Multiple linear feature detection based on multiple-structuring-element center-surround top-hat transform

Linear feature detection is an important technique in different applications of image processing. To detect linear features in different types of images, a simple but effective algorithm based on a multiple-structuring-element center-surround top-hat transform is proposed. The center-surround top-hat transform is discussed and analyzed. Based on the properties of this transform for image feature detection, multiple structuring elements are constructed corresponding to the possible linear features at different directions. The whole algorithm is divided into four parts. First, the algorithm uses the center-surround top-hat transform to detect all the possible linear features at different directions through constructing multiple structuring elements. Second, the detected linear feature regions at each direction are processed by a closing operation to remove the possible holes or unconnected regions. Third, the processed results of the detected linear feature regions at all directions are combined to form all the possible detected linear feature regions. Fourth, the combined result is refined by using some simple operations to form the final result. Experimental results on different types of images from different applications verified the effective performance of the proposed algorithm. Moreover, the experimental results indicate that the proposed algorithm could be used in different applications.     

Multi-Level Feature-Based Ensemble Model for Target-Related Stance Detection

Stance detection is the task of attitude identification toward a standpoint. Previous work of stance detection has focused on feature extraction but ignored the fact that irrelevant features exist as noise during higher-level abstracting. Moreover, because the target is not always mentioned in the text, most methods have ignored target information. In order to solve these problems, we propose a neural network ensemble method that combines the timing dependence bases on long short-term memory (LSTM) and the excellent extracting performance of convolutional neural networks (CNNs). The method can obtain multi-level features that consider both local and global features. We also introduce attention mechanisms to magnify target information-related features. Furthermore, we employ sparse coding to remove noise to obtain characteristic features. Performance was improved by using sparse coding on the basis of attention employment and feature extraction. We evaluate our approach on the SemEval-2016Task 6-A public dataset, achieving a performance that exceeds the benchmark and those of participating teams.     

Accurate Multi-Scale Feature Fusion CNN for Time Series Classification in Smart Factory

Time series classification (TSC) has attracted various attention in the community of machine learning and data mining and has many successful applications such as fault detection and product identification in the process of building a smart factory. However, it is still challenging for the efficiency and accuracy of classification due to complexity, multi-dimension of time series. This paper presents a new approach for time series classification based on convolutional neural networks (CNN). The proposed method contains three parts: short-time gap feature extraction, multi-scale local feature learning, and global feature learning. In the process of short-time gap feature extraction, large kernel filters are employed to extract the features within the short-time gap from the raw time series. Then, a multi-scale feature extraction technique is applied in the process of multi-scale local feature learning to obtain detailed representations. The global convolution operation with giant stride is to obtain a robust and global feature representation. The comprehension features used for classifying are a fusion of short time gap feature representations, local multi-scale feature representations, and global feature representations. To test the efficiency of the proposed method named multi-scale feature fusion convolutional neural networks (MSFFCNN), we designed, trained MSFFCNN on some public sensors, device, and simulated control time series data sets. The comparative studies indicate our proposed MSFFCNN outperforms other alternatives, and we also provided a detailed analysis of the proposed MSFFCNN.     

基于组合图像特征与分层节点搜索的回环检测方法

目的 文中通过提出一种新的回环解决方案,平衡回环检测系统的高准确率与高运行效率。方法 提出一种利用组合图像特征与分层节点搜索的新方法。首先,计算一种原始图像的下采样二值化全局特征和经过改进的ORB(oriented FAST and rotated BRIEF)局部特征,将其存入图像特征数据库。其次,引入一种分层节点搜索算法,在数据库中搜索与当前图像特征最相似的全局特征作为回环候选。最后,利用改进的ORB特征进行局部特征匹配,验证候选图像,确定回环检测结果。结果 使用该算法在3个不同的数据集上进行验证,测试中每次回环检测的平均处理时间仅需19 ms。结论 实验结果表明,该算法在运行效率、准确率、召回率等方面均达到了领域内的先进水平。     

An Efficient Steganalysis Model Based on Multi-Scale LTP and Derivative Filters

Local binary pattern (LBP) is one of the most advanced image classification recognition operators and is commonly used in texture detection area. Research indicates that LBP also has a good application prospect in steganalysis. However, the existing LBP-based steganalysis algorithms are only capable to detect the least significant bit (LSB) and the least significant bit matching (LSBM) algorithms. To solve this problem, this paper proposes a steganalysis model called msdeLTP, which is based on multi-scale local ternary patterns (LTP) and derivative filters. The main characteristics of the msdeLTP are as follows: First, to reduce the interference of image content on features, the msdeLTP uses derivative filters to acquire residual images on which subsequent operations are based. Second, instead of LBP features, LTP features are extracted considering that the LTP feature can exhibit multiple variations in the relationship of adjacent pixels. Third, LTP features with multiple scales and modes are combined to show the relationship of neighbor pixels within different radius and along different directions. Analysis and simulation show that the msdeLTP uses only 2592-dimensional features and has similar detection accuracy as the spatial rich model (SRM) at the same time, showing the high steganalysis efficiency of the method.     

