Discriminative metric design for robust pattern recognition

Motivated by the development of discriminative feature extraction (DFE), many researchers have come to realize the importance of designing a front-end feature extraction unit with an appropriate link to backend classification. This paper proposes an advanced formalization of DFE, which we call the discriminative metric design (DMD), and elaborates on its exemplar implementation by using a simple, linear feature transformation matrix. The resulting DMD implementation is shown to have a close relationship to various discriminative pattern recognizers, including artificial neural networks. The utility of the proposed method is clearly demonstrated in speech pattern recognition experiments     

Pattern recognition using a family of design algorithms based uponthe generalized probabilistic descent method

This paper provides a comprehensive introduction to a novel approach to pattern recognition which is based on the generalized probabilistic descent method (GPD) and its related design algorithms. The paper contains a survey of recent recognizer design techniques, the formulation of GPD, the concept of minimum classification error learning that is closely related to the GPD formalization, a relational analysis between GPD and other important design methods, and various embodiments of GPD-based design, including segmental-GPD, minimum spotting error training, discriminative utterance verification, and discriminative feature extraction. GPD development has its origins in basic pattern recognition and Bayes decision theory. It represents a simple but careful re-investigation of the classical theory and successfully leads to an innovative framework. For clarity of presentation, detailed discussions about its embodiments are provided for examples of speech pattern recognition tasks that use a distance-based classifier. Experimental results in speech pattern recognition tasks clearly demonstrate the remarkable utility of the family of GPD-based design algorithms     

基于核协同表示与鉴别投影的辐射源调制识别

针对辐射源识别中的特征稳定性不高和低信噪比环境适应性不足等问题,提出了一种基于二次时频分布、核协同表示与鉴别投影的识别方法.首先,通过时频变换、稀疏域降噪和二次特征提取的预处理算法降低噪声干扰和特征冗余,以获取高稳定性的二次时频分布特征;然后,采用核协同表示和鉴别投影思想进行降维学习和字典学习,以提升数据低维表征和类间鉴别能力;最后,通过离线训练完成系统优化并用于分类验证.仿真结果表明,二次时频分布特征具备较高稳定性,识别方法具备较强鲁棒性、时效性和适应性;当信噪比为-10dB时,该方法对8类辐射源信号的整体平均识别率达到96.88%.     

多流形判别分析在特征提取中的应用研究

为了更好地提高人脸识别率及其识别效率,提出了一种基于多流形判别分析(MMDA)的图像特征提取方法.在MM-DA方法中,为了寻求能够同时最大化类间散布矩阵和最小化类内散布矩阵的判别矩阵,类间、类内分布图分别被用来描述类间和类内的分离性,类内图可以表示子流形的信息,而类间图可以代表多流形的信息,从而更好地实现分类.在ORL及FERET人脸数据库上进行实验,结果表明了MMDA方法在特征提取中的有效性.     

High-dimensional feature extraction using bit-plane decomposition of local binary patterns for robust face recognition

Transforming an original image into a high-dimensional (HD) feature has been proven to be effective in classifying images. This paper presents a novel feature extraction method utilizing the HD feature space to improve the discriminative ability for face recognition. We observed that the local binary pattern can be decomposed into bit-planes, each of which has scale-specific directional information of the face image. Each bit-plane not only has the inherent local-structure of the face image but also has an illumination-robust characteristic. By concatenating all the decomposed bit-planes, we generate an HD feature vector with an improved discriminative ability. To reduce the computational complexity while preserving the incorporated local structural information, a supervised dimension reduction method, the orthogonal linear discriminant analysis, is applied to the HD feature vector. Extensive experimental results show that existing classifiers with the proposed feature outperform those with other conventional features under various illumination, pose, and expression variations.     

Ensemble convolutional neural networks for automatic fusion recognition of multi‐platform radar emitters

Presently, the extraction of hand‐crafted features is still the dominant method in radar emitter recognition. To solve the complicated problems of selection and updation of empirical features, we present a novel automatic feature extraction structure based on deep learning. In particular, a convolutional neural network (CNN) is adopted to extract high‐level abstract representations from the time‐frequency images of emitter signals. Thus, the redundant process of designing discriminative features can be avoided. Furthermore, to address the performance degradation of a single platform, we propose the construction of an ensemble learning‐based architecture for multi‐platform fusion recognition. Experimental results indicate that the proposed algorithms are feasible and effective, and they outperform other typical feature extraction and fusion recognition methods in terms of accuracy. Moreover, the proposed structure could be extended to other prevalent ensemble learning alternatives.     

