Search

As a popular technique for swapping faces with someone else's in images or videos through deep neural networks, deepfake causes a serious threat to the security of multimedia content today. However, because counterfeit images are usually compressed when propagating over the Internet, and because the compression factor used is unknown, most of the existing deepfake detection models have poor robustness for the detection of compressed images with unknown compression factors. To solve this problem, we notice that an image has a high similarity with its compressed image based on symmetry, and this similarity is not easily affected by the compression factor, so this similarity feature can be used as an important clue for compressed deepfake detection. A TCNSC (Two-branch Convolutional Networks with Similarity and Classifier) method that combines compression factor independence is proposed in this paper. The TCNSC method learns two feature representations from the deepfake image, i.e., similarity of the image and its compressed counterpart and authenticity of the deepfake image. A joint training strategy is then utilized for feature extraction, in which the similarity characteristics are obtained by similarity learning while obtaining authenticity characteristics, so the proposed TCNSC model is trained for robust feature learning. Experimental results on the FaceForensics++ (FF++) dataset show that the proposed method significantly outperforms all competing methods under three compression settings of high-quality (HQ), medium-quality (MQ), and low-quality (LQ). For the LQ, MQ, and HQ settings, TCNSC achieves 91.8%, 93.4%, and 95.3% in accuracy, and outperforms the state-of-art method (Xception-RAW) by 16.9%, 10.1%, and 4.1%, respectively. [ABSTRACT FROM AUTHOR]

Currently, deep-learning-based methods have been widely used in fault diagnosis to improve the diagnosis efficiency and intelligence. However, most schemes require a great deal of labeled data and many iterations for training parameters. They suffer from low accuracy and over fitting under the few-shot scenario. In addition, a large number of parameters in the model consumes high computing resources, which is far from practical. In this paper, a multi-scale and lightweight Siamese network architecture is proposed for the fault diagnosis with few samples. The architecture proposed contains two main modules. The first part implements the feature vector extraction of sample pairs. It is composed of two lightweight convolutional networks with shared weights symmetrically. Multi-scale convolutional kernels and dimensionality reduction are used in these two symmetric networks to improve feature extraction and reduce the total number of model parameters. The second part takes charge of calculating the similarity of two feature vectors to achieve fault classification. The proposed network is validated by multiple datasets with different loads and speeds. The results show that the model has better accuracy, fewer model parameters and a scale compared to the baseline approach through our experiments. Furthermore, the model is also proven to have good generalization capability. [ABSTRACT FROM AUTHOR]

The accurate segmentation of retinal images is a basic step in screening for retinopathy and glaucoma. Most existing retinal image segmentation methods have insufficient feature information extraction. They are susceptible to the impact of the lesion area and poor image quality, resulting in the poor recovery of contextual information. This also causes the segmentation results of the model to be noisy and low in accuracy. Therefore, this paper proposes a multi-scale and multi-branch convolutional neural network model (multi-scale and multi-branch network (MSMB-Net)) for retinal image segmentation. The model uses atrous convolution with different expansion rates and skip connections to reduce the loss of feature information. Receiving domains of different sizes captures global context information. The model fully integrates shallow and deep semantic information and retains rich spatial information. The network embeds an improved attention mechanism to obtain more detailed information, which can improve the accuracy of segmentation. Finally, the method of this paper was validated on the fundus vascular datasets, DRIVE, STARE and CHASE datasets, with accuracies/F1 of 0.9708/0.8320, 0.9753/0.8469 and 0.9767/0.8190, respectively. The effectiveness of the method in this paper was further validated on the optic disc visual cup DRISHTI-GS1 dataset with an accuracy/F1 of 0.9985/0.9770. Experimental results show that, compared with existing retinal image segmentation methods, our proposed method has good segmentation performance in all four benchmark tests. [ABSTRACT FROM AUTHOR]

