scholarly journals Multiple Optical Sensor Fusion for Mineral Mapping of Core Samples

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3766
Author(s):  
Behnood Rasti ◽  
Pedram Ghamisi ◽  
Peter Seidel ◽  
Sandra Lorenz ◽  
Richard Gloaguen
Keyword(s):  
Feature Extraction ◽  
Sensor Fusion ◽  
Optical Sensor ◽  
Feature Fusion ◽  
Heterogeneous Data ◽  
Hyperspectral Data ◽  
Low Rank ◽  
Svm Classifier ◽  
Imaging Data ◽  
Rank Analysis

Geological objects are characterized by a high complexity inherent to a strong compositional variability at all scales and usually unclear class boundaries. Therefore, dedicated processing schemes are required for the analysis of such data for mineralogical mapping. On the other hand, the variety of optical sensing technology reveals different data attributes and therefore multi-sensor approaches are adapted to solve such complicated mapping problems. In this paper, we devise an adapted multi-optical sensor fusion (MOSFus) workflow which takes the geological characteristics into account. The proposed processing chain exhaustively covers all relevant stages, including data acquisition, preprocessing, feature fusion, and mineralogical mapping. The concept includes (i) a spatial feature extraction based on morphological profiles on RGB data with high spatial resolution, (ii) a specific noise reduction applied on the hyperspectral data that assumes mixed sparse and Gaussian contamination, and (iii) a subsequent dimensionality reduction using a sparse and smooth low rank analysis. The feature extraction approach allows one to fuse heterogeneous data at variable resolutions, scales, and spectral ranges and improve classification substantially. The last step of the approach, an SVM classifier, is robust to unbalanced and sparse training sets and is particularly efficient with complex imaging data. We evaluate the performance of the procedure with two different multi-optical sensor datasets. The results demonstrate the superiority of this dedicated approach over common strategies.

scholarly journals Feature Extraction and Fusion Using Deep Convolutional Neural Networks for Face Detection

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Xiaojun Lu ◽  
Xu Duan ◽  
Xiuping Mao ◽  
Yuanyuan Li ◽  
Xiangde Zhang
Keyword(s):  
Feature Extraction ◽  
Face Detection ◽  
Feature Fusion ◽  
Binary Classification ◽  
Recall Rate ◽  
Feature Representation ◽  
Svm Classifier ◽  
Computation Complexity ◽  
Average Precision ◽  
Deep Convolutional Neural Networks

This paper proposes a method that uses feature fusion to represent images better for face detection after feature extraction by deep convolutional neural network (DCNN). First, with Clarifai net and VGG Net-D (16 layers), we learn features from data, respectively; then we fuse features extracted from the two nets. To obtain more compact feature representation and mitigate computation complexity, we reduce the dimension of the fused features by PCA. Finally, we conduct face classification by SVM classifier for binary classification. In particular, we exploit offset max-pooling to extract features with sliding window densely, which leads to better matches of faces and detection windows; thus the detection result is more accurate. Experimental results show that our method can detect faces with severe occlusion and large variations in pose and scale. In particular, our method achieves 89.24% recall rate on FDDB and 97.19% average precision on AFW.

scholarly journals Multiscale Deep Spatial Feature Extraction Using Virtual RGB Image for Hyperspectral Imagery Classification

2020 ◽  
Vol 12 (2) ◽  
pp. 280 ◽  
Author(s):  
Liqin Liu ◽  
Zhenwei Shi ◽  
Bin Pan ◽  
Ning Zhang ◽  
Huanlin Luo ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Hyperspectral Image ◽  
Feature Fusion ◽  
Hyperspectral Data ◽  
Learning Technology ◽  
Learning Networks ◽  
Spatial Features ◽  
Training Samples ◽  
Rgb Image

