基于线性子空间和商图像理论的人脸光照补偿

光照是影响人脸识别率的主要因素,它已成为人脸识别技术发展的瓶颈。根据商图像理论,在所构造的低维训练集上对待识别的图像进行光照条件估计,通过加光和去光两种方法,实现了光照补偿的目的,并通过识别实验验证了其补偿效果。     

基于球面谐波基图像的任意光照下的人脸识别

提出了一种基于球面谐波基图像的光照补偿算法,用以在任意光照条件下进行人脸识别.算法分两步进行：光照估计和光照补偿.基于人脸形状大致相同和每个人脸的反射率基本相等的假设,首先估计了输入人脸图像光照的9个低频谐波系数.根据光照估计的结果,提出了两种光照补偿方法：纹理图像和差图像.纹理图像为输入图像与其光照辐照图之商,与输入图像的光照条件无关.差图像为输入图像与平均人脸在相同光照下的图像之差,通过减去平均人脸在相同光照下的图像,减弱了光照的影响.在CMU-PIE人脸库和Yale B人脸库上的实验表明,通过光照补偿,不同光照下人脸图像识别率有了很大提高.     

基于形态学商图像的光照归一化算法

复杂光照条件下的人脸识别是一个困难但需迫切解决的问题,为此提出了一种有效的光照归一化算法.该方法根据面部光照特点,基于数学形态学和商图像技术对各种光照条件下的人脸图像进行归一化处理,并且将它发展到动态地估计光照强度,进一步增强消除光照和保留特征的效果.与传统的技术相比,该方法无须训练数据集以及假定光源位置,并且每人只需一幅注册图像.在耶鲁人脸图像库B上的测试表明,该算法以较小的计算代价取得了优良的识别性能.     

复杂光照环境下视频人脸序列的自动检测方法

基于视频序列人脸自动检测是人脸跟踪、识别等研究的基础。提出了一种结合图像增强技术、gabor特征变 换和adaboost算法的视频序列人脸检测方法,其主要思想是使用图像增强技术对图像进行光照补偿,减轻不同的光 照条件(如局部的阴影和高亮等)对检测结果的影响。该方法首先通过高频增强滤波强化图像的边缘和细节信息,用 基于直方图的技术来调节图像的亮度,然后应用gabor小波变换进行特征抽取,最后采用adaboost方法训练样本,完 成人脸的检测。实验表明,该方法能够在不同的光照条件下准确检测出人脸,显示出较强的鲁棒性。     

互补色小波颜色恒常性/白平衡方法

借助于互补色小波, 本文提出一种新的颜色恒常性统计方法.分析表明:标准光照图像的互补色小波子带关系, 可以利用联合拉普拉斯分布来进行描述.统计学习标准光照图像, 可获得拉普拉斯分布的参数, 为图像建立起标准光照的基准模型.该基准模型可为光照偏移(颜色恒常偏移)的图像提供光照补偿依据, 使偏光图像通过光照补偿恢复为标准光照图像, 从而得到光照参数.基于该基准模型对补偿光照参数进行最大似然估计的实验结果表明:本文所提方法的处理效果与列出的最好文献算法相当, 其在常用数据库上估计到的光照参数误差中值小0.1°, 而均值和最大值则小0.3°.     

复杂光照环境下视频人脸序列的自动检测方法

基于视频序列人脸自动检测是人脸跟踪、识别等研究的基础.提出了一种结合图像增强技术、gabor特征变换和adaboost算法的视频序列人脸检测方法,其主要思想是使用图像增强技术对图像进行光照补偿,减轻不同的光照条件(如局部的阴影和高亮等)对检测结果的影响.该方法首先通过高频增强滤波强化图像的边缘和细节信息,用基于直方图的技术采调节图像的亮度,然后应用gabor小波变换进行特征抽取,最后采用adaboost方法训练样本,完成人脸的检测.实验表明,该方法能够在不同的光照条件下准确检测出人脸,显示出较强的鲁棒性.     

