基于肤色信息与宽度优先搜索的AAM人脸特征定位算法

提出了一种结合肤色信息与宽度优先搜索的AAM(Active Appearcance Models)人脸检测算法。该算法充分利用彩色人脸图像中的肤色信息,建立肤色模型,结合形态学运算和宽度优先搜索算法,定位人脸重心,有效地缩小了搜索窗口。实验表明,和AAM算法相比,该算法不仅检测率提高,而且速度提高60%以上。     

快速人脸动画方法

本文介绍了一种简单有效的由单幅人脸照片生成人脸变形动画的方法．首先，根据一张人脸正面的照片，使用特征识别的方法生成人脸模型，然后使用模型关键表情插值法产生人脸变形动画．这种方法的优点在于只需要一张人脸正面照片，在更低的硬件条件下达到或接近其他方法生成的人脸动画效果。     

基于轮廓信息的人脸检测

针对彩色图像提出了一种基于肤色模型、脸部轮廓信息以及眼睛特征的人脸检测算法.采用基于YCbCr色彩空间的肤色分割模型,初步筛选人脸的候选区域;在此基础上进行边缘检测,获得人脸轮廓信息,并利用遗传算法拟合脸部的椭圆;在椭圆的水平方向根据眼睛的几何特征来检测"眼睛对",再根据"三停五眼"来定位人脸,并利用左右对称性验证人脸.实验表明,该算法对于彩色图像的正面人脸检测具有良好的效果.     

基于头肩图像序列的人脸特征定位系统的实现

针对复杂背景的人脸彩色图像进行特征定位,一直是研究的热点和难点问题.提出了一种实时进行人脸特征定位的算法.在单人脸头肩图像序列中,首先利用背景差分法提取出人脸前景图像,利用几何先验知识和积分投影法分离出人脸区域;接着在人脸区域中采用YCbCr肤色模型、模板匹配以及边缘检测的方法定位出眼睛和嘴角,最后在RGB空间上采用阈值方法和积分投影法相结合的方法确定眉毛和鼻子的位置.实验表明,系统可以快速地检测出人脸特征,具有较高的检测精度和鲁棒性,检测的帧率达到10fps.     

基于特征和弹性网格模型的快速人脸建模

为解决特定人脸的建模问题提供了一个简单而行之有效的方法。给定特定人脸的正面侧面照片,以及内嵌具有人脸特征信息的弹性人脸网格模型,采用基于小波分析的方法进行人脸特征识别,基于特定人脸的特征线相对于一般人脸模型上的特征线的位移,根据弹性系数求解所有点的位移变化,适配特定人脸几何。纹理映射之后生成能以任意视线方向观察的高度真实感特定人脸。该方法能在廉价的PC平台上快速而方便地得到实现。     

三维脸部网格模型的交互式调整

脸部网络模型的建立是基于模型的人脸合成技术的关键步骤。提出了一种结合自动和交互方式，利用正交图象的三维人脸模型调整算法，首先利用区域增长法和矩形模板匹配确定正面图象中人脸及各特征区域的位置，利用变形模板自动提取人脸完整特征；然后交互地修正人脸特点的准确正面位置，并从侧面图象提取特征点的深度；最后算法自动确定脸部姿态和利用反向距离内插调整模型非特征点，获得输和人脸模型。实验结果表明，该算法简便实用，费时较少，具有一定的实用价值。     

复合特征的眼睛中心定位

为实现在正面人脸中定位眼睛中心点,提出复合特征算法。在整体人脸图像主动表观模型的基础上,引入局部表观模型,使全局AAM的最优结果进一步转换到眼睛局部区域的最优定位,结合在线的肤色纹理特征,使用扇形区域积分定位内外眼角点,实现眼睛边界点的在线精确定位。使用积分图的特征梯度定位虹膜区域的边界,用圆形参数进行虹膜边缘检测,实现眼睛虹膜区域的精确定位。实验结果表明,该算法可以鲁棒地确定眼睛中心,对于实时视频等低分辨率图像能够较好地实现定位。     

视频人脸检测与特征点定位研究

基于对视频中人脸的检测和特征点定位算法的学习与研究,文中提出了一种结合连续均值向量和主动形状模型的新方法.该方法首先对视频帧进行局部连续均值量化变换处理,快速地检测出似人脸区.然后用改进ASM方法来定位所检测出人脸的特征点,使用双阈值Sobel算子进行边缘检测,提取边缘信息,当搜索时利用这些边缘信息来改变特征点的权值,使带有更多边缘信息的像素点更有可能被选为最佳候选点.该方法可以快速地对人脸做出检测,并能很好地定位出人脸特征点     