图像处理技术在车牌号识别领域中的算法改进

针对图像处理技术在车牌号识别领域中的运用,结合目前常用识别方法(模板匹配法、神经网络法和支持向量机识别法)和主要特征提取方式(统计特征提取和结构特征提取)各自的优点,设计出一种多层分支结构的车牌号识别系统,该系统根据不同待识别字符的特征进行分类,然后匹配上对该类特征识别较有优势的特征提取方法和字符识别算法,并提出一种对折识别算法运用其中,通过对字符的分层识别和分支识别,从而达到精确、高效识别的目的,最后通过试验测试和统计分析,证明了该方法在车牌号识别中的优越性.     

Discriminative low-rank embedding with manifold constraint for image feature extraction and classification

The robustness against noise, outliers, and corruption is a crucial issue in image feature extraction. To address this concern, this paper proposes a discriminative low-rank embedding image feature extraction algorithm. Firstly, to enhance the discriminative power of the extracted features, a discriminative term is introduced using label information, obtaining global discriminative information and learning an optimal projection matrix for data dimensionality reduction. Secondly, manifold constraints are incorporated, unifying low-rank embedding and manifold constraints into a single framework to capture the geometric structure of local manifolds while considering both local and global information. Finally, test samples are projected into a lower-dimensional space for classification. Experimental results demonstrate that the proposed method achieves classification accuracies of 95.62%, 95.22%, 86.38%, and 86.54% on the ORL, CMUPIE, AR, and COIL20 datasets, respectively, outperforming dimensionality reduction-based image feature extraction algorithms.     

Gait recognition based on modified phase-only correlation

Gait recognition is an emerging biometric technology aiming to identify people purely through the analysis of the way they walk. The technology has attracted interest as a method of identification because it is noncontact and does not require the subject’s cooperation. Clothing, carrying conditions and other intra-class variations, also referred to as “covariates,” affect the performance of gait recognition systems. This paper proposes a supervised feature extraction method, which is able to select relevant discriminative features for human recognition to mitigate the impact of covariates and hence improve the recognition performances. The proposed method is evaluated using the CASIA gait database (dataset B), and the experimental results suggest that our method yields 81.40 % of correct classification when compared against similar techniques which do not exceed 77.96 %.     

面向行人再识别的特征融合与鉴别零空间方法

针对行人再识别技术易受到光照、姿态和视角等因素影响，同一个人外观特征变化明显，较难提取其不变特征，导致识别率偏低的问题，本文提出面向行人再识别的融合特征与鉴别零空间方法。首先利用HSV、LAB、RGB和YCrCb四种颜色特征和Gabor滤波器提取条纹特征， GOG描述子提取块状特征，并将这两种特征融合成一个特征向量，然后将融合后的的特征投影到鉴别零空间，降低特征维数，最后利用欧氏距离计算距离进行行人再识别。本文所提方法在VIPeR、Prids_450s和CUHK01数据库上的rank1识别率分别是52.7%、72.2%和59.7%，实验结果表明所提方法能充分融合行人图像特征，对环境有较强鲁棒性，可有效提高识别率。      

引入高阶注意力机制的人体行为识别

现有的视频行为识别方法在特征提取过程中,存在忽略各个特征之间相互作用关系的问题,对近似动作的区分效果不理想。因此,提出引入高阶注意力机制的人体行为识别方法。在深度卷积神经网络中引入高阶注意力模块,通过注意力机制建模和利用复杂和高阶的统计信息,对训练过程中特征图各个部分的权重进行重新分配,从而关注局部细粒度信息,产生有区别性的关注建议,捕获行为之间的细微差异。在UCF101和HMDB51这两个人体行为数据集上的实验结果表明,与现有方法相比,识别率得到了一定的提升,验证了所提出方法的有效性和鲁棒性,提高了对近似行为的辨别能力。      

Human skeleton representation for 3D action recognition based on complex network coding and LSTM

3D skeleton sequences contain more effective and discriminative information than RGB video and are more suitable for human action recognition. Accurate extraction of human skeleton information is the key to the high accuracy of action recognition. Considering the correlation between joint points, in this work, we first propose a skeleton feature extraction method based on complex network. The relationship between human skeleton points in each frame is coded as a network. The changes of action over time are described by a time series network composed of skeleton points. Network topology attributes are used as feature vectors, complex network coding and LSTM are combined to recognize human actions. The method was verified on the NTU RGB + D60, MSR Action3D and UTKinect-Action3D dataset, and have achieved good performance, respectively. It shows that the method of extracting skeleton features based on complex network can properly identify different actions. This method that considers the temporal information and the relationship between skeletons at the same time plays an important role in the accurate recognition of human actions.     