改进的多光谱聚合通道行人检测

针对外部环境的多变性和复杂性导致的单一波段下行人检测准确率较低的问题,提出了一种改进的基于可见和红外双波段聚合通道特征的行人检测算法。分别提取可见图像与红外图像的聚合通道特征;通过改变像素对比规则,采用自适应的阈值进行比较,将得到的改进的中心对称的局部二值模式特征添加到特征通道中;针对多光谱聚合通道特征设计了不同滤波器组进行滤波;训练分类器,实现多光谱下行人检测。实验表明,改进的局部二值模式特征能更好地描述红外图像中行人的对称性,中间滤波层丰富了候选特征池,算法在多种场景均能有效检测出行人,提高了行人检测精度,与利用多光谱聚合积分通道的检测工作相比,平均漏检率有所降低。

     

Realistic Smile Expression Recognition Approach Using Ensemble Classifier with Enhanced Bagging

A robust smile recognition system could be widely used for many real-world applications. Classification of a facial smile in an unconstrained setting is difficult due to the invertible and wide variety in face images. In this paper, an adaptive model for smile expression classification is suggested that integrates a fast features extraction algorithm and cascade classifiers. Our model takes advantage of the intrinsic association between face detection, smile, and other face features to alleviate the over-fitting issue on the limited training set and increase classification results. The features are extracted taking into account to exclude any unnecessary coefficients in the feature vector; thereby enhancing the discriminatory capacity of the extracted features and reducing the computational process. Still, the main causes of error in learning are due to noise, bias, and variance. Ensemble helps to minimize these factors. Combinations of multiple classifiers decrease variance, especially in the case of unstable classifiers, and may produce a more reliable classification than a single classifier. However, a shortcoming of bagging as the best ensemble classifier is its random selection, where the classification performance relies on the chance to pick an appropriate subset of training items. The suggested model employs a modified form of bagging while creating training sets to deal with this challenge (error-based bootstrapping). The experimental results for smile classification on the JAFFE, CK+, and CK+48 benchmark datasets show the feasibility of our proposed model.     

Modeling failure of heterogeneous viscoelastic solids under dynamic/impact loading due to multiple evolving cracks using a two-way coupled multiscale model

This paper presents a model for predicting damage evolution in heterogeneous viscoelastic solids under dynamic/impact loading. Some theoretical developments associated with the model have been previously reported. These are reviewed briefly, with the main focus of this paper on new developments and applications. A two-way coupled multiscale approach is employed and damage is considered in the form of multiple cracks evolving in the local (micro) scale. The objective of such a model is to develop the ability to consider energy dissipation due to both bulk dissipation and the development of multiple cracks occurring on multiple length and time scales. While predictions of these events may seem extraordinarily costly and complex, there are multiple structural applications where effective models would save considerable expense. In some applications, such as protective devices, viscoelastic materials may be preferred because of the considerable amount of energy dissipated in the bulk as well as in the fracture process. In such applications, experimentally based design methodologies are extremely costly, therefore suggesting the need for improved models. In this paper, the authors focus on the application of the newly developed multiscale model to the solution of some example problems involving dynamic and impact loading of viscoelastic heterogeneous materials with growing cracks at the local scale.     

An Efficient Detection Approach of Content Aware Image Resizing

Content aware image resizing (CAIR) is an excellent technology used widely for image retarget. It can also be used to tamper with images and bring the trust crisis of image content to the public. Once an image is processed by CAIR, the correlation of local neighborhood pixels will be destructive. Although local binary patterns (LBP) can effectively describe the local texture, it however cannot describe the magnitude information of local neighborhood pixels and is also vulnerable to noise. Therefore, to deal with the detection of CAIR, a novel forensic method based on improved local ternary patterns (ILTP) feature and gradient energy feature (GEF) is proposed in this paper. Firstly, the adaptive threshold of the original local ternary patterns (LTP) operator is improved, and the ILTP operator is used to describe the change of correlation among local neighborhood pixels caused by CAIR. Secondly, the histogram features of ILTP and the gradient energy features are extracted from the candidate image for CAIR forgery detection. Then, the ILTP features and the gradient energy features are concatenated into the combined features, and the combined features are used to train classifier. Finally support vector machine (SVM) is exploited as a classifier to be trained and tested by the above features in order to distinguish whether an image is subjected to CAIR or not. The candidate images are extracted from uncompressed color image database (UCID), then the training and testing sets are created. The experimental results with many test images show that the proposed method can detect CAIR tampering effectively, and that its performance is improved compared with other methods. It can achieve a better performance than the state-of-the-art approaches.     