Deep learning has been successfully applied to classification tasks in many fields due to its good performance in learning discriminative features. However, the application of deep learning to printing defect classification is very rare, and there is almost no research on the classification method for printing defects with imbalanced samples. In this paper, we present a deep convolutional neural network model to extract deep features directly from printed image defects. Furthermore, considering the asymmetry in the number of different types of defect samples—that is, the number of different kinds of defect samples is unbalanced—seven types of over-sampling methods were investigated to determine the best method. To verify the practical applications of the proposed deep model and the effectiveness of the extracted features, a large dataset of printing detect samples was built. All samples were collected from practical printing products in the factory. The dataset includes a coarse-grained dataset with four types of printing samples and a fine-grained dataset with eleven types of printing samples. The experimental results show that the proposed deep model achieves a 96.86% classification accuracy rate on the coarse-grained dataset without adopting over-sampling, which is the highest accuracy compared to the well-known deep models based on transfer learning. Moreover, by adopting the proposed deep model combined with the SVM-SMOTE over-sampling method, the accuracy rate is improved by more than 20% in the fine-grained dataset compared to the method without over-sampling. [ABSTRACT FROM AUTHOR]

To monitor the tool wear state of computerized numerical control (CNC) machining equipment in real time in a manufacturing workshop, this paper proposes a real-time monitoring method based on a fusion of a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) network with an attention mechanism (CABLSTM). In this method, the CNN is used to extract deep features from the time-series signal as an input, and then the BiLSTM network with a symmetric structure is constructed to learn the time-series information between the feature vectors. The attention mechanism is introduced to self-adaptively perceive the network weights associated with the classification results of the wear state and distribute the weights reasonably. Finally, the signal features of different weights are sent to a Softmax classifier to classify the tool wear state. In addition, a data acquisition experiment platform is developed with a high-precision CNC milling machine and an acceleration sensor to collect the vibration signals generated during tool processing in real time. The original data are directly fed into the depth neural network of the model for analysis, which avoids the complexity and limitations caused by a manual feature extraction. The experimental results show that, compared with other deep learning neural networks and traditional machine learning network models, the model can predict the tool wear state accurately in real time from original data collected by sensors, and the recognition accuracy and generalization have been improved to a certain extent. [ABSTRACT FROM AUTHOR]

A number of researchers prefer using multi-channel surface electromyography (sEMG) pattern recognition in hand gesture recognition to increase classification accuracy. Using this method can lead to computational complexity. Hand gesture classification by employing single channel sEMG signal acquisition is quite challenging, especially for low-rate sampling frequency. In this paper, a study on the pattern recognition method for sEMG signals of nine finger movements is presented. Common surface single channel electromyography (sEMG) was used to measure five different subjects with no neurological or muscular disorder by having nine hand movements. This research had several sequential processes (i.e., feature extraction, feature reduction, and feature classification). Sixteen time-domain features were employed for feature extraction. The features were then reduced using principal component analysis (PCA) into two and three-dimensional feature space. The artificial neural network (ANN) classifier was tested on two different feature sets: (1) using all principal components obtained from PCA (PC1–PC3) and (2) using selected principal components (PC2 and PC3). The third best principal components were then used for classification using ANN. The average accuracy using all subject signals was 86.7% to discriminate the nine finger movements. [ABSTRACT FROM AUTHOR]

Person re-identification is the task of matching pedestrian images across a network of non-overlapping camera views. It poses aggregated challenges resulted from random human pose, clutter from the background, illumination variations, and other factors. There has been a vast number of studies in recent years with promising success. However, key challenges have not been adequately addressed and continue to result in sub-optimal performance. Attention-based person re-identification gains more popularity in identifying discriminatory features from person images. Its potential in terms of extracting features common to a pair of person images across the feature extraction pipeline has not been be fully exploited. In this paper, we propose a novel attention-based Siamese network driven by a mutual-attention module decomposed into spatial and channel components. The proposed mutual-attention module not only leads feature extraction to the discriminative part of individual images, but also fuses mutual features symmetrically across pairs of person images to get informative regions common to both input images. Our model simultaneously learns feature embedding for discriminative cues and the similarity measure. The proposed model is optimized with multi-task loss, namely classification and verification loss. It is further optimized by a learnable mutual-attention module to facilitate an efficient and adaptive learning. The proposed model is thoroughly evaluated on extensively used large-scale datasets, Market-1501 and Duke-MTMC-ReID. Our experimental results show competitive results with the state-of-the-art works and the effectiveness of the mutual-attention module. [ABSTRACT FROM AUTHOR]

