Facial Feature Extraction Method Based on Coefficients of Variances

Principal Component Analysis （PCA） and Linear Discriminant Analysis （LDA） are two popular feature extraction techniques in statistical pattern recognition field. Due to small sample size problem LDA cannot be directly applied to appearance-based face recognition tasks. As a consequence, a lot of LDA-based facial feature extraction techniques are proposed to deal with the problem one after the other. Nullspace Method is one of the most effective methods among them. The Nullspace Method tries to find a set of discriminant vectors which maximize the between-class scatter in the null space of the within-class scatter matrix. The calculation of its discriminant vectors will involve performing singular value decomposition on a high-dimensional matrix. It is generally memory- and time-consuming. Borrowing the key idea in Nullspace method and the concept of coefficient of variance in statistical analysis we present a novel facial feature extraction method, i.e., Discriminant based on Coefficient of Variance （DCV） in this paper. Experimental results performed on the FERET and AR face image databases demonstrate that DCV is a promising technique in comparison with Eigenfaces, Nullspace Method, and other state-of-the-art facial feature extraction methods.     

Statistical learning based facial animation

To synthesize real-time and realistic facial animation, we present an effective algorithm which combines image- and geometry-based methods for facial animation simulation. Considering the numerous motion units in the expression coding system, we present a novel simplified motion unit based on the basic facial expression, and construct the corresponding basic action for a head model. As image features are difficult to obtain using the performance driven method, we develop an automatic image feature recognition method based on statistical learning, and an expression image semi-automatic labeling method with rotation invariant face detection, which can improve the accuracy and efficiency of expression feature identification and training. After facial animation redirection, each basic action weight needs to be computed and mapped automatically. We apply the blend shape method to construct and train the corresponding expression database according to each basic action, and adopt the least squares method to compute the corresponding control parameters for facial animation. Moreover, there is a pre-integration of diffuse light distribution and specular light distribution based on the physical method, to improve the plausibility and efficiency of facial rendering. Our work provides a simplification of the facial motion unit, an optimization of the statistical training process and recognition process for facial animation, solves the expression parameters, and simulates the subsurface scattering effect in real time. Experimental results indicate that our method is effective and efficient, and suitable for computer animation and interactive applications.     

Video color conceptualization using optimization

Color conceptualization aims to propagate"color concepts"from a library of natural color images to the input image by changing the main color.However,the existing method may lead to spatial discontinuities in images because of the absence of a spatial consistency constraint.In this paper,to solve this problem,we present a novel method to force neighboring pixels with similar intensities to have similar color.Using this constraint,the color conceptualization is formalized as an optimization problem with a quadratic cost function.Moreover,we further expand two-dimensional(still image)color conceptualization to three-dimensional(video),and use the information of neighboring pixels in both space and time to improve the consistency between neighboring frames.The performance of our proposed method is demonstrated for a variety of images and video sequences.     

Content-based facial image authentication via statistic features

A statistic approach for facial image authentication is proposed. The typical model of digital signature generation and facial image authenticating is discussed firstly. Then the interesting region of facial image is extracted by a set of haar-like features. To prepare enough training samples, a sample enlarging method based power low transformation （PLT） is proposed. The statistic feature of a facial image is extracted by calculating the coefficients of it＇s projection onto a subspace trained offiine by the enlarged sample set. The experimental results demonstrated the capability to distinguish the content-preserving operations and the malicious operations.     

Facial Beautification Method Based on Age Evolution

This paper proposes a new facial beautification method using facial rejuvenation based on the age evolution. Traditional facial beautification methods only focus on the color of skin and deformation and do the transformation based on an experimental standard of beauty. Our method achieves the beauty effect by making facial image looks younger, which is different from traditional methods and is more reasonable than them. Firstly, we decompose the image into different layers and get a detail layer. Secondly, we get an age-related parameter： the standard deviation of the Gaussian distribution that the detail layer follows, and the support vector machine （SVM） regression is used to fit a function about the age and the standard deviation. Thirdly, we use this function to estimate the age of input image and generate a new detail layer with a new standard deviation which is calculated by decreasing the age. Lastly, we combine the original layers and the new detail layer to get a new face image. Experimental results show that this algo- rithm can make facial image become more beautiful by facial rejuvenation. The proposed method opens up a new way about facial beautification, and there are great potentials for applications.     

一种基于自然图像统计模型的图像合成检测方法

Nowadays, digital images can be easily tampered due to the availability of powerful image processing software. As digital cameras continue to replace their analog counterparts, the importance of authenticating digital images, identifying their sources, and detecting forgeries is increasing. Blind image forensics is used to analyze an image in the complete absence of any digital watermark or signature. Image compositing is the most common form of digital tampering. Assuming that image compositing operations affect the inherent statistics of the image, we propose an image compositing detection method on based on a statistical model for natural image in the wavelet transform domain. The generalized Gaussian model (GGD) is employed to describe the marginal distribution of wavelet coefficients of images, and the parameters of GGD are obtained using maximum-likelihood estimator. The statistical features include GGD parameters, prediction error, mean, variance, skewness, and kurtosis at each wavelet detail subband. Then, these feature vectors are used to discriminate between natural images and composite images using support vector machine (SVM). To evaluate the performance of our proposed method, we carried out tests on the Columbia Uncompressed Image Splicing Detection Dataset and another advanced dataset, and achieved a detection accuracy of 92% and 79%, respectively. The detection performance of our method is better than that of the method using camera response function on the same dataset.     

