基于能量的时频特征提取研究

有效地从含有噪声的非平稳信号中提取特征是进行非平稳信号分类等研究的基础。应用流域算法,对含有高斯白噪声的非平稳信号的时频分布图进行分割,并根据能量占优的准则对其合并,提出了一种基于能量的特征提取方法。仿真结果表明该方法能有效地提取特征量,且对高斯白噪声具有很好的抗噪性能。     

Classification and feature extraction of AVIRIS data

The processing of Airborne Visible-Infrared Imaging Spectrometer (AVIRIS) data is discussed both in terms of feature extraction and classification. The recently proposed decision boundary feature extraction method is reviewed and then applied in experiments. Results of classifications for AVIRIS data from Iceland 1991 are given with emphasis on geological applications. The classifiers used include neural network methods and statistical approaches. The decision boundary feature extraction method shows excellent performance for these data     

Range-spread target detection using the time-frequency feature based on sparse representation

The wideband radar transmitting the linear frequency modulation signal often processes its echoes by the stretched processing. This paper deals with the range-spread target detection in white complex Gaussian noise. Here, we propose a new detection method for the range-spread target based on sparse representation, which selects the time-frequency feature to realise the target detection. It can be simply described as follows: first, the sketched signal is reconstructed from its noisy measurements by basis pursuit de-noising (BPDN); scatterers on the target are determined by its reconstruction and used to calculate the Wigner distribution; for the target embedded in noise, the time-frequency feature in its power-density spectrum is compared with the decision threshold. Meanwhile, the median absolute deviation (MAD) is adopted to estimate the noise variance. The mainly novelties can be concluded as follows: the Fourier matrix is selected to sparsely represent the sketched signal; the sparsity is used to improve the SNR of the received echoes; the Wigner transform is utilised to acquire the time-frequency feature of the range-spread target. Both the optimisation theory and time-frequency representation are introduced to solve the target detection problem. Experimental results on the raw data show that the proposed detector outperforms the conventional methods.     

Pattern recognition using discriminative feature extraction

We propose a new design method, called discriminative feature extraction for practical modular pattern recognizers. A key concept of discriminative feature extraction is the design of an overall recognizer in a manner consistent with recognition error minimization. The utility of the method is demonstrated in a Japanese vowel recognition task     

QRS feature extraction using linear prediction

This communication proposes a method called linear prediction (a high performant technique in digital speech processing) for analyzing digital ECG signals. There are several significant properties indicating that ECG signals have an important feature in the residual error signal obtained after processing by Durbin's linear prediction algorithm. This communication also indicates that the prediction order need not be more than two for fast arrhythmia detection. The ECG signal classification puts an emphasis on the residual error signal. For each ECG's QRS complex, the feature for recognition is obtained from a nonlinear transformation which transforms every residual error signal to a set of three states pulse-code train relative to the original ECG signal. The pulse-code train has the advantage of easy implementation in digital hardware circuits to achieve automated ECG diagnosis. The algorithm performs very well in feature extraction in arrhythmia detection. Using this method, our studies indicate that the PVC (premature ventricular contraction) detection has at least a 92 percent sensitivity for MIT/BIH arrhythmia database.     

Generalized feature extraction using expansion matching

A novel generalized feature extraction method based on the expansion matching (EXM) method and on the Karhunen-Loeve transform (KLT) is presented. The method provides an efficient way to locate complex features of interest like corners and junctions with reduced number of filtering operations. The EXM method is used to design optimal detectors for a set of model elementary features. The KL representation of these model EXM detectors is used to filter the image and detect candidate interest points from the energy peaks of the eigen coefficients. The KL coefficients at these candidate points are then used to efficiently reconstruct the response and differentiate real junctions and corners from arbitrary features in the image. The method is robust to additive noise and is able to successfully extract, classify, and find the myriad compositions of corner and junction features formed by combinations of two or more edges or lines. This method differs from previous works in several aspects. First, it treats the features not as distinct entities, but as combinations of elementary features. Second, it employs an optimal set of elementary feature detectors based on the EM approach. Third, the method incorporates a significant reduction in computational complexity by representing a large set of EXM filters by a relatively small number of eigen filters derived by the KL transform of the basic EXM filter set. This is a novel application of the KL transform, which is usually employed to represent signals and not impulse responses as in our present work.     

