scholarly journals Deep Feature Fusion Based Dual Branch Network for X-ray Security Inspection Image Classification

2021 ◽  
Vol 11 (16) ◽  
pp. 7485
Author(s):  
Yingda Xu ◽  
Jianming Wei
Keyword(s):  
Computer Security ◽  
Network Architecture ◽  
Feature Fusion ◽  
Class Imbalance ◽  
Classification Performance ◽  
Fusion Model ◽  
X Ray ◽  
Deep Feature ◽  
Scanned Images ◽  
Security Inspection

Automatic computer security inspection of X-ray scanned images has an irresistible trend in modern life. Aiming to address the inconvenience of recognizing small-sized prohibited item objects, and the potential class imbalance within multi-label object classification of X-ray scanned images, this paper proposes a deep feature fusion model-based dual branch network architecture. Firstly, deep feature fusion is a method to fuse features extracted from several model layers. Specifically, it operates these features by upsampling and dimension reduction to match identical sizes, then fuses them by element-wise sum. In addition, this paper introduces focal loss to handle class imbalance. For balancing importance on samples of minority and majority class, it assigns weights to class predictions. Additionally, for distinguishing difficult samples from easy samples, it introduces modulating factor. Dual branch network adopts the two components above and integrates them in final loss calculation through the weighted sum. Experimental results illustrate that the proposed method outperforms baseline and state-of-art by a large margin on various positive/negative ratios of datasets. These demonstrate the competitivity of the proposed method in classification performance and its potential application under actual circumstances.

scholarly journals Cross-Modality Interaction Network for Equine Activity Recognition Using Imbalanced Multi-Modal Data

Sensors ◽  
2021 ◽  
Vol 21 (17) ◽  
pp. 5818
Author(s):  
Axiu Mao ◽  
Endai Huang ◽  
Haiming Gan ◽  
Rebecca S. V. Parkes ◽  
Weitao Xu ◽  
...  
Keyword(s):  
Activity Recognition ◽  
Network Architecture ◽  
Feature Fusion ◽  
Recognition Performance ◽  
Class Imbalance ◽  
Imbalanced Data ◽  
Interaction Network ◽  
Classification Performance ◽  
Sensor Data ◽  
Class Imbalance Problem

With the recent advances in deep learning, wearable sensors have increasingly been used in automated animal activity recognition. However, there are two major challenges in improving recognition performance—multi-modal feature fusion and imbalanced data modeling. In this study, to improve classification performance for equine activities while tackling these two challenges, we developed a cross-modality interaction network (CMI-Net) involving a dual convolution neural network architecture and a cross-modality interaction module (CMIM). The CMIM adaptively recalibrated the temporal- and axis-wise features in each modality by leveraging multi-modal information to achieve deep intermodality interaction. A class-balanced (CB) focal loss was adopted to supervise the training of CMI-Net to alleviate the class imbalance problem. Motion data was acquired from six neck-attached inertial measurement units from six horses. The CMI-Net was trained and verified with leave-one-out cross-validation. The results demonstrated that our CMI-Net outperformed the existing algorithms with high precision (79.74%), recall (79.57%), F1-score (79.02%), and accuracy (93.37%). The adoption of CB focal loss improved the performance of CMI-Net, with increases of 2.76%, 4.16%, and 3.92% in precision, recall, and F1-score, respectively. In conclusion, CMI-Net and CB focal loss effectively enhanced the equine activity classification performance using imbalanced multi-modal sensor data.

scholarly journals Dense Connectivity Based Two-Stream Deep Feature Fusion Framework for Aerial Scene Classification

2018 ◽  
Vol 10 (7) ◽  
pp. 1158 ◽  
Author(s):  
Yunlong Yu ◽  
Fuxian Liu
Keyword(s):  
Remote Sensing ◽  
Feature Fusion ◽  
Local Binary Patterns ◽  
Aerial Image ◽  
Great Success ◽  
Scene Classification ◽  
Fusion Model ◽  
Deep Architecture ◽  
Deep Feature ◽  
Training Samples

