Illumination Invariant Face Recognition Using Quaternion-Based Correlation Filters

Existing face recognition systems decrease their performance when face images are affected by lighting variations. Recently, several quaternionic representations of face image features and a quaternion-based correlation filter have been combined in order to cope with the effects of having non-properly illuminated face images. The use of this approach has the advantage of using only one training face image per person. In this paper, the original idea based on the unconstrained optimal trade-off quaternion filter (UOTQF) is extended and two additional different correlation filters in quaternionic domain are evaluate: a phase only quaternion filter (POQF) and a separable trade-off quaternion filter (STOQF). Three different quaternion-based correlation filters are designed and conjugated with four face feature extraction methods aiming at obtaining the best combination: a two-level discrete wavelet decomposition (DWT), image differentiation (DIF), discrete cosine transform (DCT) and local binary patterns (LBP). Verification and identification experiments confirms that when combining a quaternionic representation with a quaternion-based correlation filter, both with good discriminative power and illumination invariant properties, an improvement in face recognition accuracy is obtained.     

Facial feature extraction using complex dual-tree wavelet transform

In this paper, we propose a novel method for facial feature extraction using the directional multiresolution decomposition offered by the complex wavelet transform. The dual-tree implementation of complex wavelet transform offered by Selesnick is used (DT-DWT(S)) [I.W., Selesnick, R.G. Baraniuk, N.C. Kingsbury, The dual-tree complex wavelet transform, IEEE Signal Processing Magazine, 6, s.l., IEEE, November 2005, vol. 22, pp. 123–151.]. In the dual-tree implementation, two parallel discrete wavelet transform (DWT) with different lowpass and highpass filters in different scales are used. The linear combination of subbands generated by two parallel DWT is used to generate 6 different directional subbands with complex coefficients. A test statistic, which is derived with absolute value of complex coefficient, whose distribution matches very closely with the directional information in the 6 subbands of the DT-DWT(S) is derived and used for detecting facial feature edges. The use of the complex wavelet transform is motivated by the fact that it helps eliminate the effects of non-uniform illumination, and the directional information provided by the different subbands makes it possible to detect edge features with different directionalities in the corresponding image. Edge information of facial area is enhanced using multiresolution structure of DT-DWT(S). The proposed method also employs an adaptive skin colour model instead of a predefined skin colour statistic. The model is developed with a unimodal Gaussian distribution using the skin region which is extracted excluding the detected edge map obtained from the DT-DWT(S). By combining the edge information obtained by using DT-DWT(S) and the non-skin areas obtained from the pixel statistics, the facial features are extracted. The algorithm is tested over the well known Carnegie Mellon University (CMU) and Marks Weber face databases. The average detection rate of the proposed method using DT-DWT(S) provides up to 9.6% improvement over the same method using discrete wavelet transform (DWT).     

基于小波能量特性的图像增强研究

为了提高图像的清晰度使之更适合于人的视觉特性或机器的识别,需要对图像的特征或边缘进行加强.本文根据图像的小波系数反映了图像的频率和能量的分布特性,提出了依据各尺度的小波分解得到的子图块能量的分布来相应地采取阀值.从而,依据阀值对子图进行系数变换,之后通过小波重构得到最终的增强图像.     

Speech recognition with improved support vector machine using dual classifiers and cross fitness validation

In this research, a new speech recognition method based on improved feature extraction and improved support vector machine (ISVM) is developed. A Gaussian filter is used to denoise the input speech signal. The feature extraction method extracts five features such as peak values, Mel frequency cepstral coefficient (MFCC), tri-spectral features, discrete wavelet transform (DWT), and the difference values between the input and the standard signal. Next, these features are scaled using linear identical scaling (LIS) method with the same scaling method and the same scaling factors for each set of features in both training and testing phases. Following this, to accomplish the training process, an ISVM is developed with best fitness validation. The ISVM consists of two stages: (i) linear dual classifier that finds the same class attributes and different class attributes simultaneously and (ii) cross fitness validation (CFV) method to prevent over fitting problem. The proposed speech recognition method offers 98.2% accuracy.     

