An Explainable Framework for Diagnosis of COVID-19 Pneumonia via Transfer Learning and Discriminant Correlation Analysis

2021 ◽  
Vol 17 (3s) ◽  
pp. 1-16
Author(s):  
Siyuan Lu ◽  
Di Wu ◽  
Zheng Zhang ◽  
Shui-Hua Wang
Keyword(s):  
Correlation Analysis ◽  
Feature Fusion ◽  
Classification Performance ◽  
Image Features ◽  
Image Feature ◽  
Functional Link ◽  
Image Representations ◽  
Learning Machine ◽  
Lung Window ◽  
Fold Cross Validation

The new coronavirus COVID-19 has been spreading all over the world in the last six months, and the death toll is still rising. The accurate diagnosis of COVID-19 is an emergent task as to stop the spreading of the virus. In this paper, we proposed to leverage image feature fusion for the diagnosis of COVID-19 in lung window computed tomography (CT). Initially, ResNet-18 and ResNet-50 were selected as the backbone deep networks to generate corresponding image representations from the CT images. Second, the representative information extracted from the two networks was fused by discriminant correlation analysis to obtain refined image features. Third, three randomized neural networks (RNNs): extreme learning machine, Schmidt neural network and random vector functional-link net, were trained using the refined features, and the predictions of the three RNNs were ensembled to get a more robust classification performance. Experiment results based on five-fold cross validation suggested that our method outperformed state-of-the-art algorithms in the diagnosis of COVID-19.

scholarly journals An Efficient and Lightweight Convolutional Neural Network for Remote Sensing Image Scene Classification

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 1999 ◽  
Author(s):  
Donghang Yu ◽  
Qing Xu ◽  
Haitao Guo ◽  
Chuan Zhao ◽  
Yuzhun Lin ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Convolutional Neural Network ◽  
Visual Recognition ◽  
Feature Fusion ◽  
Remote Sensing Image ◽  
Classification Performance ◽  
Image Features ◽  
Training Dataset ◽  
Scene Classification

Classifying remote sensing images is vital for interpreting image content. Presently, remote sensing image scene classification methods using convolutional neural networks have drawbacks, including excessive parameters and heavy calculation costs. More efficient and lightweight CNNs have fewer parameters and calculations, but their classification performance is generally weaker. We propose a more efficient and lightweight convolutional neural network method to improve classification accuracy with a small training dataset. Inspired by fine-grained visual recognition, this study introduces a bilinear convolutional neural network model for scene classification. First, the lightweight convolutional neural network, MobileNetv2, is used to extract deep and abstract image features. Each feature is then transformed into two features with two different convolutional layers. The transformed features are subjected to Hadamard product operation to obtain an enhanced bilinear feature. Finally, the bilinear feature after pooling and normalization is used for classification. Experiments are performed on three widely used datasets: UC Merced, AID, and NWPU-RESISC45. Compared with other state-of-art methods, the proposed method has fewer parameters and calculations, while achieving higher accuracy. By including feature fusion with bilinear pooling, performance and accuracy for remote scene classification can greatly improve. This could be applied to any remote sensing image classification task.

scholarly journals Wood Defect Detection Based on Depth Extreme Learning Machine

2020 ◽  
Vol 10 (21) ◽  
pp. 7488
Author(s):  
Yutu Yang ◽  
Xiaolin Zhou ◽  
Ying Liu ◽  
Zhongkang Hu ◽  
Fenglong Ding
Keyword(s):  
Deep Learning ◽  
Extreme Learning Machine ◽  
Defect Detection ◽  
Clustering Algorithm ◽  
Classification Performance ◽  
Image Features ◽  
Test Time ◽  
Machine Model ◽  
Feature Extraction Method ◽  
Learning Machine

The deep learning feature extraction method and extreme learning machine (ELM) classification method are combined to establish a depth extreme learning machine model for wood image defect detection. The convolution neural network (CNN) algorithm alone tends to provide inaccurate defect locations, incomplete defect contour and boundary information, and inaccurate recognition of defect types. The nonsubsampled shearlet transform (NSST) is used here to preprocess the wood images, which reduces the complexity and computation of the image processing. CNN is then applied to manage the deep algorithm design of the wood images. The simple linear iterative clustering algorithm is used to improve the initial model; the obtained image features are used as ELM classification inputs. ELM has faster training speed and stronger generalization ability than other similar neural networks, but the random selection of input weights and thresholds degrades the classification accuracy. A genetic algorithm is used here to optimize the initial parameters of the ELM to stabilize the network classification performance. The depth extreme learning machine can extract high-level abstract information from the data, does not require iterative adjustment of the network weights, has high calculation efficiency, and allows CNN to effectively extract the wood defect contour. The distributed input data feature is automatically expressed in layer form by deep learning pre-training. The wood defect recognition accuracy reached 96.72% in a test time of only 187 ms.