In recent years, deep learning technology has been widely used in the field of hyperspectral image classification and achieved good performance. However, deep learning networks need a large amount of training samples, which conflicts with the limited labeled samples of hyperspectral images. Traditional deep networks usually construct each pixel as a subject, ignoring the integrity of the hyperspectral data and the methods based on feature extraction are likely to lose the edge information which plays a crucial role in the pixel-level classification. To overcome the limit of annotation samples, we propose a new three-channel image build method (virtual RGB image) by which the trained networks on natural images are used to extract the spatial features. Through the trained network, the hyperspectral data are disposed as a whole. Meanwhile, we propose a multiscale feature fusion method to combine both the detailed and semantic characteristics, thus promoting the accuracy of classification. Experiments show that the proposed method can achieve ideal results better than the state-of-art methods. In addition, the virtual RGB image can be extended to other hyperspectral processing methods that need to use three-channel images.

scholarly journals Low-Rank Linear Dynamical Systems for Motor Imagery EEG

2016 ◽  
Vol 2016 ◽  
pp. 1-7 ◽  
Author(s):  
Wenchang Zhang ◽  
Fuchun Sun ◽  
Chuanqi Tan ◽  
Shaobo Liu
Keyword(s):  
Feature Extraction ◽  
Dynamical Systems ◽  
Motor Imagery ◽  
Feature Fusion ◽  
Low Cost ◽  
Matrix Decomposition ◽  
Low Rank ◽  
Common Spatial Pattern ◽  
Decomposition Approach ◽  
Linear Dynamical Systems

The common spatial pattern (CSP) and other spatiospectral feature extraction methods have become the most effective and successful approaches to solve the problem of motor imagery electroencephalography (MI-EEG) pattern recognition from multichannel neural activity in recent years. However, these methods need a lot of preprocessing and postprocessing such as filtering, demean, and spatiospectral feature fusion, which influence the classification accuracy easily. In this paper, we utilize linear dynamical systems (LDSs) for EEG signals feature extraction and classification. LDSs model has lots of advantages such as simultaneous spatial and temporal feature matrix generation, free of preprocessing or postprocessing, and low cost. Furthermore, a low-rank matrix decomposition approach is introduced to get rid of noise and resting state component in order to improve the robustness of the system. Then, we propose a low-rank LDSs algorithm to decompose feature subspace of LDSs on finite Grassmannian and obtain a better performance. Extensive experiments are carried out on public dataset from “BCI Competition III Dataset IVa” and “BCI Competition IV Database 2a.” The results show that our proposed three methods yield higher accuracies compared with prevailing approaches such as CSP and CSSP.

scholarly journals Stacked Denoise Autoencoder Based Feature Extraction and Classification for Hyperspectral Images

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
Chen Xing ◽  
Li Ma ◽  
Xiaoquan Yang
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Activation Function ◽  
Hyperspectral Data ◽  
Fine Tuning ◽  
Support Vector ◽  
Svm Classifier ◽  
Nonlinear Properties ◽  
Feature Representations ◽  
High Level

Deep learning methods have been successfully applied to learn feature representations for high-dimensional data, where the learned features are able to reveal the nonlinear properties exhibited in the data. In this paper, deep learning method is exploited for feature extraction of hyperspectral data, and the extracted features can provide good discriminability for classification task. Training a deep network for feature extraction and classification includes unsupervised pretraining and supervised fine-tuning. We utilized stacked denoise autoencoder (SDAE) method to pretrain the network, which is robust to noise. In the top layer of the network, logistic regression (LR) approach is utilized to perform supervised fine-tuning and classification. Since sparsity of features might improve the separation capability, we utilized rectified linear unit (ReLU) as activation function in SDAE to extract high level and sparse features. Experimental results using Hyperion, AVIRIS, and ROSIS hyperspectral data demonstrated that the SDAE pretraining in conjunction with the LR fine-tuning and classification (SDAE_LR) can achieve higher accuracies than the popular support vector machine (SVM) classifier.

scholarly journals SPATIAL-SPECTRAL MORPHOLOGICAL FEATURE EXTRACTION FOR HYPERSPECTRAL IMAGES CLASSIFICATION

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 315-320
Author(s):  
M. Dowlatshah ◽  
H. Ghassemian ◽  
M. Imani
Keyword(s):  
Feature Extraction ◽  
Principal Component ◽  
Extraction Process ◽  
Hyperspectral Data ◽  
Svm Classifier ◽  
Morphological Filters ◽  
Structural Element ◽  
Binary Images ◽  
Remote Sensing Image Classification ◽  
Spatial Dependencies