Heuristic feature extraction method for BCI with harmony search and discrete wavelet transform

For the brain-computer interface system (BCI), pre-processing has an important role to ensure system performance. However, the speech recognition system using electroencephalogram (EEG) is weak against temporal effects. Therefore, in general cases, wavelet transform has been used to cope with the temporal effects and non-stationary characteristic of EEG. The discrete version of wavelet transform, called DWT, requires a filter of the system for use in downsampling the signal. In other words, it is important to determine the suitable type of filter. In many cases, it is difficult to find an adequate filter for DWT because of differences in the characteristics of the input signal. In this paper, we proposed a heuristic approach to finding the optimal filter of the system for EEG signals. The harmony search algorithm (HSA) was used for finding of the optimal filter. In the learning process with the EEG system, the optimal wavelet filter could be found, which is automatically designed for subject personality.     

A new method for expert target recognition system: Genetic wavelet extreme learning machine (GAWELM)

In last year’s, the expert target recognition has been become very important topic in radar literature. In this study, a target recognition system is introduced for expert target recognition (ATR) using radar target echo signals of High Range Resolution (HRR) radars. This study includes a combination of an adaptive feature extraction and classification using optimum wavelet entropy parameter values. The features used in this study are extracted from radar target echo signals. Herein, a genetic wavelet extreme learning machine classifier model (GAWELM) is developed for expert target recognition. The GAWELM composes of three stages. These stages of GAWELM are genetic algorithm, wavelet analysis and extreme learning machine (ELM) classifier. In previous studies of radar target recognition have shown that the learning speed of feedforward networks is in general much slower than required and it has been a major disadvantage. There are two important causes. These are: (1) the slow gradient-based learning algorithms are commonly used to train neural networks, and (2) all the parameters of the networks are fixed iteratively by using such learning algorithms. In this paper, a new learning algorithm named extreme learning machine (ELM) for single-hidden layer feedforward networks (SLFNs) Ahern et al., 1989, Al-Otum and Al-Sowayan, 2011, Avci et al., 2005a, Avci et al., 2005b, Biswal et al., 2009, Frigui et al., in press, Cao et al., 2010, Guo et al., 2011, Famili et al., 1997, Han and Huang, 2006, Huang et al., 2011, Huang et al., 2006, Huang and Siew, 2005, Huang et al., 2009, Jiang et al., 2011, Kubrusly and Levan, 2009, Le et al., 2011, Lhermitte et al., in press, Martínez-Martínez et al., 2011, Matlab, 2011, Nelson et al., 2002, Nejad and Zakeri, 2011, Tabib et al., 2009, Tang et al., 2011, which randomly choose hidden nodes and analytically determines the output weights of SLFNs, to eliminate the these disadvantages of feedforward networks for expert target recognition area. Then, the genetic algorithm (GA) stage is used for obtaining the feature extraction method and finding the optimum wavelet entropy parameter values. Herein, the optimal one of four variant feature extraction methods is obtained by using a genetic algorithm (GA). The four feature extraction methods proposed GAWELM model are discrete wavelet transform (DWT), discrete wavelet transform–short-time Fourier transform (DWT–STFT), discrete wavelet transform–Born–Jordan time–frequency transform (DWT–BJTFT), and discrete wavelet transform–Choi–Williams time–frequency transform (DWT–CWTFT). The discrete wavelet transform stage is performed for optimum feature extraction in the time–frequency domain. The discrete wavelet transform stage includes discrete wavelet transform and calculating of discrete wavelet entropies. The extreme learning machine (ELM) classifier is performed for evaluating the fitness function of the genetic algorithm and classification of radar targets. The performance of the developed GAWELM expert radar target recognition system is examined by using noisy real radar target echo signals. The applications results of the developed GAWELM expert radar target recognition system show that this GAWELM system is effective in rating real radar target echo signals. The correct classification rate of this GAWELM system is about 90% for radar target types used in this study.     

Variable lighting face recognition using discrete wavelet transform

This paper presents a new discrete wavelet transform (DWT) based illumination normalization approach for face recognition under varying lighting conditions. Our method consists of three steps. Firstly, DWT-based denoising technique is employed to detect the illumination discontinuities in the detail subbands. And the detail coefficients are updated with using the obtained discontinuity information. Secondly, a smooth version of the input image is obtained by applying the inverse DWT on the updated wavelet coefficients. Finally, multi-scale reflectance model is presented to extract the illumination invariant features. The merit of the proposed method is it can preserve the illumination discontinuities when smoothing image. Thus it can reduce the halo artifacts in the normalized images. Moreover, only one parameter involved and the parameter selection process is simple and computationally fast. Experiments are carried out upon the Yale B and CMU PIE face databases, and the results demonstrate the proposed method can achieve satisfactory recognition rates under varying illumination conditions.     

