ISAR image scattering center association based on speeded-up robust features

Multimedia Tools and Applications - It is difficult for the imaging radar of the single antenna to correlate the scattering centers in 3D reconstruction. Therefore, an association method of...     

Cancellable face template algorithm based on speeded-up robust features and winner-takes-all

Multimedia Tools and Applications - Features such as face, fingerprint, and iris imprints have been used for authentication in biometric system. The toughest feature amongst these is the face....     

Retraction Note: Decision response of subway evacuation signs based on brain component features

Neural Computing and Applications -     

Retraction Note to: Traffic identification and traffic analysis based on support vector machine

Neural Computing and Applications -     

GMM based language identification system using robust features

In this work, we have proposed new feature vectors for spoken language identification (LID) system. The Mel frequency cepstral coefficients (MFCC) and formant frequencies derived using short-time window speech signal. Formant frequencies are extracted from linear prediction (LP) analysis of speech signal. Using these two kind of features of speech signal, new feature vectors are derived using cluster based computation. A GMM based classifier has been designed using these new feature vectors. The language specific apriori knowledge is applied on the recognition output. The experiments are carried out on OGI database and LID recognition performance is improved.     

基于改进SIFT的离线签名鉴别方法

针对高质量模仿签名和签名图像的尺度变化对鉴别效果影响较大的问题,提出了一种基于改进SIFT的离线签名鉴别方法。该方法首先改进尺度空间的建立,减少尺度空间的层数和组数,然后检测签名图像的SIFT特征点和提取特征描述子,根据特征描述子间的欧氏距离进行匹配,通过邻近距离之比和特征点角度差筛选匹配对,并对匹配对特征点的角度差进行直方图统计构成ODH(Orientation Difference Histogram)特征向量。最终根据匹配对的数量和ODH特征向量的相似度完成鉴别工作。本文方法在本地数据库上的等误率为6.7%,在4NSigComp2010公共数据库上的等误率为20%。实验结果表明,该方法与现有方法相比有效的提高了鉴别正确率。     

Implicit excitation source features for robust language identification

In present work, the robustness of excitation source features has been analyzed for language identification (LID) task. The raw samples of linear prediction (LP) residual signal, its magnitude and phase components are processed at sub-segmental, segmental and supra-segmental levels for capturing the robust language-specific phonotactic information. Present LID study has been carried out on 27 Indian languages from Indian Institute of Technology Kharagpur-Multi Lingual Indian Language Speech Corpus (IITKGP-MLILSC). Gaussian mixture models are used to develop the LID systems using robust language-specific excitation source information. Robustness of excitation source information has been evinced in view of (i) background noise, (ii) varying amount of training data and (iii) varying length of test samples. Finally, the robustness of proposed excitation source features is compared with the well-known spectral features using LID performances obtained from IITKGP-MLILSC database. Segmental level excitation source features obtained from raw samples of LP residual signal and its phase component perform better at low SNR levels, compared with the vocal tract features.     

基于快速鲁棒特征的CamShift跟踪算法

为了解决CamShift算法由于对颜色敏感导致的跟踪效果变差或失效的问题,提出一种基于局部特征匹配的CamShift跟踪算法。采用快速鲁棒特征(SURF)方法在多通道图像的目标区域和搜索区域提取包含图像信息的局部特征点,并利用近似最近邻搜索对特征点进行匹配;使用提纯后的匹配结果得到特征点的位置、尺度及方向信息,对CamShift方法进行约束和更新,以提高跟踪精度和稳定性。实验结果表明,与经典CamShift算法和同类的改进算法相比,该算法能够较好地实现对复杂背景下旋转和放缩运动目标的实时跟踪。     

Personal identification based on finger-vein features

Finger-vein recognition refers to a recent biometric technique which exploits the vein patterns in the human finger to identify individuals. The advantages of finger vein over traditional biometrics (e.g. face, fingerprint, and iris) lie in low-risk forgery, noninvasiveness, and noncontact. This paper here presents a new method of personal identification based on finger-vein recognition. First, a stable region representing finger-vein network is cropped from the image plane of an imaging sensor. A bank of Gabor filters is then used to exploit the finger-vein characteristics at different orientations and scales. Based on the filtered image, both local and global finger-vein features are extracted to construct a finger-vein code (FVCode). Finally, finger-vein recognition is implemented using the cosine similarity measure classifier, and a fusion scheme in decision level is adopted to improve the reliability of identification. Experimental results show that the proposed method exhibit an exciting performance in personal identification.     

