检索结果-内蒙古大学图书馆

Iranian Machine Vision and image processing (MVIP)

作者： Mohamad Ebrahim Aghili Hassan Ghassemian Maryam Imani Arani Image Processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

Hyperspectral anomaly detection is crucial for applications like aerial surveillance in remote sensing images. However, robust identification of anomalous pixels remains challenging. A novel spectral-spatial anomaly detection technique called Dual-Domain Autoencoders (DDA) is proposed to address these challenges. First, Nonnegative Matrix Factorization (NMF) is applied to decompose the hyperspectral data into anomaly and background components. Refinement of the designation is then done using intersection masking. Next, a spectral autoencoder is trained on identified background signature pixels and used to reconstruct the image. The reconstruction error highlights spectral anomalies. Furthermore, a spatial autoencoder is trained on principal component patches from likely background areas. Fused reconstruction error from the spectral and spatial autoencoders is finally used to give enhanced anomaly detection. Experiments demonstrate higher AUC for DDA over individual autoencoders and benchmark methods. The integration of matrix factorization and dual-domain, fused autoencoders thus provides superior anomaly identification. Spatial modeling further constrains the background, enabling accurate flagging of unusual local hyperspectral patterns. This study provides the effectiveness of employing autoencoders trained on intelligently sampled hyperspectral pixel signatures and spatial features for improved spectral-spatial anomaly detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of Heart Sounds Using Multi-Branch Deep Convolutional Network and LSTM-CNN

arXiv

引用

arXiv 2024年

作者： Latifi, Seyed Amir Ghassemian, Hassan Imani, Maryam Image Processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

This paper presents a fast and cost-effective method for diagnosing cardiac abnormalities with high accuracy and reliability using low-cost systems in clinics. The primary limitation of automatic diagnosing of cardiac diseases is the rarity of correct and acceptable lab.led samples, which can be expensive to prepare. Two methods are proposed to address this issue. The first method is a unique Multi-Branch Deep Convolutional Neural Network (MBDCN) architecture inspired by human auditory processing, specifically designed to optimize feature extraction by employing various sizes of convolutional filters and audio signal power spectrum as input. In the second method, called as Long short-term memory-Convolutional Neural (LSCN) model, Additionally, the network architecture includes Long Short-Term Memory (LSTM) network blocks to improve feature extraction in the time domain. The innovative approach of combining multiple parallel branches consisting of the one-dimensional convolutional layers along with LSTM blocks helps in achieving superior results in audio signal processing tasks. The experimental results demonstrate the superiority of the proposed methods over the state-of-the-art techniques. The overall classification accuracy of heart sounds with the LSCN network is more than 96%. The efficiency of this network is significant compared to common feature extraction methods such as Mel Frequency Cepstral Coefficients (MFCC) and wavelet transform. Therefore, the proposed method shows promising results in the automatic analysis of heart sounds and has potential applications in the diagnosis and early detection of cardiovascular diseases. © 2024, CC BY-NC-SA.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Contextual information Classification of Remotely Sensed images

Contextual Information Classification of Remotely Sensed Ima...

引用

International Conference on Pattern Recognition and image analysis (IPRIA)

作者： Alirza Dori Hassan Ghassemian Maryam Imani Image processing and Information Analysis Lab Faculty of Electrical and Computer Engineering TarbiatModares University Tehran Iran

This work proposes a multidisciplinary contextual information extraction and decision fusion approach for increasing the classification accuracy. It improves the image classification with integrating the results of various classifiers. The proposed method is implemented in three-steps: 1) contextual feature extraction using four different feature extractors methods: a) Gray Level Cooccurrence Matrix, b) Gabor filters, c) Laplacian Gaussian filters and d) Gaussian Derivatives Functions; 2) classification of contextual features using four different classification rules (ML, Tree, KNN and SVM) by using only 2% of data for training the classifiers; and 3) finally, decision fusion using six decision fusion rules. The experimental results on real remotely sensed images have been presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Change Detection in SAR images Using a Six-Branch CNN and Adaptive Window Approach

Unsupervised Change Detection in SAR Images Using a Six-Bran...

