基于自举算法和支持向量机的人脸检测系统

针对复杂背景下的灰度图像人脸检测存在计算量大且负检率高等问题,提出了一种有较好可用性的层级递进的人脸检测系统。系统第一部分采用扩展的Haar型特征并结合自举算法,使其分类性能要优于原始的Haar型特征。在系统的第二部分,采用从粗到细的视觉处理逻辑对图像采样,并提出了正面直立人脸的像素值的置信度的概念,且以支持向量机作为学习算法,使系统具有良好的检测性能。该系统在实际应用图像的测试中取得良好效果,具有可用性。     

Boosted cascade of scattered rectangle features for object detection

This paper presents a variant of Haar-like feature used in Viola and Jones detection framework,called scattered rectangle feature,based on the common-component analysis of local region feature. Three common components,feature filter,feature structure and feature form,are extracted without concern-ing the details of the studied region features,which cast a new light on region feature design for spe-cific applications and requirements: modifying some component(s) of a feature for an improved one or combining different components of existing features for a new favorable one. Scattered rectangle feature follows the former way,extending the feature structure component of Haar-like feature out of the restriction of the geometry adjacency rule,which results in a richer representation that explores much more orientations other than horizontal,vertical and diagonal,as well as misaligned,detached and non-rectangle shape information that is unreachable to Haar-like feature. The training result of the two face detectors in the experiments illustrates the benefits of scattered rectangle feature empirically; the comparison of the ROC curves under a rigid and objective detection criterion on MIT CMU upright face test set shows that the cascade based on scattered rectangle features outperforms that based on Haar-like features.     

Context modeling for facial landmark detection based on Non-Adjacent Rectangle (NAR) Haar-like feature

Automatically locating facial landmarks in images is an important task in computer vision. This paper proposes a novel context modeling method for facial landmark detection, which integrates context constraints together with local texture model in the cascaded AdaBoost framework. The motivation of our method lies in the basic human psychology observation that not only the local texture information but also the global context information is used for human to locate facial landmarks in faces. Therefore, in our solution, a novel type of feature, called Non-Adjacent Rectangle (NAR) Haar-like feature, is proposed to characterize the co-occurrence between facial landmarks and its surroundings, i.e., the context information, in terms of low-level features. For the locating task, traditional Haar-like features (characterizing local texture information) and NAR Haar-like features (characterizing context constraints in global sense) are combined together to form more powerful representations. Through Real AdaBoost learning, the most discriminative feature set is selected automatically and used for facial landmark detection. To verify the effectiveness of the proposed method, we evaluate our facial landmark detection algorithm on BioID and Cohn-Kanade face databases. Experimental results convincingly show that the NAR Haar-like feature is effective to model the context and our proposed algorithm impressively outperforms the published state-of-the-art methods. In addition, the generalization capability of the NAR Haar-like feature is further validated by extended applications to face detection task on FDDB face database.     

基于人脸识别技术的Android平台隐私保护系统设计

Android移动设备的普及和其日渐丰富的功能,使其极大地融入了人们的生活,同时人们也对Android设备的信息安全提出了更高的要求。随着人脸识别技术的不断发展,人脸识别技术在现实生活中开始成功应用,成为一种有效的安全防护手段。文章围绕人脸识别技术,设计和实现了Android平台上的隐私保护系统。考虑到Android设备计算能力和存储能力的局限性,人脸识别的各个步骤使用了基于Haar特征的AdaBoost人脸检测算法和基于局部二值特征（LBP）的特征提取算法等简单高效的算法。文章最终实现了Android平台上的人脸识别系统,用人脸识别和文件加密对设备进行访问控制。     

基于新Haar-like特征的多角度人脸检测

在Haar-like特征的基础上增加新的检测特征,给出特征计算方法和积分方法,实现多角度人脸检测。将多角度人脸分为3类,即全侧脸、半侧脸和正面人脸。利用连续Adaboost算法训练各类人脸检测器,用金字塔式结构将各类人脸检测器级联成一个多角度人脸检测器。在CMU人脸检测集合上,该检测器的成功率为85．2％,高于Adaboost算法和浮点Adaboost算法。     

基于Adaboost算法的多角度人脸检测

文中提出了一种基于Adaboost算法的多角度人脸检测方法.多角度人脸检测问题的研究与正面人脸检测相比,相对薄弱,离实际应用的需求还比较远.首先使用Haar特征设计并构造弱分类器空间,用Adaboost算法学习得到基于视图的多分类器级联的人脸检测器;然后将多角度人脸划分成三类:全侧脸,半侧脸及正面人脸,并为不同角度的人脸建立不同的检测器分别用于检测.在CMU侧面人脸检测集合上,用基于Adaboost的方法对多角度人脸图像进行仿真实验,检测正确率为89.8%,误报数为243个.相比Schneiderman等人的方法,该方法具有更好的性能.     