scholarly journals Coal quality prediction based on multi-feature fusion of flotation foam images

2020 ◽  
Author(s):  
yateng bai ◽  
xiaoping ma
Keyword(s):  
Real Time ◽  
Feature Fusion ◽  
Image Features ◽  
Image Feature ◽  
Coal Preparation ◽  
Coal Quality ◽  
Coal Flotation ◽  
Edge Operator ◽  
Occurrence Matrix

Abstract Coal flotation monitoring cannot provide real-time feedback on the yield and ash of coal preparation products because it is influenced by the subjective nature of artificial judgment of coal preparation status and the lag of product quality testing of coal preparation. This paper aims to extract the texture, colour and shape features of floating foam images using various image processing methods, such as colour space, wavelet transform, greyscale co-occurrence matrix and edge operator, and to quantify the characterisation of various characteristic parameters on the basis of the indicative effect of floating foam characteristics on the quality of coal preparation products. The correlation between image features and the yield and ash of flotation products is studied, and a regression prediction model of coal preparation yield and ash was established by combining various image feature parameters using machine learning methods. Experimental results show that the proposed method can realise the real-time monitoring of coal mine flotation and effectively predict coal quality.

scholarly journals Coal quality prediction based on multi-feature fusion of flotation foam images

2020 ◽  
Author(s):  
Yateng Bai ◽  
Xiaoping Ma
Keyword(s):  
Real Time ◽  
Feature Fusion ◽  
Image Features ◽  
Image Feature ◽  
Coal Preparation ◽  
Coal Quality ◽  
Coal Flotation ◽  
Edge Operator ◽  
Occurrence Matrix

Abstract Coal flotation monitoring cannot provide real-time feedback on the yield and ash of coal preparation products because it is influenced by the subjective nature of artificial judgment of coal preparation status and the lag of product quality testing of coal preparation. This paper aims to extract the texture, colour and shape features of floating foam images using various image processing methods, such as colour space, wavelet transform, greyscale co-occurrence matrix and edge operator, and to quantify the characterisation of various characteristic parameters on the basis of the indicative effect of floating foam characteristics on the quality of coal preparation products. The correlation between image features and the yield and ash of flotation products is studied, and a regression prediction model of coal preparation yield and ash was established by combining various image feature parameters using machine learning methods. Experimental results show that the proposed method can realise the real-time monitoring of coal mine flotation and effectively predict coal quality.

DISCRIMINATORY SPARSE CODING AND ITS APPLICATION TO FACE RECOGNITION

2003 ◽  
Vol 03 (03) ◽  
pp. 503-521
Author(s):  
JUN SUN ◽  
WENYUAN WANG ◽  
QING ZHUO ◽  
CHENGYUAN MA
Keyword(s):  
Feature Extraction ◽  
Sparse Coding ◽  
Recognition Performance ◽  
Classification Performance ◽  
Image Features ◽  
Face Image ◽  
Image Feature ◽  
Training Samples ◽  
The Subject ◽  
Independent Features

Feature extraction is very important in the subject of pattern recognition. Sparse coding is an approach for extracting the independent features of an image. The image features extracted by sparse coding have led to better recognition performance as compared to those from traditional PCA-based methods. A new discriminatory sparse coding (DSC) algorithm is proposed in this paper to further improve the classification performance. Based on reinforcement learning, DSC encodes the training samples by individual class rather than by individual image as in sparse coding. Having done that it will produce a set of features with large and small intraclass variations, which is very suitable for recognition tasks. Experiments are performed on face image feature extraction and recognition. Compared with the traditional PCA- and ICA-based methods, DSC shows a much better recognition performance.

Facial Expression Recognition Using Improved Canonical Correlation Analysis

2011 ◽  
Vol 255-260 ◽  
pp. 2183-2187
Author(s):  
Lei Gang ◽  
Zhang Yong
Keyword(s):  
Correlation Analysis ◽  
Facial Expression ◽  
Canonical Correlation Analysis ◽  
Canonical Correlation ◽  
Feature Fusion ◽  
Learning Algorithm ◽  
Recognition Rate ◽  
Image Features ◽  
Optimization Function ◽  
Multi Mode