基于模糊平面的信号识别方法

将一维信号变换到二维坐标平面往往更有利于描述信号的时变特征,从而实现信号的分类识别。基于离散时频分布的信号识别方法,将时频核设计问题转化为以信号自模糊函数为原始特征的特征选择问题,以实现特征降维和信号识别。时频核设计孤立考察模糊平面上各个特征点,且降维空间中存在着识别信息冗余。将核设计的原理推广,直接基于模糊平面进行信号识别,利用K—L展开和线性变换对自模糊函数进行特征提取,在降维空间内综合了各原始特征共有的分类信息,并去除特征之间的相关性,从而比时频核设计方法具有更优的信号识别性能。     

Discriminative tonal feature extraction method in mandarin speech recognition

To utilize the supra-segmental nature of Mandarin tones, this article proposes a feature extraction method for hidden markov model (HMM) based tone modeling. The method uses linear transforms to project F0 (fundamental frequency) features of neighboring syllables as compensations, and adds them to the original F0 features of the current syllable. The transforms are discriminatively trained by using an objective function termed as "minimum tone error", which is a smooth approximation of tone recognition accuracy. Experiments show that the new tonal features achieve 3.82% tone recognition rate improvement, compared with the baseline, using maximum likelihood trained HMM on the normal F0 features. Further experiments show that discriminative HMM training on the new features is 8.78% better than the baseline.     

基于PCA与Fisherface互补双特征提取的人耳图像识别

人耳识别目前是一种新的生物特征识别技术,特征提取是模式识别技术中的关键环节,决定着分类结果正确率的高低,单特征提取方法需要在一定的条件下才能取得较高的识别率,但是采用双特征提取却可以克服单特征提取的这一局限性.为了提高分类结果的正确率,提出了一个全新的方法,即基于主成分分析(PCA)与fisherface的互补双特征提取方法,并将其运用于人耳图像识别中,在北京科技大学提供的人耳图像库上的实验结果表明,该方法的人耳识别率明显高于PCA、fisherface、ICA单特征提取的人耳识别率.     

基于PCA和核FDA的人脸识别研究

基于主分量分析的特征脸识别是人脸识别中重要的识别方法,具有简单、实用等特点。Fisher判别分析是统计分析一种常用的降维方法,多类Fisher判别分析在模式识别领域得到广泛应用。核方法技术是设计全局非线性算法最流行的工具之一,应用核方法技术使得低维空间线性不可分的样本在高维空间线性可分。先对ORL人脸数据库中的图像应用主分量分析提取主分量,再应用核Fisher判别方法把特征向量做隐式变换,最后把得到的数据采用k-紧邻分类器进行分类识别,并对实验结果做了比较分析。     

Adaptive feature selection based on reconstruction residual and accurately located landmarks for expression-robust 3D face recognition

A novel adaptive feature selection based on reconstruction residual and accurately located landmarks for expression-robust 3D face recognition is proposed in this paper. Firstly, the novel facial coarse-to-fine landmarks localization method based on Active Shape Model and Gabor wavelets transformation is proposed to exactly and automatically locate facial landmarks in range image. Secondly, the multi-scale fusion of the pyramid local binary patterns (F-PLBP) based on the irregular segmentation associated with the located landmarks is proposed to extract the discriminative feature. Thirdly, a sparse representation-based classifier based on the adaptive feature selection (A-SRC) using the distribution of the reconstruction residual is presented to select the expression-robust feature and identify the faces. Finally, the experimental evaluation based on FRGC v2.0 indicates that the adaptive feature selection method using F-PLBP combined with the A-SRC can obtain the high recognition accuracy by performing the higher discriminative power to overcome the influence from the facial expression variations.     

Discriminative temporal feature extraction for robust speechrecognition

A discriminative temporal feature processing method for robust speech recognition is presented by combining the knowledge and the statistical methods. The cepstral features are first filtered by a RASTA method based on human hearing perception and then processed using the minimum classification error algorithm. Improved recognition performance can be achieved in both quiet and noisy environments     

基于内容的视频镜头的分类

论文在研究了视频关键帧选取和特征提取技术的基础上,提出了一种基于内容的视频镜头分类方法,并将其应用于动漫/真人的视频镜头的分类,以检验所提方法的性能。实验首先提取了视频的语义特征,接着使用互信息对特征的有效性进行分析,最后使用支持向量机作为分类器,对特征分析的结果进行验证。