Person re-identification (Re-ID) is a non-overlapping multi-camera retrieval task to match different images of the same person, and it has become a hot research topic in many fields, such as surveillance security, criminal investigation, and video analysis. As one kind of important architecture for person re-identification, Siamese networks usually adopt standard softmax loss function, and they can only obtain the global features of person images, ignoring the local features and the large margin for classification. In this paper, we design a novel symmetric Siamese network model named Siamese Multiple Granularity Network (SMGN), which can jointly learn the large margin multiple granularity features and similarity metrics for person re-identification. Firstly, two branches for global and local feature extraction are designed in the backbone of the proposed SMGN model, and the extracted features are concatenated together as multiple granularity features of person images. Then, to enhance their discriminating ability, the multiple channel weighted fusion (MCWF) loss function is constructed for the SMGN model, which includes the verification loss and identification loss of the training image pair. Extensive comparative experiments on four benchmark datasets (CUHK01, CUHK03, Market-1501 and DukeMTMC-reID) show the effectiveness of our proposed method and its performance outperforms many state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Ear recognition is an active research area in the biometrics community with the ultimate goal to recognize individuals effectively from ear images. Traditional ear recognition methods based on handcrafted features and conventional machine learning classifiers were the prominent techniques during the last two decades. Arguably, feature extraction is the crucial phase for the success of these methods due to the difficulty in designing robust features to cope with the variations in the given images. Currently, ear recognition research is shifting towards features extracted by Convolutional Neural Networks (CNNs), which have the ability to learn more specific features robust to the wide image variations and achieving state-of-the-art recognition performance. This paper presents and compares ear recognition models built with handcrafted and CNN features. First, we experiment with seven top performing handcrafted descriptors to extract the discriminating ear image features and then train Support Vector Machines (SVMs) on the extracted features to learn a suitable model. Second, we introduce four CNN based models using a variant of the AlexNet architecture. The experimental results on three ear datasets show the superior performance of the CNN based models by 22%. To further substantiate the comparison, we perform visualization of the handcrafted and CNN features using the t-distributed Stochastic Neighboring Embedding (t-SNE) visualization technique and the characteristics of features are discussed. Moreover, we conduct experiments to investigate the symmetry of the left and right ears and the obtained results on two datasets indicate the existence of a high degree of symmetry between the ears, while a fair degree of asymmetry also exists. [ABSTRACT FROM AUTHOR]

In the process of knowledge graph construction, entity linking is a pivotal step, which maps mentions in text to a knowledge base. Existing models only utilize individual information to represent their latent features and ignore the correlation between entities and their mentions. Besides, in the process of entity feature extraction, only partial latent features, i.e., context features, are leveraged to extract latent features, and the pivotal entity structural features are ignored. In this paper, we propose SA-ESF, which leverages the symmetrical Bi-LSTM neural network with the double attention mechanism to calculate the correlation between mentions and entities in two aspects: (1) entity embeddings and mention context features; (2) mention embeddings and entity description features; furthermore, the context features, structural features, and entity ID feature are integrated to represent entity embeddings jointly. Finally, we leverage (1) the similarity score between each mention and its candidate entities and (2) the prior probability to calculate the final ranking results. The experimental results on nine benchmark dataset validate the performance of SA-ESF where the average F1 score is up to 0.866. [ABSTRACT FROM AUTHOR]

Because the existing methods extract the signal characteristics of electronic communication networks, there is a problem of poor extraction. In this paper, a feature extraction method based on symmetric algorithm for transmission signals in electronic communication networks is proposed. The transmission signal in the time domain is decomposed by three-layer wavelet packet decomposition through threshold denoising and data dimension reduction. The adaptive floating threshold is used as a threshold to quantify the wavelet coefficients of the signal, which can effectively remove noise while retaining valuable transmission signal. Secondly, the feature extraction algorithm based on symmetric Holder coefficient is used to transform the transmitted signal from time domain to frequency domain, identify the signal sequence, and classify the signal sequence using neural network classifier. The simulation results show that the proposed method can extract the transmission signal of electronic communication network with the highest accuracy of 98.21%. This method can extract the amplitude and frequency characteristics of the transmission signal accurately under strong vibration environment. It is an efficient method for feature extraction of transmission signal. [ABSTRACT FROM AUTHOR]