New algorithm for 3D facial model reconstruction and its application in virtual reality

3D human face model reconstruction is essential to the generation of facial animations that is widely used in the field of virtual reality (VR). The main issues of 3D facial model reconstruction based on images by vision technologies are in twofold: one is to select and match the corresponding features of face from two images with minimal interaction and the other is to generate the realistic-looking human face model. In this paper, a new algorithm for realistic-looking face reconstruction is presented based on stereo vision. Firstly, a pattern is printed and attached to a planar surface for camera calibration, and corners generation and corners matching between two images are performed by integrating modified image pyramid Lucas-Kanade (PLK) algorithm and local adjustment algorithm, and then 3D coordinates of corners are obtained by 3D reconstruction. Individual face model is generated by the deformation of general 3D model and interpolation of the features. Finally, realistic-looking human face model     

Spatio-Temporal Video Motion Detection Using Marked-Watershed and Morphological Operations

In this article, we describe a moving object detection method developed based on spatio-temporal information and marked-watershed for extracting the moving objects from a video sequence. The algorithm begins with difference image between two adjacent frames and, using the Canny operator on the difference image, determines the initial edge mask for the object in motion Morphological operators are applied to the initial edge map to obtain a temporal segmentation mask of the moving object and binary marker image of the foreground and background, which is subject to the watershed thresholding. The markers are used to modify multi-scale morphological gradient image of the current frame. Finally, the watershed algorithm is performed on the modified gradients to locate the non-stationary objects accurately in the spatial domain of motion frames. Experimental results show that the proposed technique can overcome the shortcoming of over-segmentation of the watershed algorithm. In computationally efficient way, it segments and extracts semantically meaningful objects, which are in slow or fast motion from the video frames of scenes involving complex background. Performance evaluation yields that the detection accuracy can be as high as 98% to 99% for different video sequences.     

Single image haze removal via depth-based contrast stretching transform

Under the weather of haze, fog, or smoke, outdoor images show poor visibility and low contrast.Low contrast results in the difficulty for carrying out basic local feature(e.g., interest points and edges) detection algorithms, which are necessary procedures in some computer vision applications. Hence, increasing contrast of degraded images is very important since it is helpful in finding more distinct features from haze images.However, few single image haze removal methods can simultaneously achieve clear visibility, sufficiently high contrast, and simplicity. In this paper, we propose an intuitive and effective method, called the depth-based contrast stretching transform(DCST), to simultaneously obtain clear visibility and enhance contrast of a single haze gray image. The DCST stretches the contrast of haze images based on the coarse depth layers of scenes.Our method is simple and almost real time and can be extended to color images. We analyze in detail that the image stretched by the DCST has a higher local contrast than the image recovered via the physical-based model.Experiments demonstrate that images stretched by the DCST have excellent visibility and contrast compared with a few existing algorithms. Compelling performance is also presented by comparing the proposed method with other representative methods in the application of local feature detection.     

实时视频图像中的人脸检测与跟踪

视频图像目标检测与跟踪是远程协作系统中感兴趣的研究课题之一。文中提出了一种协同系统中视频序列图像人脸检测及实时跟踪的方法。该方法根据用户选定的目标(如人脸)的颜色分布特点，用多幅训练样本图像建立人脸肤色模型，然后根据该模型和人脸特征对待检测的彩色图像进行分割与匹配，从而确定候选区域是否人脸。在视频图像跟踪中用此方法可实现人脸的实时检测跟踪，为了提高跟踪速度，提出了改进的基于运动预测的快速跟踪法。该方法充分利用运动连续性规律，能较好地处理多干扰目标同时出现的情形。实验表明所提出的方法执行效率高，检测跟踪正确率高．对有旋转的非正面人脸图像也有较好的适应性。     

基于彩色人脸模板的人脸检测算法

针对目前基于色彩的人脸检测只能用于人脸区域的粗检这一不足,提出一种利用人脸的五官位置及色彩信息建立彩色人脸模板的算法。采用光照补偿对图像进行预处理,利用YCbCr空间中的肤色模型进行粗检,确定出人脸候选区域,利用建构好的模板进行搜索比对定位出人脸。实验结果表明该方法对不同光照环境和复杂背景的图片均有较好的适应性,检测精度也得到了提高。     

一种基于肤色模型和模板匹配的人脸检测算法

近年来,随着人机识别技术的日益发展,人脸检测问题越来越受到重视,而人脸检测技术的关键在于准确率和检测速度.为了有效提高人脸检测的效率,提出了一种基于肤色分割和模板匹配算法的人脸检测方法.首先,建立颜色模型,利用颜色信息对图像进行粗检测,得到粗检测结果,然后,采用模板匹配技术确定人脸.该算法克服了单用模板匹配法的时间延迟,提高了检测精度和速度.     