Aerial scene classification is an active and challenging problem in high-resolution remote sensing imagery understanding. Deep learning models, especially convolutional neural networks (CNNs), have achieved prominent performance in this field. The extraction of deep features from the layers of a CNN model is widely used in these CNN-based methods. Although the CNN-based approaches have obtained great success, there is still plenty of room to further increase the classification accuracy. As a matter of fact, the fusion with other features has great potential for leading to the better performance of aerial scene classification. Therefore, we propose two effective architectures based on the idea of feature-level fusion. The first architecture, i.e., texture coded two-stream deep architecture, uses the raw RGB network stream and the mapped local binary patterns (LBP) coded network stream to extract two different sets of features and fuses them using a novel deep feature fusion model. In the second architecture, i.e., saliency coded two-stream deep architecture, we employ the saliency coded network stream as the second stream and fuse it with the raw RGB network stream using the same feature fusion model. For sake of validation and comparison, our proposed architectures are evaluated via comprehensive experiments with three publicly available remote sensing scene datasets. The classification accuracies of saliency coded two-stream architecture with our feature fusion model achieve 97.79%, 98.90%, 94.09%, 95.99%, 85.02%, and 87.01% on the UC-Merced dataset (50% and 80% training samples), the Aerial Image Dataset (AID) (20% and 50% training samples), and the NWPU-RESISC45 dataset (10% and 20% training samples), respectively, overwhelming state-of-the-art methods.

Postoperative glioma segmentation in CT image using deep feature fusion model guided by multi-sequence MRIs

2019 ◽  
Vol 30 (2) ◽  
pp. 823-832 ◽  
Author(s):  
Fan Tang ◽  
Shujun Liang ◽  
Tao Zhong ◽  
Xia Huang ◽  
Xiaogang Deng ◽  
...  
Keyword(s):  
Feature Fusion ◽  
Ct Image ◽  
Fusion Model ◽  
Deep Feature

scholarly journals COVID-19 Detection from Chest X-ray Images Using Feature Fusion and Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1480
Author(s):  
Nur-A-Alam Alam ◽  
Mominul Ahsan ◽  
Md. Abdul Based ◽  
Julfikar Haider ◽  
Marcin Kowalski
Keyword(s):  
Deep Learning ◽  
Cross Validation ◽  
Feature Fusion ◽  
Extraction Methods ◽  
Classification Performance ◽  
Classification Model ◽  
Edge Preservation ◽  
X Ray ◽  
Testing Stage ◽  
Chest X Ray

Currently, COVID-19 is considered to be the most dangerous and deadly disease for the human body caused by the novel coronavirus. In December 2019, the coronavirus spread rapidly around the world, thought to be originated from Wuhan in China and is responsible for a large number of deaths. Earlier detection of the COVID-19 through accurate diagnosis, particularly for the cases with no obvious symptoms, may decrease the patient’s death rate. Chest X-ray images are primarily used for the diagnosis of this disease. This research has proposed a machine vision approach to detect COVID-19 from the chest X-ray images. The features extracted by the histogram-oriented gradient (HOG) and convolutional neural network (CNN) from X-ray images were fused to develop the classification model through training by CNN (VGGNet). Modified anisotropic diffusion filtering (MADF) technique was employed for better edge preservation and reduced noise from the images. A watershed segmentation algorithm was used in order to mark the significant fracture region in the input X-ray images. The testing stage considered generalized data for performance evaluation of the model. Cross-validation analysis revealed that a 5-fold strategy could successfully impair the overfitting problem. This proposed feature fusion using the deep learning technique assured a satisfactory performance in terms of identifying COVID-19 compared to the immediate, relevant works with a testing accuracy of 99.49%, specificity of 95.7% and sensitivity of 93.65%. When compared to other classification techniques, such as ANN, KNN, and SVM, the CNN technique used in this study showed better classification performance. K-fold cross-validation demonstrated that the proposed feature fusion technique (98.36%) provided higher accuracy than the individual feature extraction methods, such as HOG (87.34%) or CNN (93.64%).

Biological Gender Estimation from Panoramic Dental X-ray Images Based on Multiple Feature Fusion Model

2020 ◽  
Vol 21 (1) ◽  
Author(s):  
Wenchi Ke ◽  
Fei Fan ◽  
Peixi Liao ◽  
Yancun Lai ◽  
Qingsong Wu ◽  
...  
Keyword(s):  
Feature Fusion ◽  
Fusion Model ◽  
X Ray ◽  
Multiple Feature ◽  
Multiple Feature Fusion ◽  
Biological Gender

scholarly journals Deep Feature Fusion Model for Sentence Semantic Matching

2019 ◽  
Vol 61 (2) ◽  
pp. 601-616 ◽  
Author(s):  
Xu Zhang ◽  
Wenpeng Lu ◽  
Fangfang Li ◽  
Xueping Peng ◽  
Ruoyu Zhang
Keyword(s):  
Feature Fusion ◽  
Semantic Matching ◽  
Fusion Model ◽  
Deep Feature
Sign in / Sign up

Export Citation Format

Share Document