基于小波变换和光照补偿的人脸识别方法

针对光照对人脸识别影响的问题,提出一种结合小波变换和光照补偿的人脸识别方法。该方法首先利用离散小波变换将人脸图像的低频子带和高频子带分离,在小波变换的低频子带上分别进行直方图均衡化和对数变换,将处理后的低频子带进行融合构成新的低频子带。接着对高频子带进行阈值去噪后乘以一个标量,构成新的高频子带。最后利用小波逆变换重构出新的人脸图像并利用PCA算法进行识别。实验结果表明,该方法能有效地削弱光照的影响,提高人脸识别率。     

基于Armlets的人脸光照补偿

提出了一种用于非均匀光照条件下人脸识别的光照补偿算法。该算法通过在对数域计算2维Armlets多小波变换来实现人脸光照补偿,然后直接在对数域进行人脸识别。在Yale B人脸库中与其他光照补偿算法进行了比较,实验结果表明,该方法的平均误识率仅为0.18%,优于现有的其他算法。     

人脸识别中基于多小波变换的光照补偿

提出了一种用于非均匀光照条件下人脸识别的光照补偿算法。该算法在对数域计算2维多小波变换来实现人脸光照补偿,然后直接在对数域进行人脸识别。在Yale B人脸库中与其它光照补偿算法进行了比较,实验结果表明,该方法的平均误识率仅为0.70%,优于现有的绝大多数算法。     

改进的手指静脉图像识别算法仿真研究

为了解决传统 PCA 方法和小波矩融合 PCA 方法在光照条件变化较大时不能有效抽取图像局部特征,导致识别率较低的问题,提出了一种直接基于子图像向量的线性鉴别分析方法,即模块 PCA 手指静脉特征提取算法.上述算法通过对图像进行分块,利用 PCA 对分块得到的子图进行鉴别分析.由于使用子图像矩阵,能有效地抽取图像的局部特征,避免使用奇异值分解理论,过程简便.实验结果表明,所提出的方法在识别性能上明显优于传统 PCA 算法和小波矩融合 PCA 方法,识别率可以分别提高 5.6 和 4.1 个百分点.     

A method of illumination compensation for human face image based on quotient image

Illumination variation is one of the critical factors affecting face recognition rate. A novel approach for human face illumination compensation is presented in this paper. It constructs the nine-dimension face illumination subspace based on quotient image. In addition, with the aim to improve algorithm efficiency, a half-face illumination image is proposed and the low-dimension training set of the face image under different illumination conditions are obtained by means of PCA and wavelet transform. After processing, two different illumination compensation strategies are given: one is adding light, and the other is removing light. Based on the illumination compensation strategy, we implement the typical illumination sample image synthesis and the standard illumination sample image synthesis on a PCA feature subspace and a wavelet transform subspace, respectively, and the illumination compensation of the gray images and the color images are further realized. Experimental results based on the Yale Face Database B, the Extended Yale Face Database B and the CAS-PEAL Face Database indicate that execution time after compensation is approximately half the time and face recognition rate is improved by 20% compared with that of the original images.     

一种基于EMD的人脸图像光照问题处理方法

鉴于经验模态分解（EMD）算法的无参数特性和基于数据驱动的自适应分析,从EMD算法筛选过程中插值点和差值算法选取的角度出发,提出了一种标准EMD的改进算法。用改进的EMD算法分解需要识别的人脸图像,得到从整体上有效消除了光照变化影响的原人脸图像的重构图像,并将重构图像用于识别。通过在Yale B人脸库上的实验结果表明,将提出的光照处理方法应用到人脸识别中可以取得较好的效果。     

Illumination invariant extraction for face recognition using neighboring wavelet coefficients

The features of a face can change drastically as the illumination changes. In contrast to pose position and expression, illumination changes present a much greater challenge to face recognition. In this paper, we propose a novel wavelet based approach that considers the correlation of neighboring wavelet coefficients to extract an illumination invariant. This invariant represents the key facial structure needed for face recognition. Our method has better edge preserving ability in low frequency illumination fields and better useful information saving ability in high frequency fields using wavelet based NeighShrink denoise techniques. This method proposes different process approaches for training images and testing images since these images always have different illuminations. More importantly, by having different processes, a simple processing algorithm with low time complexity can be applied to the testing image. This leads to an easy application to real face recognition systems. Experimental results on Yale face database B and CMU PIE Face Database show that excellent recognition rates can be achieved by the proposed method.     