复杂背景中的人脸检测与定位

基于人类视觉机制,描述了一种由粗到细的复杂背景中的人脸检测方法。其基本思想是首先粗略定出人脸可能存在的区域,然后在可能的区域内进一步细致匹配,以证实人脸的存在并对其进行准确定位。在粗略检测中利用人脸的肤色分布统计模型将人脸从背景中分割出来;在准确定位中联合人脸的肤色分布统计模型、发色分布统计模型以及不同方向的头部模型,用模糊模式匹配的方法进行准确定位。实验结果表明该方法比在复杂背景中直接利用肤色信息检测人脸的方法速度快,准确率高,鲁棒性好。     

一种有效的皮肤检测算法

肤色特征是人体表面的重要特征,在人脸检测与识别、基于内容的不良图像过滤系统中有着重要的地位。分析了YUV颜色空间系统的特点,提出了一种基于椭圆区域的皮肤模型,将该模型应用于基于内容的不良图像过滤系统的皮肤检测部分中。实验表明,利用该模型进行皮肤检测能够达到很好的效果。     

肤色模型快速人脸检测算法研究

为提高人脸检测效率．研究实现采用肤色模型的低分辨率视频快速人脸检测算法。主要步骤包括采用Gray World方法的图像预处理、图像二值化和形态学处理等,从而实现快速人脸定位。实验结果证明该方法的正确性、快速性和有效性。该算法可以为后期人脸特征检测的精确定位奠定基础。     

视频中多线索的人脸特征检测与跟踪

针对目前的人脸特征检测与跟踪算法存在的对环境适应能力差、缺乏自我检错能力的缺点，该文提出了一种多线索综合的新方法，多线索中包括基于深度信息的人脸区域粗分割，基于多关联模板匹配的人脸检测，利用多尺度Sobel卷积的特征提取，基于“特征眼”的人眼验证以及基于多视图的校验方法，多种线索互相补充，自我检错和纠错，对背景，光照及姿态变化具有较强的适应能力，实验表明该方法是有效的，鲁棒的。     

非合作面部晃动情况下的心率检测

目的 心率是直接反映人体健康的重要指标之一,基于视频的非接触式心率检测在医疗健康领域具有广泛的应用前景。然而,现有的基于视频的方法不适用于复杂的现实场景,主要原因是没有考虑视频中目标晃动干扰和空间尺度特征,使得血液容积脉冲信号提取不准确,检测精度不尽人意。为了克服以上缺陷,提出一种抗人脸晃动干扰的非接触式心率检测方法。方法 本文方法主要包含3个步骤：首先,针对目标晃动干扰人脸区域选择的问题,利用判别响应图拟合检测参考图像的人脸区域及主要器官特征点,在人脸跟踪时首次引入倾斜校正思想,输出晃动干扰抑制后的人脸视频;然后,结合空间尺度的差异,采用颜色放大方法对晃动干扰抑制后的人脸视频进行时空处理,提取干净的血液容积脉冲信号;最后,考虑到小样本问题,通过傅里叶系数迭代插值的频域分析方法估计心率。结果 在人脸静止的合作情况以及人脸晃动的非合作情况下采集视频,对心率检测结果进行定量分析,本文方法在两种情况下的准确率分别为97.84%和97.30%,与经典和最新的方法相比,合作情况准确率提升大于1%,非合作情况准确率提升大于7%,表现了出色的性能。结论 提出了一种基于人脸视频处理的心率检测方法,通过有效分析人脸的晃动干扰和尺度特性,提取到干净的血液容积脉冲信号,提高了心率检测的精度和鲁棒性。     

基于Bandlet和KW技术的移动应用面部情感识别

由于情感感知移动应用的智能性和用户易接受性,使情感感知移动应用不断增加。由于移动设备的处理能力有限,因此移动设备上的情感识别方法的算法实现应该实时和高效。提出了一个移动应用上的高精度和低计算复杂度的情感识别方法。在该方法中,人脸视频由智能手机的摄像头捕获,从视频中提取一些有代表性的帧,并且用一个人脸检测模块从这些帧中提取人脸区域。脸部区域被Bandlet变换处理,结果子波被划分为互不重叠的子块。计算每个块的局部二进制值模式的直方图,将所有块的直方图关联起来作为描述面部图像的特征集。用Kruskal-Wallis检验从面部图像特征集中选择最具优势的特征,将这些特征送入高斯混合模型分类器中进行情感识别。实验结果表明,该方法在一个合理的时间内实现了高识别精度。     

数字图像识别在人脸检测中的应用

利用数字图像模式识别技术实现了人脸的自动检测及特征定位.对数字图像处理中的颜色模型、肤色建模的原理及在人脸识别中的应用进行了概述,分析了人脸识别过程中存在的困难,展望了人脸识别技术的发展方向.