Image Authenticity Detection Using DWT and Circular Block-Based LTrP Features

Copy-move forgery is the most common type of digital image manipulation, in which the content from the same image is used to forge it. Such manipulations are performed to hide the desired information. Therefore, forgery detection methods are required to identify forged areas. We have introduced a novel method for features computation by employing a circular block-based method through local tetra pattern (LTrP) features to detect the single and multiple copy-move attacks from the images. The proposed method is applied over the circular blocks to efficiently and effectively deal with the post-processing operations. It also uses discrete wavelet transform (DWT) for dimension reduction. The obtained approximate image is distributed into circular blocks on which the LTrP algorithm is employed to calculate the feature vector as the LTrP provides detailed information about the image content by utilizing the direction-based relation of central pixel to its neighborhoods. Finally, Jeffreys and Matusita distance is used for similarity measurement. For the evaluation of the results, three datasets are used, namely MICC-F220, MICC-F2000, and CoMoFoD. Both the qualitative and quantitative analysis shows that the proposed method exhibits state-of-the-art performance under the presence of post-processing operations and can accurately locate single and multiple copy-move forgery attacks on the images.     

基于多对象匹配与融合字符特征的印刷质量检验方法

目的 为了增强字符配准对字符位姿变化的鲁棒性和识别能力,以及印刷质量检验精度和缺陷类型分析对不同字符产品的自适应性,提出一种基于多对象匹配与融合字符特征的印刷质量检验方法。方法 采用多张合格字符样品图像进行模板构建;借助多对象匹配来配准多个待检验的字符,消除字符位姿的变化对字符配准的影响;进行逐像素的比对,检验字符区域的质量;利用灰度阈值分割以及Sobel边缘检测,将字符区域分成3个待检验的局部特征区域：边缘、前景、后景;进而获取边缘完整性,前景面积和灰度,背景面积和灰度这些显著的字符特征,由多张字符样品训练每个特征的自适应的合格范围;将其组合,形成融合字符特征,分析缺陷的类型。结果 测试数据表明,针对不同种类、不同精度要求的字符产品,所提方法对于字符质量的判断准确率达到100%,对缺陷类型的分类准确率保持在84.2%以上。结论 所提字符质量检验方法拥有良好的鲁棒性与自适应性,在包装、印刷等行业具备较高的应用价值。     

Ammonia Monitoring Near 1.5 mum with Diode-Laser Absorption Sensors

We investigated ammonia spectroscopy near 1.5 mum to select transitions appropriate for trace ammonia detection in air-quality and combustion emissions-monitoring applications using diode lasers. Six ammonia features were selected for these trace-gas detection applications based on their transition strengths and isolation from interfering species. The strengths, positions, and lower-state energies for the lines in each of these features were measured and compared with values published in the literature. Ammonia slip was measured in the exhaust above an atmospheric pressure premixed ethylene-air burner to demonstrate the feasibility of the in situ diode-laser sensor.     

High Performance Classification of Android Malware Using Ensemble Machine Learning

Although Android becomes a leading operating system in market, Android users suffer from security threats due to malwares. To protect users from the threats, the solutions to detect and identify the malware variant are essential. However, modern malware evades existing solutions by applying code obfuscation and native code. To resolve this problem, we introduce an ensemble-based malware classification algorithm using malware family grouping. The proposed family grouping algorithm finds the optimal combination of families belonging to the same group while the total number of families is fixed to the optimal total number. It also adopts unified feature extraction technique for handling seamless both bytecode and native code. We propose a unique feature selection algorithm that improves classification performance and time simultaneously. 2-gram based features are generated from the instructions and segments, and then selected by using multiple filters to choose most effective features. Through extensive simulation with many obfuscated and native code malware applications, we confirm that it can classify malwares with high accuracy and short processing time. Most existing approaches failed to achieve classification speed and detection time simultaneously. Therefore, the approach can help Android users to keep themselves safe from various and evolving cyber-attacks very effectively.     

