Real object recognition using moment invariants

Moments and functions of moments have been extensively employed as invariant global features of images in pattern recognition. In this study, a flexible recognition system that can compute the good features for high classification of 3-D real objects is investigated. For object recognition, regardless of orientation, size and position, feature vectors are computed with the help of nonlinear moment invariant functions. Representations of objects using two-dimensional images that are taken from different angles of view are the main features leading us to our objective. After efficient feature extraction, the main focus of this study, the recognition performance of classifiers in conjunction with moment-based feature sets, is introduced     

Indian sign language recognition using Krawtchouk moment-based local features

In this paper, Krawtchouk moment-based shape features at lower orders are proposed for Indian sign language (ISL) recognition system which gives local information about the shape from a specific region of interest. The shape recognition capability of Krawtchouk moment-based local features is verified on two databases: the standard Jochen Triesch’s database and 26 ISL alphabets which are collected from 72 different subjects, with variations in position, scale and rotation. Feature selection is performed to minimise redundancy. The effect of order and feature dimensionality for different classifiers is studied. Results show that Krawtchouk moment-based local features are found to exhibit user, scale, rotation and translation invariance. Moreover, they have shape identification capability.     

基于卷积神经网络和Transformer网络的鸟声识别

针对传统鸟声识别算法中特征提取方式单一、分类识别准确率低等问题,提出一种结合卷积神经网络和Transformer网络的鸟声识别方法。该方法综合考虑网络局部特征学习和全局上下文依赖性构造,从原始鸟声音频信号中提取短时傅里叶变换(Short Time Fourier Transform,STFT)语谱图特征,将其输入到卷积神经网络(ConvolutionalNeural Network,CNN)中提取局部频谱特征信息,同时提取鸟声信号的对数梅尔特征及一阶差分、二阶差分特征用于合成梅尔频率倒谱系数(Mel Frequency Cepstrum Coefficient,MFCC)混合特征向量,将其输入到Transformer网络中获取全局序列特征信息,最后融合所提取的特征可得到更丰富的鸟声特征参数,通过Softmax分类器得到鸟声识别结果。在Birdsdata和xeno-canto鸟声数据集上进行实验,平均识别准确率分别达到了97.81%和89.47%。实验结果表明该方法相较于其他现有的鸟声识别模型具有更高的识别准确率。     

采用图像融合技术的多模式人脸识别

利用图像融合技术实现了基于可见光图像和红外热图像相结合的多模式人脸识别,研究了两种图像在像素级和特征级的融合方法.在像素级,提出了基于小波分解的图像融合方法,实现了两种图像的有效融合.在特征级,采用分别提取两种识别方法中具有较好分类效果的前50%的特征进行特征级的融合.实验表明,经像素级和特征级融合后,识别准确率都较单一图像有很大程度的提高,并且特征级的融合效果明显优于像素级的融合.因此,基于图像融合技术的多模式人脸识别,有效的增加了图像的信息量,是提高人脸识别准确率的有效途径之一.     

Occlusion invariant face recognition using mean based weight matrix and support vector machine

In this paper, a novel occlusion invariant face recognition algorithm based on Mean based weight matrix (MBWM) technique is proposed. The proposed algorithm is composed of two phases—the occlusion detection phase and the MBWM based face recognition phase. A feature based approach is used to effectively detect partial occlusions for a given input face image. The input face image is first divided into a finite number of disjointed local patches, and features are extracted for each patch, and the occlusion present is detected. Features obtained from the corresponding occlusion-free patches of training images are used for face image recognition. The SVM classifier is used for occlusion detection for each patch. In the recognition phase, the MBWM bases of occlusion-free image patches are used for face recognition. Euclidean nearest neighbour rule is applied for the matching. GTAV face database that includes many occluded face images by sunglasses and hand are used for the experiment. The experimental results demonstrate that the proposed local patch-based occlusion detection technique works well and the MBWM based method shows superior performance to other conventional approaches.     

Face Recognition Based on Gabor Feature Extraction Followed by FastICA and LDA

Over the past few decades, face recognition has become the most effective biometric technique in recognizing people’s identity, as it is widely used in many areas of our daily lives. However, it is a challenging technique since facial images vary in rotations, expressions, and illuminations. To minimize the impact of these challenges, exploiting information from various feature extraction methods is recommended since one of the most critical tasks in face recognition system is the extraction of facial features. Therefore, this paper presents a new approach to face recognition based on the fusion of Gabor-based feature extraction, Fast Independent Component Analysis (FastICA), and Linear Discriminant Analysis (LDA). In the presented method, first, face images are transformed to grayscale and resized to have a uniform size. After that, facial features are extracted from the aligned face image using Gabor, FastICA, and LDA methods. Finally, the nearest distance classifier is utilized to recognize the identity of the individuals. Here, the performance of six distance classifiers, namely Euclidean, Cosine, Bray-Curtis, Mahalanobis, Correlation, and Manhattan, are investigated. Experimental results revealed that the presented method attains a higher rank-one recognition rate compared to the recent approaches in the literature on four benchmarked face datasets: ORL, GT, FEI, and Yale. Moreover, it showed that the proposed method not only helps in better extracting the features but also in improving the overall efficiency of the facial recognition system.     