引用

Iranian Conference on electrical engineering (ICEE)

作者： Abbas Kakoolvand Maryam Imani Hassan Ghassemian Image processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

Change detection is one of the important and hot topics in remote sensing. Adaptive windowing approaches can preserve image details while reduce noise in the process of change detection. In the proposed method, two difference images (DIs) are obtained by using the adaptive window approach. Some fake lab.ls are provided from these DIs. Neural networks have a good performance in image processing. To use this advantage, a six-branch convolutional neural network (CNN) is trained using the fake lab.ls. Using these six branches with utilizing the adaptive windows, the network can preserve image detail while reduce noise. The proposed method based on three criteria (PCC, Kappa, and F1 score) has the best results in two datasets and has results close to the best method in other datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Empirical Mode Decomposition Based Morphological Profile For Hyperspectral image Classification

Empirical Mode Decomposition Based Morphological Profile For...

引用

International Conference on Pattern Recognition and image analysis (IPRIA)

作者： Kosar Amiri Maryam Imani Hassan Ghassemian Analysis Lab Faculty of Electrical and Computer Engineering Image processing and Information Tarbiat Modares University Tehran Iran

The empirical mode decomposition (EMD) based morphological profile (MP), called as EMDMP, is proposed for hyperspectral image classification in this work. The EMD algorithm can well decompose the nonlinear spectral feature vector to intrinsic components and the residual term. To extract the main spatial characteristics and shape structures, the closing operators are applied to the intrinsic components. In contrast, to extract details and more abstract contextual features, the opening operators are applied to the residual component. Finally, a multi-resolution morphological profile is provided with concatenation of the intrinsic components-based closing profile and residual component based opening profile. EMDMP achieves 96.54% overall accuracy compared to 95.15% obtained by convolutional neural network (CNN) on Indian dataset with 10 % training samples. In University of Pavia with 1% training samples, EMDMP results in 97.66% overall accuracy compared to 95.90% obtained by CNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Classification of Respiratory Sound and Lung Diseases

Feature Extraction and Classification of Respiratory Sound a...

引用

International Conference on Pattern Recognition and image analysis (IPRIA)

作者： Seyed Amir Latifi Hassan Ghassemian Maryam Imani Image processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

Bacteria, viruses, and fungi can cause respiratory infections. It is usually possible to detect respiratory diseases early by listening to the lung sounds with a stethoscope. In reality, lung sound analysis is a time-consuming and difficult task that depends on medical skills and recognition experience. Recent advances in automatic respiratory sound recognition and classification have attracted more attention. The outbreak of COVID-19 throughout the world and the high patient numbers have placed a great deal of pressure on medical professionals. A smart algorithm is therefore a necessity to provide a faster and more accurate detection of lung infections by automatically processing the sounds of the lungs. This paper proposes two new lung sound feature extraction, maximum entropy Gabor filter bank (MAGFB), and maximum entropy Mel filter bank (MAMFB). The classification is performed by a deep neural convolution network (DCNN) by using 50% of data for training the classifier. The filter banks have been substituted, instead of the convolutional layers. Experiments were conducted on the ICBHI 2017 Challenge dataset (with eight classes). The proposed method has a better performance compared to famous methods such as MFCC and Wavelet transform. Particularly, the performance of the second method is significant. For ICBHI 2017 challenge dataset, the overall accuracy of MFCC, Wavelet, MAGFB and MAMFB were 87%, 86%,90% and 93%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusion of Multi-Level CNN With LBP Features For Facial Emotion Recognition

Fusion of Multi-Level CNN With LBP Features For Facial Emoti...