Abstract. Remote sensing image classification is a method for labeling pixels to show the Land cover types. The ambiguity in the classification process can be reduced if the spatial dependencies, which exist among the adjacent pixels, are intelligently incorporated into the feature extraction process. One of the methods for spatial feature extraction is applying morphological filters. The basic idea of the morphological filters is comparison of structures within the image with a reference form called structural element. Four types of important morphological filters are included (dilation, erosion, opening, and closing) in this work. Opening morphological filter is used to extract spatial features where this filter is implemented by applying two successive sequences dilation and erosion operators. This filter removes the light areas smaller than the structural element in binary images; and in the gray level images, the areas smaller than the structural element and brighter than the neighboring regions are removed. Differential morphology filters are other important morphological filters, which are also used in this work. In the proposed method, the principal component analysis is used to reduce the data dimensions and an SVM classifier is applied to classify the hyperspectral data. The proposed method provides better classification results than the conventional morphological profile about 2%-5% for the University of Pavia and Pavia Center datasets. The results represent the good performance of the proposed method by using a small number of training samples.

scholarly journals Hyperspectral Feature Extraction Using Sparse and Smooth Low-Rank Analysis

2019 ◽  
Vol 11 (2) ◽  
pp. 121 ◽  
Author(s):  
Behnood Rasti ◽  
Pedram Ghamisi ◽  
Magnus Ulfarsson
Keyword(s):  
Feature Extraction ◽  
Total Variation ◽  
Low Rank ◽  
Support Vector ◽  
Feature Extraction Method ◽  
Rank Analysis ◽  
Vector Machines ◽  
Piecewise Smoothness ◽  
Orthogonality Constraint ◽  
New Type

In this paper, we develop a hyperspectral feature extraction method called sparse and smooth low-rank analysis (SSLRA). First, we propose a new low-rank model for hyperspectral images (HSIs) where we decompose the HSI into smooth and sparse components. Then, these components are simultaneously estimated using a nonconvex constrained penalized cost function (CPCF). The proposed CPCF exploits total variation penalty, ℓ 1 penalty, and an orthogonality constraint. The total variation penalty is used to promote piecewise smoothness, and, therefore, it extracts spatial (local neighborhood) information. The ℓ 1 penalty encourages sparse and spatial structures. Additionally, we show that this new type of decomposition improves the classification of the HSIs. In the experiments, SSLRA was applied on the Houston (urban) and the Trento (rural) datasets. The extracted features were used as an input into a classifier (either support vector machines (SVM) or random forest (RF)) to produce the final classification map. The results confirm improvement in classification accuracy compared to the state-of-the-art feature extraction approaches.

scholarly journals Dilated Semantic Segmentation for Breast Ultrasonic Lesion Detection Using Parallel Feature Fusion

Diagnostics ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1212
Author(s):  
Rizwana Irfan ◽  
Abdulwahab Ali Almazroi ◽  
Hafiz Tayyab Rauf ◽  
Robertas Damaševičius ◽  
Emad Abouel Nasr ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Feature Extraction ◽  
Transfer Learning ◽  
Death Rate ◽  
Feature Fusion ◽  
Semantic Segmentation ◽  
Lesion Detection ◽  
Support Vector ◽  
Svm Classifier ◽  
Feature Vectors