Gaussian weak classifiers based on co-occurring Haar-like features for face detection

Recently, in the context of appearance-based face detection, it has been shown by Mita et al. that weak classifiers based on co-occurring, or multiple, Haar-like features provide better speed-accuracy trade-off than the widely used Viola and Jones’s weak classifiers, which use only a single Haar-like feature. In this paper, we extend Mita et al.’s work by proposing Gaussian weak classifiers that fuse information obtained from the co-occurring features at the feature level, and are potentially more discriminative. Experimental results, on the standard MIT+CMU test images, show that the face detectors built using Gaussian weak classifiers achieve up to 38 % more accuracy in terms of false positives and 42 % decrease in testing time when compared to the detectors built using Mita et al.’s weak classifiers.     

基于模糊集理论的人脸检测

分析了模糊集理论运用于人脸检测的可行性,采用Haar矩形特征和隶属度函数对样本集进行训练,运用特征集的熵和AdaBoost算法选取适当的弱分类器,并构建了分发型人脸检测器。检测时,对于不像人脸的子窗口通过靠前的结构简单的强分类器快速将其淘汰掉;对于像人脸的子窗口,根据其与人脸的相似程度,由分发器动态地选择后面的强分类器进行判定。在MIT+CMU的正面人脸图片集中进行了测试,实验结果表明,此检测器在检测性能降低不大的情况下,可以有效地提高检测效率。     

基于Gabor不确定度的嵌入式人脸识别系统

多尺度Gabor特征的维数和数据量过大,不适合在ARM板上直接实现完成。利用计算每个尺度Gabor特征不确定度并采用加权融合的方法,很好地解决了图像维数和数据量过大的难点。加权融合过程包括多尺度Gabor特征的提取、不确定度权值的计算和加权融合过程;同时使用了类Haar特征提取人脸、利用二维主成分分析(2DPCA)对人脸图像进行降维。基于EELiod 270嵌入式开发平台,使用ORL和Yale图像库对该方法进行了测试,并与其他人脸识别算法进行比较。结果显示,在保证识别率的同时,算法运算量大幅度下降,且实时识别效果良好。     

Haar-like特征双阈值Adaboost人脸检测

目的 针对基于Haar-like特征的Adaboost人脸检测算法,在应用于视频流时训练的时间较长,以及检测效率较低的问题,提出了一种基于区间阈值的Adaboost人脸检测算法。方法 通过运行传统的Adaboost算法对人脸图像Haar-like特征值进行提取分析后,对人脸样本与非人脸样本特征值进行比较,发现在某一特定的特征值区间内,人脸和非人脸区域能够得到准确区分,根据此特性,进行分类器的选择,在简化弱分类器计算步骤的同时,降低训练时间,提高对人脸的识别能力。除此之外,弱分类器的增强通过Adaboost算法的放大使得强分类器分类精度提高,与级联结构的配合使用也提升了最终模型检测人脸的准确率。结果 利用MIT（Massachusetts Institute of Technology）标准人脸库对改进Adaboost算法的性能进行验证,通过实验验证结果可知,改进后的Adaboost人脸检测算法训练速度提升为原来的1.44倍,检测率上升到94.93%,虚警率下降到6.03%。并且将改进算法在ORL（Olivetti Research Laboratory）、FERET（face recognition technology）以及CMU Multi-PIE（the CMU Multi-PIE face database）这3种标准人脸库中,分别与SVM（support vector machine）、DL（deep learning）、CNN（convolutional neural networks）以及肤色模型等4种算法进行了人脸检测对比实验,实验结果显示,改进后的Adaboost算法在进行人脸检测时,检测率提升了2.66%,训练所需时间减少至624.45 s,检测效果明显提升。结论 提出的基于区间阈值的Adaboost人脸检测算法,在分类器的训练和人脸检测方面都比传统的Adaboost算法性能更高,能够更好地满足人员较密集处（如球场等地）对多人脸同时检测的实际需求。     

基于小训练样本的AdaBoost人脸检测

AdaBoost算法已被广泛地应用于人脸检测系统中,但往往需要大量的训练样本。针对其训练过程复杂冗长的缺陷,选择研究基于少量训练样本的人脸检测问题。采用协方差特征代替图像统计的直方图进行特征提取。为达到更好的分类效果,应用基于Fisher判别式分析的线性超平面分类器,通过AdaBoost算法构成多层级联分类器进行人脸检测。在小数据库里可以看到,与目前用于多数人脸检测系统的类Haar特征相比,该算法在减少训练样本的同时能获得更好的检测效果。     

Face detection based on skin color likelihood

We propose a face detection method based on skin color likelihood via a boosting algorithm which emphasizes skin color information while deemphasizing non-skin color information. A stochastic model is adapted to compute the similarity between a color region and the skin color. Both Haar-like features and Local Binary Pattern (LBP) features are utilized to build a cascaded classifier. The boosted classifier is implemented based on skin color emphasis to localize the face region from a color image. Based on our experiments, the proposed method shows good tolerance to face pose variation and complex background with significant improvements over classical boosting-based classifiers in terms of total error rate performance.     