基于轮廓信息的人脸检测

针对彩色图像提出了一种基于肤色模型、脸部轮廓信息以及眼睛特征的人脸检测算法。采用基于YCbCr色彩空间的肤色分割模型,初步筛选人脸的候选区域;在此基础上进行边缘检测,获得人脸轮廓信息,并利用遗传算法拟合脸部的椭圆;在椭圆的水平方向根据眼睛的几何特征来检测“眼睛对”,再根据“三停五眼”来定位人脸,并利用左右对称性验证人脸。实验表明,该算法对于彩色图像的正面人脸检测具有良好的效果。     

基于照片的特定三维人脸建模方法

个性化的人脸模型在游戏娱乐、电影制作、聋哑人辅助教学等领域发挥着重要的作用.因此特定人脸建模越来越受人们重视.特定人脸建模是指利用具体的人脸信息建立具有不同特征的人脸模型.利用人脸的正面和侧面照片,首先对通用人脸模型进行几何信息的修改,使通用人脸模型的几何形状与特定的人脸模型一致;然后参考MPEG-4中的人脸定义标准,标识出人脸正面照片以及侧面照片中的特征点,使用克里金函数插值方法,通过对通用人脸模型进行纹理图像的变形,从而建立特定人脸模型.实验结果表明,克里金插值方法是一种光滑的内插方法,在数据点多时,其内插的结果可信度较高.     

A neural network system for matching dental radiographs

This paper addresses the problem of creating a postmortem identification system by matching image features extracted from dental radiographs. We lay the architecture of a prototype automated dental identification system (ADIS), which tackles the dental image matching problem by first extracting high-level features to expedite retrieval of potential matches and then by low-level image comparison using inherent features of dental images. We propose the use of learnable inherent dental image features for tooth-to-tooth image comparisons. We treat the tooth-to-tooth matching problem as a binary classification problem for which we propose probabilistic models of class-conditional densities. We also propose an adaptive strategic searching technique and use it in conjunction with back propagation in order to estimate system parameters. We present promising experimental results that reflect the value of our approach.     

Harmonized Portrait-Background Image Composition

Portrait-background image composition is a widely used operation in selfie editing, video meeting, and other portrait applications. To guarantee the realism of the composited images, the appearance of the foreground portraits needs to be adjusted to fit the new background images. Existing image harmonization approaches are proposed to handle general foreground objects, thus lack the special ability to adjust portrait foregrounds. In this paper, we present a novel end-to-end network architecture to learn both the content features and style features for portrait-background composition. The method adjusts the appearance of portraits to make them compatible with backgrounds, while the generation of the composited images satisfies the prior of a style-based generator. We also propose a pipeline to generate high-quality and high-variety synthesized image datasets for training and evaluation. The proposed method outperforms other state-of-the-art methods both on the synthesized dataset and the real composited images and shows robust performance in video applications.     

基于主动表观模型姿态矫正和局部加权匹配人脸识别

非约束环境下,光照、姿态、表情、遮挡等复杂背景因素给人脸识别带来严重影响。提出一种基于AAM（active appearance model）的图像对齐和局部匹配人脸识别算法,使之能够增强人脸识别算法对姿态、表情变化的鲁棒性。AAM能够快速准确地定位人脸的特征点,进而将图像扭转到一个标准正面人脸模型中。接着,提出一种新的基于信息熵的Gabor jet加权方法用于提高人脸识别率;并且对Borda count分类器组合方法进行了改进,认为在投票过程中为其设置阈值来排除“噪声”的干扰可以提高识别率。通过与多种人脸识别方法的实验结果比较表明,使用AAM矫正图像后,联合熵加权Gabor方法和加阈值Borda能够取得比单独使用更好的成绩。     

Automated feature detection in digital images of skin

This paper presents a new approach to the detection of cutaneous features such as pigmented moles, pores and hair in digital images. We show that by considering the digitized image to be a 3-D terrain with brightness being height, common skin features appear as 'pits' in the terrain. Pits contain a great deal of information about local features in a form that can be easily extracted and analyzed. Pigmented lesions of clinical interest typically have pit characteristics which can be used to separate them from other features. We show empirically that, by creating a statistical database, on the average over 99% of pits can be classified correctly after only a few training images are established for a subject. When attempting to detect pigmented lesions, mean sensitivity ranges from 78% to 98%, depending on imaging conditions and the classification algorithm used. Using image compression, the speed of this screening technique is shown to be increased by a factor of 4 without loss of sensitivity.     