利用小波和分形理论进行水下回波的特征提取

该文首先分析了五类湖底回波的不同尺度下小波子空间的能量特征和分形维特征;然后将这些特征矢量作为分类的特征,并根据特征本身的离散程度对其进行加权;最后采用最小距离分类器对其进行分类,取得了 96.11％的分类正确率。     

浅水区水下爆炸直达声辨识与时频分析

为有效截取直达声分量以分析真实的水下爆炸声源特性,提出一种利用局部相关峰进行直达信号辨识的标记算法,并建立起算法结果的评价函数,然后结合浅水区水下爆炸实验,对比射线理论计算所得直达声分量的数目,初步验证了算法合理性,最后对所捕获的最优直达声片段(宽度约1.8 ms)进行希尔伯特-黄变换(HHT),分析频谱特性。结果表明：直达声压级时间序列具有良好的自相关性,且在近程条件下,其相对排列特征能近似保持稳定;该算法可以获得较高的局部相关峰,使得直达声片段能够被清晰地标记出来,尤其是在超近程条件下,相关峰可达0.9以上;爆炸声源的主频带稳定在0~10 kHz,且峰值频率约1 kHz,但是当传播距离较远时,其形状会明显受到声速剖面影响。     

Real-time vehicle recognition using local feature extraction

A novel feature extraction method based on local textures of images for real-time vehicle recognition tasks is proposed. In particular, feature vectors are extracted from judicious combinations of partitioning and overlapping image blocks with a view to reducing cardinality while retaining sufficient feature information for effective recognition. Experimental results are presented that show a reduction in computational load of 80% and robustness to illumination and noise can be achieved     

Facial feature extraction using a probabilistic approach

Facial features such as lip corners, eye corners and nose tip are critical points in a human face. Robust extraction of such facial feature locations is an important problem which is used in a wide range of applications. In this work, we propose a probabilistic framework and several methods which can extract critical points on a face using both location and texture information. The new framework enables one to learn the facial feature locations probabilistically from training data. The principle is to maximize the joint distribution of location and apperance/texture parameters. We first introduce an independence assumption which enables independent search for each feature. Then, we improve upon this model by assuming dependence of location parameters but independence of texture parameters. We model location parameters with a multi-variate Gaussian and the texture parameters are modeled with a Gaussian mixture model which are much richer as compared to the standard subspace models like principal component analysis. The location parameters are found by solving a maximum likelihood optimization problem. We show that the optimization problem can be solved using various search strategies. We introduce local gradient-based methods such as gradient ascent and Newton's method initialized from independent model locations both of which require certain non-trivial assumptions to work. We also propose a multi-candidate coordinate ascent search and a coarse-to-fine search strategy which both depend on efficiently searching among multiple candidate points. Our framework is compared in detail with the conventional statistical approaches of active shape and active appearance models. We perform extensive experiments to show that the new methods outperform the conventional approaches in facial feature extraction accuracy.     

激光探测水下声源特征的时频分析

激光相干探测水面可以获取水下声源的振动特征。本文将振源分别放在水下80 cm,50 cm和20 cm三个不同深度,以1000 Hz频率振动,通过激光相干探测水面来获取水下振源的振动特征。在信号的特征提取分析中,通过采用小波分解与重构和多尺度分析和Wigner-Ville 分布相结合的方法对信号进行处理。在Wigner-Ville 分布的基础上,增加伪Wigner-Ville 分布和平滑伪Wigner-Ville 分布进行优化。针对WV分布中出现的交叉项干扰,采用Choi-Williams时频分布和Margenau-Hill谱图时频分布加以处理。特征提取与分析的结果表明：小波分析和Wigner-Ville 分布联合的方法对信号降噪和特征提取非常有效。     

普通战车车轮微多普勒特征分析与提取

本电路首先将220V交流电变为12V直流电压来为整机供电,并应用气敏传感器MQ-2把瓦斯气体浓度这一非电量转换为电信号,再经由运算放大器μA709将该信号与门限电压比较,由电压比较器转化为数字信号并控制由LM555数模集成电路组成的双稳态触发电路最后应用继电器来控制报警电路和通风设备,从而实现报警。     

基于小波分解及KCN的雷达目标特征提取

讨论了利用一维距离像进行雷达目标识别的特征提取。从缩减表征距离像的特征维数和表征目标所需特征数出发，提出了一种基于小波分解及KCN的目标特征提取方法。为比较不同特征提取方法及所提取特征的性能，引入了Fisher距离来表明各类的类内紧致性和类间分离性。实验结果表明能够有效地进行特征提取。     

