complex ◽  
Complex Valued

Although complex-valued (CV) neural networks have shown better classification results compared to their real-valued (RV) counterparts for polarimetric synthetic aperture radar (PolSAR) classification, the extension of pixel-level RV networks to the complex domain has not yet thoroughly examined. This paper presents a novel complex-valued deep fully convolutional neural network (CV-FCN) designed for PolSAR image classification. Specifically, CV-FCN uses PolSAR CV data that includes the phase information and uses the deep FCN architecture that performs pixel-level labeling. The CV-FCN architecture is trained in an end-to-end scheme to extract discriminative polarimetric features, and then the entire PolSAR image is classified by the trained CV-FCN. Technically, for the particularity of PolSAR data, a dedicated complex-valued weight initialization scheme is proposed to initialize CV-FCN. It considers the distribution of polarization data to conduct CV-FCN training from scratch in an efficient and fast manner. CV-FCN employs a complex downsampling-then-upsampling scheme to extract dense features. To enrich discriminative information, multi-level CV features that retain more polarization information are extracted via the complex downsampling scheme. Then, a complex upsampling scheme is proposed to predict dense CV labeling. It employs the complex max-unpooling layers to greatly capture more spatial information for better robustness to speckle noise. The complex max-unpooling layers upsample the real and the imaginary parts of complex feature maps based on the max locations maps retained from the complex downsampling scheme. In addition, to achieve faster convergence and obtain more precise classification results, a novel average cross-entropy loss function is derived for CV-FCN optimization. Experiments on real PolSAR datasets demonstrate that CV-FCN achieves better classification performance than other state-of-art methods.

scholarly journals Semi-Supervised PolSAR Image Classification Based on Self-Training and Superpixels

2019 ◽  
Vol 11 (16) ◽  
pp. 1933 ◽  
Author(s):  
Yangyang Li ◽  
Ruoting Xing ◽  
Licheng Jiao ◽  
Yanqiao Chen ◽  
Yingte Chai ◽  
...  
Keyword(s):  
Image Classification ◽  
State Of The Art ◽  
Sample Selection ◽  
Spatial Relations ◽  
Speckle Noise ◽  
Classification Performance ◽  
Selection Strategy ◽  
Training Set ◽  
Polarimetric Synthetic Aperture Radar ◽  
Unlabeled Sample

Polarimetric synthetic aperture radar (PolSAR) image classification is a recent technology with great practical value in the field of remote sensing. However, due to the time-consuming and labor-intensive data collection, there are few labeled datasets available. Furthermore, most available state-of-the-art classification methods heavily suffer from the speckle noise. To solve these problems, in this paper, a novel semi-supervised algorithm based on self-training and superpixels is proposed. First, the Pauli-RGB image is over-segmented into superpixels to obtain a large number of homogeneous areas. Then, features that can mitigate the effects of the speckle noise are obtained using spatial weighting in the same superpixel. Next, the training set is expanded iteratively utilizing a semi-supervised unlabeled sample selection strategy that elaborately makes use of spatial relations provided by superpixels. In addition, a stacked sparse auto-encoder is self-trained using the expanded training set to obtain classification results. Experiments on two typical PolSAR datasets verified its capability of suppressing the speckle noise and showed excellent classification performance with limited labeled data.

scholarly journals Adversarial Attack and Defence through Adversarial Training and Feature Fusion for Diabetic Retinopathy Recognition

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3922
Author(s):  
Sheeba Lal ◽  
Saeed Ur Rehman ◽  
Jamal Hussain Shah ◽  
Talha Meraj ◽  
Hafiz Tayyab Rauf ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Feature Fusion ◽  
Speckle Noise ◽  
Fundus Images ◽  
Adversarial Examples ◽  
Adversarial Training ◽  
Adversarial Attack ◽  
Retinal Fundus Images ◽  
Attacks And Defenses ◽  
Retinal Fundus

Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the security and robustness of the deployed algorithms need to be guaranteed. The security susceptibility of the DL algorithms to adversarial examples has been widely acknowledged. The artificially created examples will lead to different instances negatively identified by the DL models that are humanly considered benign. Practical application in actual physical scenarios with adversarial threats shows their features. Thus, adversarial attacks and defense, including machine learning and its reliability, have drawn growing interest and, in recent years, has been a hot topic of research. We introduce a framework that provides a defensive model against the adversarial speckle-noise attack, the adversarial training, and a feature fusion strategy, which preserves the classification with correct labelling. We evaluate and analyze the adversarial attacks and defenses on the retinal fundus images for the Diabetic Retinopathy recognition problem, which is considered a state-of-the-art endeavor. Results obtained on the retinal fundus images, which are prone to adversarial attacks, are 99% accurate and prove that the proposed defensive model is robust.