基于分块小波变换与奇异值阈值压缩的人脸特征提取与识别算法

提出了一种基于分块小波变换与奇异值阈值压缩的人脸特征提取与识别算法.该方法首先对人脸图像进行分块小波变换,并根据图像块的位置分布选取不同的频率分量,然后对该分量进行奇异值阈值压缩与特征融合,最后在ORL人脸库上利用最近邻分类器对该特征进行分类识别,验证了算法的有效性.     

高性能的9/7小波滤波器组设计

提出了一种二进制系数的9/7双正交小波滤波器组.首先对小波滤波器组的完全重构条件和双正交条件进行三角基函数变换和因式分解,然后对求出的小波滤波器系数进行优化设计,从而得到一组滤波器系数都为二进制分数的9/7双正交小波滤波器组,其离散小波变换只需采用简单的"移位-加"即可.理论分析和实验表明:改进的9/7小波滤波器组具有与CDF9/7小波滤波器组相近的性能,同时大大降低了离散小波变换的算法复杂度.因此,非常适用于大规模集成电路的实现.     

Gabor小波变换和NMF结合的人脸识别

针对训练样本较少的情况,提出了一种新的人脸识别方法。采用Gabor小波变换得到不同的子图信息,从子图中提取特征;对每个滤波器滤波产生的子图分别进行非负矩阵分解以实现数据降维及特征选择;设计两层分类器完成图像的分类识别,采用基于距离的最近邻分类器对图像进行第一层分类识别,通过对第一层分类结果进行统计记票,获得最终的识别结果。在Yale人脸库中进行实验,实验结果表明,给出的方法有效地提高了人脸识别率。     

基于Gabor小波特征抽取和支持向量机的人脸识别

文章利用Gabor小波对位置误差、光线等因素具有强的鲁棒性的优点,将人脸图像在一定格点上取大小和方向不同的2D-Gabor小波变换,取变换系数幅值作为特征向量,送入支持向量机中进行分类。有效地结合了Gabor小波的特征抽取能力和支持向量机的分类能力,并对AT&T人脸库进行性别分类和人脸识别,得到了较高的识别率。     

基于稀疏表示与小波特征的人脸识别分层框架

基于稀疏表示的人脸识别研究,非线性特征的选择研究较少。提出分层使用人脸图像的小波特征,进行稀疏表示人脸识别框架。框架首先对样本人脸进行小波变换,构造小波低频和小波高频过完备人脸字典;识别阶段首先使用人脸图像的小波低频特征进行稀疏表示,计算类别模糊稀疏,然后根据模糊系数输出类别标签或进行高频特征的稀疏表示与识别。实验结果表明,基于小波特征和稀疏表示的人脸识别分层框架提高了识别的准确率,且对遮挡很鲁棒。     

基于局部小波变换与DCT的人脸识别算法

提出了一种基于局部小波变换和离散余弦变换(DiscreteCosineTransform,DCT)相结合的人脸识别方法,该算法首先利用小波变换对人脸图像做适当层次的小波分解,然后通过离散余弦变换对低频分量作进一步的特征提取和压缩,得到人脸识别特征,最后利用欧氏距离和最近邻分类器进行识别。基于ORL人脸数据库的实验结果表明了该算法的有效性。     

Face recognition using decimated redundant discrete wavelet transforms

As discrete wavelet transform (DWT) is sensitive to the translation/shift of input signals, its effectiveness could be lessened for face recognition, particularly when the face images are translated. To alleviate drawbacks resulted from this translation effect, we propose a decimated redundant DWT (DRDWT)-based face recognition method, where the decimation-based DWTs are performed on the original signal and its 1-stepshift, respectively. Even though the DRDWT realizes the decimation, it enables us to explore the translation invariant DWT representation for the periodic shifts of the probe image that is the most similar to the gallery images. Therefore, it can solve the problem of translation sensitivity of the original DWT and address the translation effect occurring between the probe image and the gallery image. To further improve the recognition performance, we combine the global wavelet features obtained from the entire face and the local wavelet features obtained from face patches to represent both holistic and detail facial features, apply separate classifiers to global and local features and combine the resulted global and local classifiers to form an ensemble classifier. Experimental results reported for the FERET and FRGCv2.0 databases show the effectiveness of the DRDWT method and quantify its performance.     