基于二进制鲁棒不变尺度关键点-加速稳健特征的自然特征虚实注册方法

针对基于视觉的增强现实(AR)中虚实注册的准确率和实时效果受光照、遮挡和视角变化影响大,易导致注册失败的问题,提出一种基于二进制鲁棒不变尺度关键点-加速稳健特征(BRISK-SURF)算法的自然特征虚实注册方法。首先,利用加速稳健特征(SURF)特征提取算子检测特征点;然后,采用二进制尺度旋转不变鲁棒(BRISK)特征描述算子对特征点进行二进制描述,结合汉明距离实现准确高速的特征匹配;最后,根据图像间的单应性关系实现虚实注册。从图像特征匹配和虚实注册两方面进行实验,结果显示BRISK-SURF算法的平均准确率与SURF算法基本保持一致,比BRISK算法提高了约25%,平均召回率提高了约10%;基于BRISK-SURF的注册方法的结果接近参考标准数据,精度较高,实时性较好。实验结果表明,所提方法对于光照、遮挡和视角情况不同的图像具有较高的识别准确度、注册精度和实时效果。另外,使用此方法实现了基于AR的交互式旅游资源呈现与体验系统。     

一种基于鲁棒局部纹理特征的背景差分方法

针对复杂场景下运动目标的精确检测这一问题,提出一种对噪声鲁棒并具备灰度尺度不变性的局部纹理特征描述子LBP_Center,将其与像素的颜色信息结合应用于背景建模中,采用随机抽样的机制更新模型,同时引入背景复杂度以去除多模态动态背景产生的噪点。在标准测试数据集上的实验结果表明,该算法对柔性阴影及光照缓慢变化具备良好的鲁棒性,综合性能更优。     

Retraction Note: Tolerance rough set firefly-based quick reduct

Neural Computing and Applications -     

基于细粒度特征的话题句识别方法

话题句（TC）识别中采用穷举方法生成标点句的候选话题句（CTC）影响系统的执行效率和话题句识别的准确率。提出一种新的候选话题句生成方法,利用标点句在篇章中的位置特征、话题的语法特征以及话题串与说明的邻接性特征,指导候选话题句的生成过程。实验结果表明,该方法减少了候选话题句的个数,提高了系统效率。而且,通过与基于穷举式候选话题句生成策略的话题句识别工作进行对比,该方法使单个标点句话题句识别的准确率提高了0.96个百分点,使标点句序列话题句识别的准确率提高了1.31个百分点。     

一种基于鲁棒自适应观测器的故障区分方法

设计了一种鲁棒自适应观测器,通过其输出残差对传感器故障信息敏感性很高,而对系统故障信息敏感性很低的特点,实现了故障区分.设计了一套故障区分控制系统和检测策略,用以区分两类故障,以免发生误判现象.举例说明了该策略的可行性和有效性.     

一种完全数据驱动的子空间辨识与鲁棒预测控制器设计

针对线性时变多变量系统,在可能存在输入输出数据噪声的情况下,不需已知系统的先验结构信息,提出一种完全数据驱动的子空间辨识及控制器设计方法.在子空间在线辨识基础上,利用不确定性模型更好地建模被控系统,结合鲁棒控制策略进行预测控制器的设计;将系统建模与鲁棒控制器的设计包含在一个控制系统设计框架内,对模型不确定性具有更好的鲁棒性;最后给出仿真实例验证算法的有效性.     

鲁棒辨识研究的现状

综述了鲁棒辨识问题的研究进展，介绍 了鲁棒辨识问题产生的背景，对各种不同的辨识方法进行了评述，并指出各自的特点，最后总结了今后的发展方向。     

融合局部与全局特征提取的虹膜识别方法

传统的虹膜识别系统需要将虹膜图像转换至极坐标系统并进行归一化,通过平移特征向量来达到旋转不变性。为了降低传统虹膜识别方法的复杂性,提出了一种融合局部与全局特征提取的虹膜识别方法,无须对预处理后的虹膜图像进行归一化。该方法首先对分割出的虹膜图像直接采用非张量积小波提取全局特征,接着采用SIFT方法提取选定区域的局部特征,最后对虹膜局部及全局特征采用不同的权值,进行相似性距离测试。结果表明该方法在等错误率为0.935%的情况下,正确识别率达到了99.065%。在不对虹膜图像归一化的情况下,可获得很好的识别性能。     

Hyperspectral image classification based on robust discriminative extraction of multiple spectral-spatial features

In hyperspectral image (HSI) processing, the inclusion of both spectral and spatial features, e.g. morphological features, shape features, has shown great success in classification of hyperspectral data. Nevertheless, there exist two main issues to address: (1) The multiple features are often treated equally and thus the complementary information among them is neglected. (2) The features are often degraded by a mixture of various kinds of noise, leading to the classification accuracy decreased. In order to address these issues, a novel robust discriminative multiple features extraction (RDMFE) method for HSI classification is proposed. The proposed RDMFE aims to project the multiple features into a common low-rank subspace, where the specific contributions of different types of features are sufficiently exploited. With low-rank constraint, RDMFE is able to uncover the intrinsic low-dimensional subspace structure of the original data. In order to make the projected features more discriminative, we make the learned representations optimal for classification. With intrinsic information preserving and discrimination capabilities, the learned projection matrix works well in HSI classification tasks. Experimental results on three real hyperspectral datasets confirm the effectiveness of the proposed method.