IMPROVEMENT OF PUBLIC ADMINISTRATION OF INFORMATION FLOW MANAGEMENT BASED ON REFORMING THE TERRITORIAL ORGANIZATION OF POWER

2017 ◽  
Author(s):  
Andriy Stoyka ◽  
Keyword(s):  
Public Administration ◽  
Public Management ◽  
Information Technologies ◽  
Negative Influence ◽  
Information Support ◽  
Public Authorities ◽  
Effective Work ◽  
Territorial Organization ◽  
Concept Of Information

The article discusses the features of the introduction and use of modern information technologies in the management activities of state institutions. The role of the state in the regulation of information activities in the context of reforming the territorial organization of power has been clarified. The content and scope of the concept of "public management of information flows" has been determined, as well as the main tasks of ensuring information activities of public authorities. The classification of national interests in the information sphere according to their subjects has been carried out. The concept of information support in various scientific sources covering its purpose has been determined. Provided, the classification of management information according to certain categories. Tasks are proposed to overcome the negative influence of factors and ensure the effective work of state authorities of Ukraine in the field of information activities. Mechanisms for regulating the use of information potential in order to ensure the effective functioning of information policy in the field of public administration are given.

scholarly journals A Spatial-Temporal Adaptive Neighborhood-Based Ratio Approach for Change Detection in SAR Images

2018 ◽  
Vol 10 (8) ◽  
pp. 1295 ◽  
Author(s):  
Huifu Zhuang ◽  
Hongdong Fan ◽  
Kazhong Deng ◽  
Guobiao Yao
Keyword(s):  
Change Detection ◽  
Window Size ◽  
Speckle Noise ◽  
Adaptive Strategy ◽  
Negative Influence ◽  
Sar Images ◽  
Spatial Homogeneity ◽  
Difference Image ◽  
Negative Effect ◽  
Adaptive Neighborhood

The neighborhood-based method was proposed and widely used in the change detection of synthetic aperture radar (SAR) images because the neighborhood information of SAR images is effective to reduce the negative effect of speckle noise. Nevertheless, for the neighborhood-based method, it is unreasonable to use a fixed window size for the entire image because the optimal window size of different pixels in an image is different. Hence, if you let the neighborhood-based method use a large window to significantly suppress noise, it cannot preserve the detail information such as the edge of a changed area. To overcome this drawback, we propose a spatial-temporal adaptive neighborhood-based ratio (STANR) approach for change detection in SAR images. STANR employs heterogeneity to adaptively select the spatial homogeneity neighborhood and uses the temporal adaptive strategy to determine multi-temporal neighborhood windows. Experimental results on two data sets show that STANR can both suppress the negative influence of noise and preserve edge details, and can obtain a better difference image than other state-of-the-art methods.

scholarly journals Image Retrieval Using Data Mining Technique

2020 ◽  
pp. 2115-2125
Author(s):  
Sarmad T. Abdul-Samad ◽  
Sawsan Kamal
Keyword(s):  
Image Retrieval ◽  
User Satisfaction ◽  
Clustering Algorithm ◽  
Retrieval System ◽  
Spatial Information ◽  
Search Space ◽  
Extraction Process ◽  
Retrieval Process ◽  
Data Mining Technique ◽  
Image Retrieval System

Even though image retrieval is considered as one of the most important research areas in the last two decades, there is still room for improvement since it is still not satisfying for many users. Two of the major problems which need to be improved are the accuracy and the speed of the image retrieval system, in order to achieve user satisfaction and also to make the image retrieval system suitable for all platforms. In this work, the proposed retrieval system uses features with spatial information to analyze the visual content of the image. Then, the feature extraction process is followed by applying the fuzzy c-means (FCM) clustering algorithm to reduce the search space and speed up the retrieval process. The experimental results show that using the spatial features increases the system accuracy and that the clustering algorithm speeds up the image retrieval process. This shows that the proposed system works with texture and non-texture images.  

scholarly journals Artificial Intelligence Framework for Efficient Detection and Classification of Pneumonia Using Chest Radiography Images

2021 ◽  
Author(s):  
Ali Mohammad Alqudah ◽  
Shoroq Qazan ◽  
Ihssan S. Masad
Keyword(s):  
Artificial Intelligence ◽  
Input Image ◽  
Image Size ◽  
X Ray ◽  
Softmax Classifier ◽  
Non Invasive ◽  
Efficient Detection ◽  
X Ray Imaging ◽  
Chest X Ray

Abstract BackgroundChest diseases are serious health problems that threaten the lives of people. The early and accurate diagnosis of such diseases is very crucial in the success of their treatment and cure. Pneumonia is one of the most widely occurred chest diseases responsible for a high percentage of deaths especially among children. So, detection and classification of pneumonia using the non-invasive chest x-ray imaging would have a great advantage of reducing the mortality rates.ResultsThe results showed that the best input image size in this framework was 64 64 based on comparison between different sizes. Using CNN as a deep features extractor and utilizing the 10-fold methodology the propose artificial intelligence framework achieved an accuracy of 94% for SVM and 93.9% for KNN, a sensitivity of 93.33% for SVM and 93.19% for KNN and a specificity of 96.68% for SVM and 96.60% for KNN.ConclusionsIn this study, an artificial intelligence framework has been proposed for the detection and classification of pneumonia based on chest x-ray imaging with different sizes of input images. The proposed methodology used CNN for features extraction that were fed to two different types of classifiers, namely, SVM and KNN; in addition to the SoftMax classifier which is the default CNN classifier. The proposed CNN has been trained, validated, and tested using a large dataset of chest x-ray images contains in total 5852 images.

Sign in / Sign up

Export Citation Format

Share Document