引用

Iranian Conference on electrical engineering (ICEE)

作者： Ehsan Bahmanabady Maryam Imani Hassan Ghassemian Image processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

A facial emotion recognition framework is proposed in this work. The convolutional neural network (CNN) has high ability in extraction of hierarchical spatial features from low level texture characteristics to high level contextual features. A simple CNN model with three layers is suggested in this paper where the features extracted in all layers containing multi-level features are activated and used for classification. In addition, the local binary pattern (LBP) descriptor is used to extract discriminative features from the spatial structure of the input image. Therefore, four feature sources are provided by multi levels of CNN and the LBP descriptor. Each feature source is used for facial emotion recognition by applying to the support vector machine (SVM) classier. Finally, the majority voting rule is used for decision fusion to provide the final emotional lab.l of each given face image. The proposed method with 84% overall accuracy, 83% weighted F1-score and 81% kappa coefficient provides the best performance compared to LBP, multi-level CNN and two-dimensional principal component analysis (2DPCA) methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Spectral-Spatial Network for Feature Fusion and Classification of Hyperspectral images 7

A New Spectral-Spatial Network for Feature Fusion and Classi...

引用

7th International Conference on Signal processing and Intelligent Systems, ICSPIS 2021

作者： Aghili, Mohamad Ebrahim Ghassemian, Hassan Imani, Maryam Tarbiat Modares University Image Processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tehran Iran

ISBN: (纸本)9781665409384

Hyperspectral image (HSI) classification is one of the most important applications among all types of classification fields. Proper classification of spectral data leads to discovery of important land covers. In recent years, many methods have been introduced to increase the HSI classification accuracy. Methods based on neural networks show superior results compared to other methods. Among them, the two-dimensional convolutional neural networks (2D-CNNs) inspired by the human eye retina have achieved higher accuracy in classification. In most cases, HSI classifiers use only spectral features. In this paper, the spectral-spatial feature fusion and HSI classification using 2D-CNN are focused. For this purpose, the first 2D-convolutional layer of CNN is substituted by two combined 2D-Gabor-Shapelet filter banks. This layer extracts contextual information and provides valuable joint spectral-spatial features. The experimental results on real HSI (including the urban and agricultural areas and their mixture) show that the proposed method improves the overall classification performance. Compared to several famous HSI classification based on neural networks, the proposed method has higher speed and classification accuracy. © 2021 IEEE.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

Deep Curriculum Learning for PolSAR image Classification

arXiv

引用

arXiv 2021年

作者： Mousavi, Hamidreza Imani, Maryam Ghassemian, Hassan Image processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tehran Iran

Following the great success of curriculum learning in the area of machine learning, a novel deep curriculum learning method proposed in this paper, entitled DCL, particularly for the classification of fully polarimetric synthetic aperture radar (PolSAR) data. This method utilizes the entropy-alpha target decomposition method to estimate the degree of complexity of each PolSAR image patch before applying it to the convolutional neural network (CNN). Also, an accumulative mini-batch pacing function is used to introduce more difficult patches to CNN. Experiments on the widely used data set of AIRSAR Flevoland reveal that the proposed curriculum learning method can not only increase classification accuracy but also lead to faster training convergence. © 2021, CC BY.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

A Retina-Inspired Multiresolution analysis Framework for Pansharpening 1

A Retina-Inspired Multiresolution Analysis Framework for Pan...

引用

1st International Conference on Machine Vision and image processing, MVIP 2020

作者： Maneshi, Mehran Ghassemian, Hassan Khademi, Ghassem Imani, Maryam Tarbiat Modares University Image Processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tehran Iran

ISBN: (纸本)9781728168326

Technical limitations on the satellite sensors make a trade-off between the spectral and spatial resolution in remotely sensed images. To deal with this issue, pansharpening has been emerged to prepare a single image with the high spatial and spectral resolution, simultaneously. This paper presents a pansharpening approach based on the retina-inspired model and the multiresolution analysis (MRA) framework. The retina- inspired model is simplified by the difference of Gaussian (DoG) operator, and we apply it to the panchromatic image to extract the spatial details. Furthermore, the injection gains in the MRA framework are calculated through an iterative process where the gains at each iteration are updated based on the fusion result obtained from its previous iteration. To investigate the performance of the proposed model, it is compared with some classical pansharpening approaches with two data sets captured by the GeoEye-1 and Pléiades satellite imagery sensors. The experimental results show the proposed retina-inspired pansharpening method acts well in injecting the spatial information along with reducing the spectral distortion. © 2020 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：