Semi-GSGCN: Social Robot Detection Research with Graph Neural Network

Malicious social robots are the disseminators of malicious information on social networks, which seriously affect information security and network environments. Efficient and reliable classification of social robots is crucial for detecting information manipulation in social networks. Supervised classification based on manual feature extraction has been widely used in social robot detection. However, these methods not only involve the privacy of users but also ignore hidden feature information, especially the graph feature, and the label utilization rate of semi-supervised algorithms is low. Aiming at the problems of shallow feature extraction and low label utilization rate in existing social network robot detection methods, in this paper a robot detection scheme based on weighted network topology is proposed, which introduces an improved network representation learning algorithm to extract the local structure features of the network, and combined with the graph convolution network (GCN) algorithm based on the graph filter, to obtain the global structure features of the network. An end-to-end semi-supervised combination model (Semi-GSGCN) is established to detect malicious social robots. Experiments on a social network dataset (cresci-rtbust-2019) show that the proposed method has high versatility and effectiveness in detecting social robots. In addition, this method has a stronger insight into robots in social networks than other methods.     

Efficient object detection and tracking in video sequences

One of the most important problems in computer vision is the computation of the two-dimensional projective transformation (homography) that maps features of planar objects in different images and videos. This computation is required by many applications such as image mosaicking, image registration, and augmented reality. The real-time performance imposes constraints on the methods used. In this paper, we address the real-time detection and tracking of planar objects in a video sequence where the object of interest is given by a reference image template. Most existing approaches for homography estimation are based on two steps: feature extraction (first step) followed by a combinatorial optimization method (second step) to match features between the reference template and the scene frame. This paper has two main contributions. First, we detect both planar and nonplanar objects via efficient object feature classification in the input images, which is applied prior to performing the matching step. Second, for the tracking part (planar objects), we propose a fast method for the computation of the homography that is based on the transferred object features and their associated local raw brightness. The advantage of the proposed schemes is a fast matching as well as fast and robust object registration that is given by either a homography or three-dimensional pose.     

Brain tumor severity analysis using modified multi‐texton histogram and hybrid kernel SVM

Magnetic resonance image (MRI) segmentation refers to a process of assigning labels to set of pixels or multiple regions. It plays a major role in the field of biomedical applications as it is widely used by the radiologists to segment the medical images input into meaningful regions. In recent years, various brain tumor detection techniques are presented in the literature. In this article, we have developed an approach to brain tumor detection and severity analysis is done using the various measures. The proposed approach comprises of preprocessing, segmentation, feature extraction, and classification. In preprocessing steps, we need to perform skull stripping and then, anisotropic filtering is applied to make image suitable for extracting features. In feature extraction, we have modified the multi‐texton histogram (MTH) technique to improve the feature extraction. In the classification stage, the hybrid kernel is designed and applied to training of support vector machine to perform automatic detection of tumor region in MRI images. For comparison analysis, our proposed approach is compared with the existing works using K‐cross fold validation method. From the results, we can conclude that the modified multi‐texton histogram with non‐linear kernels has shown the accuracy of 86% but the MTH with non‐linear kernels shows the accuracy of 83.8%.     

Neural network classifier and multiple hypothesis image segmentation for dietary assessment using calorie calculator

Nowadays, dietary assessment becomes the emerging system for evaluating the person’s food intake. In this paper, the multiple hypothesis image segmentation and feed-forward neural network classifier are proposed for dietary assessment to enhance the performance. Initially, the segmentation is applied to input image which is used to determine the regions where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the significant feature of food items is extracted by the global feature and local feature extraction method. After the features are obtained, the classification is performed for each segmented region using feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food area volume and (ii) calorie and nutrition measure based on mass value. The outcome of the proposed method attains 96% of accuracy value which provides the better classification performance.     

STEP-based automatic system for recognising design and manufacturing features

In the present work, a STEP-based platform-independent system for design and manufacturing feature recognition is developed. A manufacturing feature taxonomy with multiple levels, which is based on the access directions of the feature, is proposed. The system can recognise both design and manufacturing features from the lower level geometry and topology available in the STEP file. The developed system can recognise intersecting features, which is a major shortcoming of previous attempts based on neutral formats. A more complete feature relationship analysis than available in the literature is carried out to find the relationships between all the types of features. Removal volumes and access directions of the features are determined to couple the feature recognition with down line applications. Raw material geometry is also considered while recognising the features. The present system is limited to parts that can be machined on a three-axis machining centre.