Breast cancer is becoming more dangerous by the day. The death rate in developing countries is rapidly increasing. As a result, early detection of breast cancer is critical, leading to a lower death rate. Several researchers have worked on breast cancer segmentation and classification using various imaging modalities. The ultrasonic imaging modality is one of the most cost-effective imaging techniques, with a higher sensitivity for diagnosis. The proposed study segments ultrasonic breast lesion images using a Dilated Semantic Segmentation Network (Di-CNN) combined with a morphological erosion operation. For feature extraction, we used the deep neural network DenseNet201 with transfer learning. We propose a 24-layer CNN that uses transfer learning-based feature extraction to further validate and ensure the enriched features with target intensity. To classify the nodules, the feature vectors obtained from DenseNet201 and the 24-layer CNN were fused using parallel fusion. The proposed methods were evaluated using a 10-fold cross-validation on various vector combinations. The accuracy of CNN-activated feature vectors and DenseNet201-activated feature vectors combined with the Support Vector Machine (SVM) classifier was 90.11 percent and 98.45 percent, respectively. With 98.9 percent accuracy, the fused version of the feature vector with SVM outperformed other algorithms. When compared to recent algorithms, the proposed algorithm achieves a better breast cancer diagnosis rate.

scholarly journals Time lapse synchrotron IR chemical imaging for observing the acclimation of a single algal cell to CO2 treatment

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ghazal Azarfar ◽  
Ebrahim Aboualizadeh ◽  
Simona Ratti ◽  
Camilla Olivieri ◽  
Alessandra Norici ◽  
...  
Keyword(s):  
Algal Cell ◽  
Principal Component ◽  
External Perturbation ◽  
Time Lapse ◽  
Chemical Imaging ◽  
Hyperspectral Data ◽  
Aqueous Environment ◽  
Ir Absorption ◽  
Imaging Data ◽  
Mid Infrared

AbstractAlgae are the main primary producers in aquatic environments and therefore of fundamental importance for the global ecosystem. Mid-infrared (IR) microspectroscopy is a non-invasive tool that allows in principle studying chemical composition on a single-cell level. For a long time, however, mid-infrared (IR) imaging of living algal cells in an aqueous environment has been a challenge due to the strong IR absorption of water. In this study, we employed multi-beam synchrotron radiation to measure time-resolved IR hyperspectral images of individual Thalassiosira weissflogii cells in water in the course of acclimation to an abrupt change of CO2 availability (from 390 to 5000 ppm and vice versa) over 75 min. We used a previously developed algorithm to correct sinusoidal interference fringes from IR hyperspectral imaging data. After preprocessing and fringe correction of the hyperspectral data, principal component analysis (PCA) was performed to assess the spatial distribution of organic pools within the algal cells. Through the analysis of 200,000 spectra, we were able to identify compositional modifications associated with CO2 treatment. PCA revealed changes in the carbohydrate pool (1200–950 cm$$^{-1}$$ - 1 ), lipids (1740, 2852, 2922 cm$$^{-1}$$ - 1 ), and nucleic acid (1160 and 1201 cm$$^{-1}$$ - 1 ) as the major response of exposure to elevated CO2 concentrations. Our results show a local metabolism response to this external perturbation.

scholarly journals Relative Total Variation Structure Analysis-Based Fusion Method for Hyperspectral and LiDAR Data Classification

2021 ◽  
Vol 13 (6) ◽  
pp. 1143
Author(s):  
Yinghui Quan ◽  
Yingping Tong ◽  
Wei Feng ◽  
Gabriel Dauphin ◽  
Wenjiang Huang ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Total Variation ◽  
Structure Analysis ◽  
Hyperspectral Image ◽  
Gabor Filter ◽  
Heterogeneous Data ◽  
Lidar Data ◽  
Fusion Method ◽  
Wide Range ◽  
Relative Total Variation

The fusion of the hyperspectral image (HSI) and the light detecting and ranging (LiDAR) data has a wide range of applications. This paper proposes a novel feature fusion method for urban area classification, namely the relative total variation structure analysis (RTVSA), to combine various features derived from HSI and LiDAR data. In the feature extraction stage, a variety of high-performance methods including the extended multi-attribute profile, Gabor filter, and local binary pattern are used to extract the features of the input data. The relative total variation is then applied to remove useless texture information of the processed data. Finally, nonparametric weighted feature extraction is adopted to reduce the dimensions. Random forest and convolutional neural networks are utilized to evaluate the fusion images. Experiments conducted on two urban Houston University datasets (including Houston 2012 and the training portion of Houston 2017) demonstrate that the proposed method can extract the structural correlation from heterogeneous data, withstand a noise well, and improve the land cover classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document