基于有效光照估计的复杂光照人脸识别

基于光照估计的光照不变量提取是提高复杂光照人脸识别性能的一种有效方法。以往算法仅考虑光照缓慢变化特性从人脸图像中估计光照,无法获取准确的光照和光照不变量。综合考虑图像的成像原理、光照缓慢变化特性和复杂照明环境,结合图像融合和平滑滤波,提出一种有效的人脸图像光照估计、光照不变量提取方法。所提算法能较好地处理阴影边缘问题,提取含有丰富面部细节特征、更接近于人脸本征的光照不变量。复杂光照Yale B+和CAS-PEAL-R1人脸库上的实验结果表明所提算法具有高效性。     

基于小波变换和去噪模型的光照不变人脸识别

针对正面光照人脸识别的难点,提出了一种应用小波变换和去噪模型的光照不变人脸识别算法。利用对图像的高频小波系数进行处理并运用去噪模型,提取光照人脸图像中的光照不变量,同时增强图像边缘特征,这有利于提取的光照不变量保持更多的人脸识别信息。在Yale B和CMU PIE人脸库上的实验结果表明,所提算法可以显著提高光照人脸图像的识别率。     

Multiscale morphology based illumination normalization with enhanced local textures for face recognition

A key challenge of face recognition is to obtain illumination invariant face images while preserving the discriminative features. The locations and shapes of small-scale features (e.g. eyebrows, eyes, nostrils, a mouth, etc.) are usually treated as key features for face recognition. However, it has also been observed that the local texture information of facial regions contains intrinsic facial features and needs to be enhanced to improve performance. To compensate for the illumination effects that appeared while extracting both the small-scale features and the texture information, we used multiscale morphological techniques. We used a generalized dynamic morphological quotient image (GDMQI) method based on Retinex theory and multiscale morphological closing to solve the artifact problem discussed in previous works. The proposed method consisted of two main steps: (i) illumination estimation and (ii) texture enhancement. The proposed method showed improved performance when using the CMU PIE, AR and Extended Yale-B databases.     

Multiscale facial structure representation for face recognition under varying illumination

Facial structure of face image under lighting lies in multiscale space. In order to detect and eliminate illumination effect, a wavelet-based face recognition method is proposed in this paper. In this work, the effect of illuminations is effectively reduced by wavelet-based denoising techniques, and meanwhile the multiscale facial structure is generated. Among others, the proposed method has the following advantages: (1) it can be directly applied to single face image, without any prior information of 3D shape or light sources, nor many training samples; (2) due to the multiscale nature of wavelet transform, it has better edge-preserving ability in low frequency illumination fields; and (3) the parameter selection process is computationally feasible and fast. Experiments are carried out upon the Yale B and CMU PIE face databases, and the results demonstrate that the proposed method achieves satisfactory recognition rates under varying illumination conditions.     

基于多尺度分析的人脸识别比较研究

在分析Gabor小波的基础上,提出了一种变采样率Gabor小波的方法,与传统的Gabor小波相比,其识别效果得到大幅提高。该方法采用Curvelet、Log-Gabor小波和Contourlet三种方法结合主分量分析应用于人脸识别。对比实验结果表明,针对表情变化,Curvelet变换不仅识别性能最佳、速度也最快;而针对光照变化,Contourlet综合性能最好,对光照变化具有较强的鲁棒性。综合而言,使用Contourlet变换对图像进行特征提取效果非常好,它能很好地表达人脸的主要信息,是对人脸图像的一种稀疏的、有效的表达。