Facial expression feature extraction using hybrid PCA and LBP

In order to recognize facial expression accurately, the paper proposed a hybrid method of principal component analysis (PCA) and local binary pattern (LBP). Firstly, the method of eight eyes segmentation was introduced to extract the effective area of facial expression image, which can reduce some useless information to subsequent feature extraction. Then PCA extracted the global grayscale feature of the whole facial expression image and reduced the data size at the same time. And LBP extracted local neighbor texture feature of the mouth area, which contributes most to facial expression recognition. Fusing the global and local feature will be more effective for facial expression recognition. Finally, support vector machine (SVM) used the fusion feature to complete facial expression recognition. Experiment results show that, the method proposed in this paper can classify different expressions more effectively and can get higher recognition rate than the traditional recognition methods.     

基于Log-Gabor小波相位一致的掌纹线特征提取

研究掌纹线的特点,提出了一种基于相位一致的掌纹线特征提取方法,多方向、多尺度的Log-Gabor小波用来计算掌纹图像的相位一致不变量以获得更丰富的掌纹线特征信息和精确的特征定位.方法提取的线特征不仅包含掌纹的结构信息,还具有纹线的强度和宽度信息;此外,由于使用图像的相位信息,方法受图像亮度和对比度影响较小,提取的特征比较稳定.方法在PolyU掌纹库上测试,结果(EER=0.6%)表明线特征提取的良好效果.     

利用小波变换特征提取的通信辐射源个体识别方法

为解决非协作通信条件下对通信辐射源的个体识别问题,提出了一种基于小波变换特征提取的个体识别方法。该方法对非协同通信的接收信号进行小波变换,通过计算类间分离度筛选最优小波基提取特征向量,并根据特征分布选取特定小波基下的小波系数复杂度作为信噪比参考值辅助个体识别。仿真结果表明,在信噪比变化的环境中及通信辐射源个体差异较小的情况下有较好的识别效果,从而验证了该方法的有效性。      

一种局部稀疏判别投影算法

提取有效特征是模式识别中的关键步骤。流形学 习算法能有效处理样本的非线性,而 稀疏表示表现出具有较好的鲁棒性。为了提取具有判别特性和鲁棒的特征,本文结合稀疏表 示和判别准则,提出了一种局部稀疏表示和判别分析的特征提取算法,即局部稀疏判别投影 算法,并应用于人脸识别。算法通过保持数据间的局部稀疏性和最大化不同类别数据间的 可分性,使得降维后的数据具有稀疏性和可分性,因此有利于后续的分类。在ORL和YALE两 个开放人脸数据库上进行了实验,实验结果表明,算法具有较高的识别性,验证了算法的正 确性和有效性。     

Stochastic kinematic modeling and feature extraction for gait analysis

This research presents a new model-based approach toward the three-dimensional (3-D) tracking and extraction of gait and human motion. We suggest the use of a hierarchical, structural model of the human body that introduces the concept of soft kinematic constraints. These constraints take the form of a priori, stochastic distributions learned from previous configurations of the body exhibited during specific activities; they are used to supplement an existing motion model limited by hard kinematic constraints. We use time-varying parameters of the structural model to measure gait velocity, stance width, stride length, stance times, and other gait variables with multiple degrees of accuracy and robustness. To characterize tracking performance, we also introduce a novel geometric model of expected tracking failures. We demonstrate and quantify the performance of the suggested models using multi-view, video sequences of human movement captured in a complex home environment.     

Digital watermark extraction using support vector machine with principal component analysis based feature reduction

This paper proposes a new approach for watermark extraction using support vector machine (SVM) with principal component analysis (PCA) based feature reduction. In this method, the original cover image is decomposed up to three level using lifting wavelet transform (LWT), and lowpass subband is selected for data hiding purpose. The lowpass subband is divided into small blocks, and a binary watermark is embedded into the original cover image by quantizing the two maximum coefficients of the block. In order to extract watermark bits with maximum correlation, SVM based binary classification approach is incorporated. The training and testing patterns are constructed by employing a reduced set of features along with block coefficients. Firstly, different features are obtained by evaluating the statistical parameters of each block coefficients, and then PCA is utilized to reduce this feature set. As far as security is concerned, randomization of coefficients, blocks, and watermark bits enhances the security of system. Furthermore, energy compaction property of LWT increases the robustness in comparison to conventional wavelet transform. A comparison of the proposed method with some of the recent techniques shows remarkable improvement in terms of robustness and security of the watermark.