Fundus vessel analysis is a significant tool for evaluating the development of retinal diseases such as diabetic retinopathy and hypertension in clinical practice. Hence, automatic fundus vessel segmentation is essential and valuable for medical diagnosis in ophthalmopathy and will allow identification and extraction of relevant symmetric and asymmetric patterns. Further, due to the uniqueness of fundus vessel, it can be applied in the field of biometric identification. In this paper, we remold fundus vessel segmentation as a task of pixel-wise classification task, and propose a novel coarse-to-fine fully convolutional neural network (CF-FCN) to extract vessels from fundus images. Our CF-FCN is aimed at making full use of the original data information and making up for the coarse output of the neural network by harnessing the space relationship between pixels in fundus images. Accompanying with necessary pre-processing and post-processing operations, the efficacy and efficiency of our CF-FCN is corroborated through our experiments on DRIVE, STARE, HRF and CHASE DB1 datasets. It achieves sensitivity of 0.7941, specificity of 0.9870, accuracy of 0.9634 and Area Under Receiver Operating Characteristic Curve (AUC) of 0.9787 on DRIVE datasets, which surpasses the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Tuberculosis is curable, still the world's second inflectional murderous disease, and ranked 13th (in 2020) by the World Health Organization on the list of leading death causes. One of the reasons for its fatality is the unavailability of modern technology and human experts for early detection. This study represents a precise and reliable machine vision-based approach for Tuberculosis detection in the lung through Symmetry CT scan images. TB spreads irregularly, which means it might not affect both lungs equally, and it might affect only some part of the lung. That's why regions of interest (ROI's) from TB infected and normal CT scan images of lungs were selected after pre-processing i.e., selection/cropping, grayscale image conversion, and filtration, Statistical texture features were extracted, and 30 optimized features using F (Fisher) + PA (probability of error + average correlation) + MI (mutual information) were selected for final optimization and only 6 most optimized features were selected. Several supervised learning classifiers were used to classify between normal and infected TB images. Artificial Neural Network (ANN: n class) based classifier Multi-Layer Perceptron (MLP) showed comparatively better and probably best accuracy of 99% with execution time of less than a second, followed by Random Forest 98.83%, J48 98.67%, Log it Boost 98%, AdaBoostM1 97.16% and Bayes Net 96.83%. [ABSTRACT FROM AUTHOR]

Artificial intelligence is widely applied to automate Diabetic retinopathy diagnosis. Diabetes-related retinal vascular disease is one of the world's most common leading causes of blindness and vision impairment. Therefore, automated DR detection systems would greatly benefit the early screening and treatment of DR and prevent vision loss caused by it. Researchers have proposed several systems to detect abnormalities in retinal images in the past few years. However, Diabetic Retinopathy automatic detection methods have traditionally been based on hand-crafted feature extraction from the retinal images and using a classifier to obtain the final classification. DNN (Deep neural networks) have made several changes in the previous few years to assist overcome the problem mentioned above. We suggested a two-stage novel approach for automated DR classification in this research. Due to the low fraction of positive instances in the asymmetric Optic Disk (OD) and blood vessels (BV) detection system, preprocessing and data augmentation techniques are used to enhance the image quality and quantity. The first step uses two independent U-Net models for OD (optic disc) and BV (blood vessel) segmentation. In the second stage, the symmetric hybrid CNN-SVD model was created after preprocessing to extract and choose the most discriminant features following OD and BV extraction using Inception-V3 based on transfer learning, and detects DR by recognizing retinal biomarkers such as MA (microaneurysms), HM (hemorrhages), and exudates (EX). On EyePACS-1, Messidor-2, and DIARETDB0, the proposed methodology demonstrated state-of-the-art performance, with an average accuracy of 97.92%, 94.59%, and 93.52%, respectively. Extensive testing and comparisons with baseline approaches indicate the efficacy of the suggested methodology. [ABSTRACT FROM AUTHOR]