Canonical Correlation Analysis (CCA) is a powerful multi-mode feature fusion method, but in traditional CCA, the optimization function is to find a pair of projections which make the mappings of the observations of the same pattern have the maximum correlation. It is an unsupervised subspace learning algorithm. This paper, we propose a Improved Canonical Correlation Analysis (ICCA) method which improves the optimization function by adopting the supervised relationships of the patterns belong to the same class. Our proposed algorithm is validated by the experiments on Jaffe facial expression database. Be compare with other methods, the recognition rate of our method is far higher than the PCA algorithm which only adopts single-mode image features and the traditional multi-mode CCA feature fusion algorithm.

scholarly journals Analysis of correlation based dimension reduction methods

2011 ◽  
Vol 21 (3) ◽  
pp. 549-558 ◽  
Author(s):  
Yong Shin ◽  
Cheong Park
Keyword(s):  
Correlation Analysis ◽  
Dimension Reduction ◽  
Canonical Correlation Analysis ◽  
Canonical Correlation ◽  
Feature Fusion ◽  
Orthogonal Transformation ◽  
Classification Performance ◽  
Class Label ◽  
Label Information ◽  
Reduction Methods

Analysis of correlation based dimension reduction methodsDimension reduction is an important topic in data mining and machine learning. Especially dimension reduction combined with feature fusion is an effective preprocessing step when the data are described by multiple feature sets. Canonical Correlation Analysis (CCA) and Discriminative Canonical Correlation Analysis (DCCA) are feature fusion methods based on correlation. However, they are different in that DCCA is a supervised method utilizing class label information, while CCA is an unsupervised method. It has been shown that the classification performance of DCCA is superior to that of CCA due to the discriminative power using class label information. On the other hand, Linear Discriminant Analysis (LDA) is a supervised dimension reduction method and it is known as a special case of CCA. In this paper, we analyze the relationship between DCCA and LDA, showing that the projective directions by DCCA are equal to the ones obtained from LDA with respect to an orthogonal transformation. Using the relation with LDA, we propose a new method that can enhance the performance of DCCA. The experimental results show that the proposed method exhibits better classification performance than the original DCCA.

High-resolution electron microscopy of the atomic structure of some grain boundaries in Au

1986 ◽  
Vol 44 ◽  
pp. 414-415
Author(s):  
W. Krakow ◽  
D. A. Smith
Keyword(s):  
Atomic Structure ◽  
High Resolution Electron Microscopy ◽  
Image Features ◽  
Image Feature ◽  
Resolution Electron ◽  
Tilt Boundaries ◽  
Processing Techniques ◽  
Atom Position ◽  
Structure Configuration

The successful determination of the atomic structure of [110] tilt boundaries in Au stems from the investigation of microscope performance at intermediate accelerating voltages (200 and 400kV) as well as a detailed understanding of how grain boundary image features depend on dynamical diffraction processes variation with specimen and beam orientations. This success is also facilitated by improving image quality by digital image processing techniques to the point where a structure image is obtained and each atom position is represented by a resolved image feature. Figure 1 shows an example of a low angle (∼10°) Σ = 129/[110] tilt boundary in a ∼250Å Au film, taken under tilted beam brightfield imaging conditions, to illustrate the steps necessary to obtain the atomic structure configuration from the image. The original image of Fig. 1a shows the regular arrangement of strain-field images associated with the cores of ½ [10] primary dislocations which are separated by ∼15Å.

Structural displacement and strain monitoring based on the edge detection operator

2016 ◽  
Vol 20 (2) ◽  
pp. 191-201 ◽  
Author(s):  
Wei Lu ◽  
Yan Cui ◽  
Jun Teng
Keyword(s):  
Edge Detection ◽  
Image Features ◽  
Image Feature ◽  
Monitoring Method ◽  
Strain Monitoring ◽  
Morphological Operator ◽  
Filtering Effect ◽  
Circular Target ◽  
Plane Displacement ◽  
The Cost

To decrease the cost of instrumentation for the strain and displacement monitoring method that uses sensors as well as considers the structural health monitoring challenges in sensor installation, it is necessary to develop a machine vision-based monitoring method. For this method, the most important step is the accurate extraction of the image feature. In this article, the edge detection operator based on multi-scale structure elements and the compound mathematical morphological operator is proposed to provide improved image feature extraction. The proposed method can not only achieve an improved filtering effect and anti-noise ability but can also detect the edge more accurately. Furthermore, the required image features (vertex of a square calibration board and centroid of a circular target) can be accurately extracted using the extracted image edge information. For validation, the monitoring tests for the structural local mean strain and in-plane displacement were designed accordingly. Through analysis of the error between the measured and calculated values of the structural strain and displacement, the feasibility and effectiveness of the proposed edge detection operator are verified.

Sign in / Sign up

Export Citation Format

Share Document