结合肤色分割与平滑的人脸图像快速美化

目的 针对目前人脸图像美化算法存在的对于细节丰富的眼睛和头发等区域处理过度平滑,美化后的图像整体美化效果较差等问题,提出一种基于肤色分割与平滑人脸图像的美化方法。方法 首先对脸部瑕疵特性,用双指数边缘保护滤波器平滑人脸图像的瑕疵,与此同时很好保持图像边缘信息;再通过利用色度直方图自适应快速检测、修正、分割肤色区域;然后利用拟合高斯羽化皮肤区域生成蒙版,融合平滑图像和原图像,保留图像头发背景等细节信息;最后基于人像美感标准,对皮肤亮度通过拟合log曲线实现快速自适应调整人脸图像亮度,增强眼睛等细节,从而快速实现人脸图像美化方法。结果 通过与其他人像美化算法相比较,在保留边缘方面,该算法更有效地对皮肤边缘上的瑕疵进行平滑,达到更好地美化人脸图像;而在时间复杂度方面,相对于前人的算法,计算速度快12倍,实现快速美化人脸图像。结论 该算法适应能力较强,对大部分人脸图像的脸部瑕疵完美去除的同时达到背景信息不变,肤色美白自然,使整体美化效果显著;尤其是细节丰富的边缘区域平滑适度,具有一定的实用性。     

一种基于图的交互式目标分割算法

静态图片的编辑中,交互式背景、前景分割的高效性研究有着重大的实际意义。传统的分割方法或是应用图片的纹理(色彩)信息,如Magic Wand,或是利用边界(对比度)信息,如Intelligent Scissors。最近提出的Graph cuts分割算法很好地结合了以上的两种信息。该文将介绍Graph cuts算法以及在该算法基础上改进得到的Grab cut算法。Grab cut算法堪称目前交互式分割方法中分割效果较好的方法,其分割精度高,交互工作少,具有较好的应用前景。文章结合作者当前的研究课题,把Grab cut算法应用在医学图像器官分割中得到了令人满意的效果。     

SVM-based image partitioning for vision recognition of AGV guide paths under complex illumination conditions

Applying computer vision to mobile robot navigation has been studied more than two decades. For the commercial off-the-shelf (COTS) automated guided vehicles (AGV) products, the cameras are still not widely used for the acquisition of guidance information from the environment. One of the most challenging problems for a vision guidance system of AGVs lies in the complex illumination conditions. Compared to the applications of computer vision where on-machine cameras are fixed in place, it is difficult to structure the illumination circumstance for an AGV that needs to travel through a large work space. In order to distinguish the original color features of path images from their illumination artifacts, an illumination-adaptive image partitioning approach is proposed based on the support vector machine (SVM) classifier with the slack constraint and the kernel function, which is utilized to divide a path image to low-, normal-, and high-illumination regions automatically. Moreover, an intelligent path recognition method is developed to carry out guide color enhancement and adaptive threshold segmentation in different regions. Experimental results show that the SVM-based classifier has the satisfactory generalization ability, and the illumination-adaptive path recognition approach has the high adaptability to the complex illumination conditions, when recognizing the path pixels in the field of view with both high-reflective and dark-shadow regions. The 98% average rate of path recognition will significantly facilitate the subsequent operation of path fitting for vision guidance of AGVs.     

基于改进C-V模型的图像分割方法

传统C-V模型分割图像利用图像区域特征,忽略 了边缘等能够反应图像细节的特征。为了达到更好的图像分割效果,对于这些细节信息的处理则显得尤为重要。图像的梯度信息在边缘区域具有较大幅值,在同质区域具有较小幅值,因而可以用图像梯度来反映图像的边缘信息。把边缘信息融入C-V模型,利用同质区域信 息和边缘信息控制曲线演化,则可以达到更好的分割效果。本文提出的新模型克服了C-V模型的一些 缺陷,对背景灰度不均匀或含弱边缘的图像能够获得更好的分割效果。     

Synergy between Object Recognition and Image Segmentation Using the Expectation-Maximization Algorithm

In this work, we formulate the interaction between image segmentation and object recognition in the framework of the Expectation-Maximization (EM) algorithm. We consider segmentation as the assignment of image observations to object hypotheses and phrase it as the E-step, while the M-step amounts to fitting the object models to the observations. These two tasks are performed iteratively, thereby simultaneously segmenting an image and reconstructing it in terms of objects. We model objects using Active Appearance Models (AAMs) as they capture both shape and appearance variation. During the E-step, the fidelity of the AAM predictions to the image is used to decide about assigning observations to the object. For this, we propose two top-down segmentation algorithms. The first starts with an oversegmentation of the image and then softly assigns image segments to objects, as in the common setting of EM. The second uses curve evolution to minimize a criterion derived from the variational interpretation of EM and introduces AAMs as shape priors. For the M-step, we derive AAM fitting equations that accommodate segmentation information, thereby allowing for the automated treatment of occlusions. Apart from top-down segmentation results, we provide systematic experiments on object detection that validate the merits of our joint segmentation and recognition approach.