With the continuous improvement in oral health awareness, people's demand for oral health diagnosis has also increased. Dental object detection is a key step in automated dental diagnosis; however, because of the particularity of medical data, researchers usually cannot obtain sufficient medical data. Therefore, this study proposes a dental object detection method for small-size datasets based on teeth semantics, structural information feature extraction, and an a priori knowledge migration, called a segmentation, points, segmentation, and classification network (SPSC-NET). In the region of interest area extraction method, the SPSC-NET method converts the teeth X-ray image into an a priori knowledge information image, composed of the edges of the teeth and the semantic segmentation image; the network structure used to extract the a priori knowledge information is a symmetric structure, which then generates the key points of the object instance. Next, it uses the key points of the object instance (i.e., the dental semantic segmentation image and the dental edge image) to obtain the object instance image (i.e., the positioning of the teeth). Using 10 training images, the test precision and recall rate of the tooth object center point of the SPSC-NET method were between 99–100%. In the classification method, the SPSC-NET identified the single instance segmentation image generated by migrating the dental object area, the edge image, and the semantic segmentation image as a priori knowledge. Under the premise of using the same deep neural network classification model, the model classification with a priori knowledge was 20% more accurate than the ordinary classification methods. For the overall object detection performance indicators, the SPSC-NET's average precision (AP) value was more than 92%, which is better than that of the transfer-based faster region-based convolutional neural network (Faster-RCNN) object detection model; moreover, its AP and mean intersection-over-union (mIOU) were 14.72% and 19.68% better than the transfer-based Faster-CNN model, respectively. [ABSTRACT FROM AUTHOR]

With the development of 3D printing, weapons are easily printed without any restriction from the production managers. Therefore, anti-3D weapon model detection is necessary issue in safe 3D printing to prevent the printing of 3D weapon models. In this paper, we would like to propose an anti-3D weapon model detection algorithm to prevent the printing of anti-3D weapon models for safe 3D printing based on the D2 shape distribution and an improved convolutional neural networks (CNNs). The purpose of the proposed algorithm is to detect anti-3D weapon models when they are used in 3D printing. The D2 shape distribution is computed from random points on the surface of a 3D weapon model and their geometric features in order to construct a D2 vector. The D2 vector is then trained by improved CNNs. The CNNs are used to detect anti-3D weapon models for safe 3D printing by training D2 vectors which have been constructed from the D2 shape distribution of 3D weapon models. Experiments with 3D weapon models proved that the D2 shape distribution of 3D weapon models in the same class is the same. Training and testing results also verified that the accuracy of the proposed algorithm is higher than the conventional works. The proposed algorithm is applied in a small application, and it could detect anti-3D weapon models for safe 3D printing. [ABSTRACT FROM AUTHOR]

When identifying the key features of the network intrusion signal based on the GA-RBF algorithm (using the genetic algorithm to optimize the radial basis) to identify the key features of the network intrusion signal, the pre-processing process of the network intrusion signal data is neglected, resulting in an increase in network signal data noise, reducing the accuracy of key feature recognition. Therefore, a key feature recognition algorithm for network intrusion signals based on neural network and support vector machine is proposed. The principal component neural network (PCNN) is used to extract the characteristics of the network intrusion signal and the support vector machine multi-classifier is constructed. The feature extraction result is input into the support vector machine classifier. Combined with PCNN and SVM (Support Vector Machine) algorithms, the key features of network intrusion signals are identified. The experimental results show that the algorithm has the advantages of high precision, low false positive rate and the recognition time of key features of R2L (it is a common way of network intrusion attack) data set is only 3.18 ms. [ABSTRACT FROM AUTHOR]

Recently, real-time human age estimation based on facial images has been applied in various areas. Underneath this phenomenon lies an awareness that age estimation plays an important role in applying big data to target marketing for age groups, product demand surveys, consumer trend analysis, etc. However, in a real-world environment, various optical and motion blurring effects can occur. Such effects usually cause a problem in fully capturing facial features such as wrinkles, which are essential to age estimation, thereby degrading accuracy. Most of the previous studies on age estimation were conducted for input images almost free from blurring effect. To overcome this limitation, we propose the use of a deep ResNet-152 convolutional neural network for age estimation, which is robust to various optical and motion blurring effects of visible light camera sensors. We performed experiments with various optical and motion blurred images created from the park aging mind laboratory (PAL) and craniofacial longitudinal morphological face database (MORPH) databases, which are publicly available. According to the results, the proposed method exhibited better age estimation performance than the previous methods. [ABSTRACT FROM AUTHOR]