移动网络环境下移动终端设备的发展与应用

随着现代生活节奏的不断加快,人们在生活工作中碎片化的时间越来越多,如何利用这些碎片化的时间成为人们不得不面对的问题。如今随着移动网络的传输速度不断提高,各种移动终端的应用很好的充实了这些碎片化的时间。本文在分析移动网络环境下移动终端设备的应用对于用户产生的信息安全问题的同时也分析了新型移动终端设备的发展前景与设计理念。     

一种快速的自动人眼定位方法

眼睛定位是人脸生物特征识别的重要组成部分。提出了一种快速、高效的人眼定位方法,该方法先用基于Haar-like特征的AdaBoost级联分类器检测出人脸块,粗定位左、右眉眼区域,采用改进的灰度投影法分别将两块区域中的眉毛部分分离掉,最后分别将左右眼区域分割成若干小图像块,联合图像块灰度均值、复杂度和结构居中度等信息精确定位人眼。该方法在中科院人脸库CAS-PEAL的Normal子库上表现优异,取得了约99%的定位正确率。实验结果表明,该方法速度快,定位效果好。     

复杂背景下具有偏转角度的正面人脸检测

美国的Voila博士提出的基于Haar-like特征的人脸检测算法是一种具有巨大发展潜力的新算法,快速而准确。通过研究,认为这一算法还存在两个有待改进的地方：一是在检测率和误检率之间难以权衡,二是可检测人脸姿态受训练样本制约。对此提出了改进措施,设计了一个可以检测相对于垂直方向有±45°偏转的正面人脸的检测算法,与基于Haar-like特征的人脸检测算法相比,具有更好的鲁棒性和更低的误差率。     

iOS平台下人脸识别系统实现研究

设计了一个基于苹果公司嵌入式操作系统iOS平台下的人脸识别系统。通过对基于Haar-like特征的AdaBoost人脸检测算法的研究,实现了实时人脸检测。提出了一种改进的基于隐马尔科夫模型的人脸识别方法,此方法采用奇异值压缩抽取人脸图像特征作为观察序列,减少了数据的存储量和计算量,解决了嵌入式系统中由于图像处理数据量大造成的低效。实验结果证明,该系统检测速度快,实时性强,识别率高,可以作为iOS平台上其他类型人脸识别应用软件开发的基础。     

复杂背景下的三级级联快速正面人脸检测算法

针对复杂背景下的正面人脸检测问题,提出一种三级级联快速正面人脸检测算法：第一级使用 HSV 肤色模型,通过分析最大肤色连通区,快速排除非人脸区域;第二级采用 Haar-like 特征结合 AdaBoost 算法定位人脸区域;最后提出基于局部特征点加权的改进主动形状模型(W-ASM)算法匹配人脸的特征点坐标,通过68个特征点位置判断当前人脸图像是否是正面人脸。实验结果表明,本算法能准确识别出垂直于图像旋转不超过±5°的正面人脸,每幅图像(640×480)平均用时仅52ms,满足实时性要求。     

A color-based face tracking algorithm for enhancing interaction with mobile devices

A color-based face tracking algorithm is proposed to be used as a human-computer interaction tool on mobile devices. The solution provides a natural means of interaction enabling a motion parallax effect in applications. The algorithm considers the characteristics of mobile use-constrained computational resources and varying environmental conditions. The solution is based on color comparisons and works on images gathered from the front camera of a device. In addition to color comparisons, the coherency of the facial pixels is considered in the algorithm. Several applications are also demonstrated in this work, which use the face position to determine the viewpoint in a virtual scene, or for browsing large images. The accuracy of the system is tested under different environmental conditions such as lighting and background, and the performance of the system is measured in different types of mobile devices. According to these measurements the system allows for accurate (7% RMS error) face tracking in real time (20–100 fps).     

Wheelchair-based mobile measurement of behavior for pressure sore prevention

A recently developed device which provides continuous, direct monitoring of the pressure relief performance of persons confined to wheelchairs is reported. A custom portable computer records the data, which is transferred for analysis to an Apple IIe. The mobile computer can also signal the patient to relieve pressure on the basis of preset criteria and the patient's performance. Teaching lift-offs to prevent ischial pressure sores is the object. Data collected with the device are used clinically and for research. Examples of such data are presented. The benefits of the device are reviewed.