基于3D和1D多特征融合的语音情感识别算法

针对语音情感识别任务中特征提取单一、分类准确率低等问题,提出一种3D和1D多特征融合的情感识别方法,对特征提取算法进行改进.在3D网络,综合考虑空间特征学习和时间依赖性构造,利用双线性卷积神经网络(Bilinear Convolutional Neural Network,BCNN)提取空间特征,长短期记忆网络(Sho...     

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.     

一种基于GDLPP的人脸识别算法

针对人脸识别中的特征提取问题,本文提出了一种结合Gabor小波特征和判别保局投影的人脸识别算法-GDLPP.该算法首先对人脸图像进行多分辨率的Gabor小波变换,提取样本的高阶统计信息;然后更改保局投影(LPP)的目标函数,增加样本类间散布约束,从而提取更具判别性的特征.本文采用最小近邻分类器估算识别率.在USPS数据库、Yale人脸库以及AR人脸库的测试结果表明,在姿态、光照、表情、训练样本数目变化的情况下,GDLPP都具有较好的识别率.     

基于局域波信息熵的高速自动机故障诊断

针对小口径火炮自动机工作时产生的短时冲击信号,提出一种将局域波分解与信息熵相结合提取特征量,并利用Elman神经网络进行故障识别的诊断方法。首先运用具有自适应特性的局域波对振动信号进行分解得到IMF分量,再接着利用信息熵理论提取IMF信息熵、局域波能谱熵及能矩谱熵作为故障特征量,最后将特征向量输入Elman神经网络进行故障分类识别。实验结果表明:该方法能准确,有效地识别故障。     

一种新颖的虹膜识别方法

提出一种基于多纹理特征融合的新颖虹膜识别方法。该方法对虹膜图像做Gabor小波变换提取不同分辨力不同方向下的纹理特征作为虹膜的全局特征,在滤波后的子窗口图像上运用灰度级共现矩阵(COM)提取虹膜的局部特征。通过加权欧几里德距离和最小距离分别对全局特征和局部特征进行分类识别。设计了FIS(模糊推理系统)特征融合分类方法来提高虹膜识别的鲁棒性。实验结果表明本方法有效可行,可以达到98.5%的识别率,并在保持1.4%较低的FRR(拒绝率)的同时可以使FAR(误识率)减少到0.1%。     

一种新颖的基于Gabor-LDA的人脸识别方法

为了克服光照、表情变化等因素对人脸识别的影响,提出了一种基于Gabor小波和最佳鉴别分析LDA的人脸识别方法。该方法充分利用了LDA得到的鉴别向量,用鉴别向量组成线性变换矩阵,直接从原始的强度图像上提取LDA特征。然后,用鉴别向量选择一些鉴别像素,仅在鉴别像素的位置上提取Gabor特征并对Gabor特征作LDA变换得到另一种LDA特征。它们分别可视为全局特征和局部特征。最后的分类器融合这两类特征。在FERET人脸库上的试验表明了该方法的有效性。     

利用Krawtchouk矩不变量实现基于形状的图像检索

图像在经过平移、旋转和尺度变化后是否仍具有很好的检索效果是基于形状的图像检索研究的一个难点.本文提出了一种利用Krawtchouk矩不变量实现基于形状的图像检索方法.该方法首先对图像进行灰度变换,然后提取图像的低阶矩,取16个低阶矩不变量作为图像的特征向量,并按照相似性度量输出相似图像从而实现基于形状的图像检索.文中给出了实验结果,并与基于几何矩不变量和基于Zernike矩不变量的图像检索方法进行了比较.结果表明本文的方法具有更好的检索性能,和上述两种方法相比,查全率分别提高了21.52%和7.6%,查准率则分别提高了16.25%和6.25%.     