Wavelet transform feature extraction from human PPG, ECG, and EEG signal responses to ELF PEMF exposures: A pilot study

This paper presents the experimental pilot study to investigate the effects of pulsed electromagnetic field (PEMF) at extremely low frequency (ELF) in response to photoplethysmographic (PPG), electrocardiographic (ECG), electroencephalographic (EEG) activity. The assessment of wavelet transform (WT) as a feature extraction method was used in representing the electrophysiological signals. Considering that classification is often more accurate when the pattern is simplified through representation by important features, the feature extraction and selection play an important role in classifying systems such as neural networks. The PPG, ECG, EEG signals were decomposed into time-frequency representations using discrete wavelet transform (DWT) and the statistical features were calculated to depict their distribution. Our pilot study investigation for any possible electrophysiological activity alterations due to ELF PEMF exposure, was evaluated by the efficiency of DWT as a feature extraction method in representing the signals. As a result, this feature extraction has been justified as a feasible method.     

小波滤波器低功耗并行的VLSI结构设计

提出一种基于行和提升算法,实现JPEG2000编码系统中的小波正反变换(discretewavelettransform)的低功耗、并行的VLSI结构设计方法·利用该方法所得结构一次处理两行数据,分时复用行处理器,使行处理器内以及行、列处理器实现并行处理,且最小化行缓存·对称扩展通过嵌入式电路实现,整个结构采用流水线设计方法优化,加快了变换速度,增加了硬件资源利用率,降低了功耗,效率几乎达到100%·小波滤波器正反变换结构已经经过FPGA验证,可作为单独的IP核应用于正在开发的JPEG2000图像编解码芯片中·     

Admissible wavelet packet features based on human inner ear frequency response for Hindi consonant recognition

It was observed that for non-stationary and quasi-stationary signals, wavelet transform has been found to be an effective tool for the time–frequency analysis. In the recent years wavelet transform being used for feature extraction in speech recognition applications. Here a new filter structure using admissible wavelet packet analysis is proposed for Hindi phoneme recognition. These filters have the benefit of having frequency bands spacing similar to the auditory Equivalent Rectangular Bandwidth (ERB) scale whose central frequencies are equally distributed along the frequency response of human cochlea. The phoneme recognition performance of proposed feature is compared with the standard baseline features and 24-band admissible wavelet packet-based features using a Hidden Markov Model (HMM) based classifier. Proposed feature shows better performance compared to conventional features for Hindi consonant recognition. To evaluate the robustness of proposed feature in the noisy environment NOISEX-92 database has been used.     

Hierarchical fusion of multi-spectral face images for improved recognition performance

This paper presents a two level hierarchical fusion of face images captured under visible and infrared light spectrum to improve the performance of face recognition. At image level fusion, two face images from different spectrums are fused using DWT based fusion algorithm. At feature level fusion, the amplitude and phase features are extracted from the fused image using 2D log polar Gabor wavelet. An adaptive SVM learning algorithm intelligently selects either the amplitude or phase features to generate a fused feature set for improved face recognition. The recognition performance is observed under the worst case scenario of using single training images. Experimental results on Equinox face database show that the combination of visible light and short-wave IR spectrum face images yielded the best recognition performance with an equal error rate of 2.86%. The proposed image-feature fusion algorithm also performed better than existing fusion algorithms.     

小波阈值去噪技术研究及其在信号处理中的应用

阈值函数的选取以及阈值的确定是小波收缩消噪的关键问题,阐述了小波变换及小波阈值去噪的基本原理.基于噪声和信号在小波变换下表现出截然不同的性质:噪声对应的小波变换系数将随着尺度的增大迅速衰减,建立了小波收缩消噪的统一框架.在该框架下总结了各种阈值函数的形式以及阈值确定的方式,研究了它们的性能及特点.仿真实验结果表明,该方法既能有效地去除信号噪声,又能较好地保留原信号中的突变信息.