一种基于核主成分分析和组合分类器的虹膜识别方法

提出了一种新的虹膜特征提取与识别方法,该方法利用核主成分分析(KPCA)在高维空间具有较强的特征选择能力来提取虹膜图像的纹理特征。采用了一种距离度量和支持向量机相结合的两级分类方法,前级采用欧式距离来度量图像间的相似性,若符合条件,给出分类结果,否则拒绝,并转入后一级分类器——支持向量机分类,以减少进入支持向量机的样本数目,该组合分类方法充分利用了支持向量机识别率高和距离度量速度快的优点。实验结果表明,该方法提高了虹膜识别率,是一种有效的虹膜识别方法。     

Near-infrared and visible light image fusion algorithm for face recognition

In order to improve face recognition accuracy, we present a simple near-infrared (NIR) and visible light (VL) image fusion algorithm based on two-dimensional linear discriminant analysis (2DLDA). We first use two such schemes to extract two classes of face discriminant features of each of NIR and VL images separately. Then the two classes of features of each kind of images are fused using the matching score fusion method. At last, a simple NIR and VL image fusion approach is exploited to combine the scores of NIR and VL images and to obtain the classification result. The experimental results show that the proposed NIR and VL image fusion approach can effectively improve the accuracy of face recognition.     

Face recognition system based on MOTIF features

This work addresses the use of the MOTIF algorithm for face feature extraction. The MOTIF algorithm is commonly used to characterize texture and shows good performance in this task; a MOTIF algorithm without the Co-occurrence Matrix is proposed to obtain face features, and the approach proves to be effective. System testing was based on a standard database (the AR Face database) that includes 120 people, 70 images with face expressions and 30 with sunglasses; 1 to 9 images were used to make the template for each person. After using Euclidean distance, Cosine distance and support vector machine as classifiers, correct classification was achieved with 98% accuracy. Further tests were performed with all databases and compared with Local Binary Pattern, DI-WBP and other commonly used schemes, demonstrating effective face recognition by the MOTIF algorithm without the co-occurrence matrix in addition to its fast performance due to the low computational cost.     

基于人体手指指节折痕的身份识别方法

基于人体生物特征的认证是鉴别个人身份的有效方法.鉴于人体的手指折痕具有稳定性且对于不同的人具有不相同的特点,本文提出了一种基于手指折痕的身份识别的新方法.该算法系统由三部分组成:图像预处理、特征提取和特征匹配.在预处理阶段,提出了基于中心坐标轴的图像定位和归一化方法,并在手指内侧分割出了用于识别的长方形窗口形状的手指子图(ROI),ROI包含了手指的第一和第二折痕线;在第二阶段,提出了基于Radon变换和奇异值分解的特征提取方法;最后利用基于欧氏距离的最近邻分类器在一个取自61人共488幅手指图像的数据库上进行了匹配试验,结果验证了该方法是可行和有效的(等错误率为2.51%).     

Adaptive Bearing Fault Diagnosis based on Wavelet Packet Decomposition and LMD Permutation Entropy

Bearing fault signal is nonlinear and non-stationary,therefore proposed a fault feature extraction method based on wavelet packet decomposition( WPD) and local mean decomposition( LMD) permutation entropy,which is based on the support vector machine( SVM) as the feature vector pattern recognition device.Firstly,the wavelet packet analysis method is used to denoise the original vibration signal,and the frequency band division and signal reconstruction are carried out according to the characteristic frequency. Then the decomposition of the reconstructed signal is decomposed into a number of product functions( PE) by the local mean decomposition( LMD),and the permutation entropy of the PF component which contains the main fault information is calculated to realize the feature quantization of the PF component. Finally,the entropy feature vector input multi-classification SVM,which is used to determine the type of fault and fault degree of bearing.The experimental results show that the recognition rate of rolling bearing fault diagnosis is 95%. Comparing with other methods,the present this method can effectively extract the features of bearing fault and has a higher recognition accuracy.     

A comprehensive study on face recognition: methods and challenges

ABSTRACT

Face Recognition is the process of identifying and verifying the faces. Face recognition has vast importance in the field of Security, Healthcare, Banking, Criminal Identification, Payment, and Advertising. In this paper, we have reviewed various techniques and challenges for the face recognition. Illumination, pose variation, facial expressions, occlusions, aging, etc. are the key challenges to the success of face recognition. Pre-processing, Face Detection, Feature Extraction, Optimal Feature Selection, and Classification are primary steps in any face recognition system. This paper provides a detailed review of each. Feature extraction techniques can be classified as appearance-based methods or geometry-based methods, such method may be local or global. Feature extraction is the most crucial stage for the success of the face recognition system. However, deep learning methods have freed the user from handcrafting the features. In this article, we have surveyed state-of-the-art methods of last few decades and the comparative study of various feature extraction methods is provided. Article also describes the current challenges in the area.