基于Adaboost算法的人脸检测实现

人脸检测是指把人脸从一幅静止的图像或者动态视频中检测出来,并且指出人脸在图像或视频中的大小和位置。目前存在着大量的人脸检测算法,其中Adaboost算法是比较实用的人脸检测算法。Adaboost算法中人脸的特征采用的是矩形特征,在大量的样本集中,提取样本的矩形特征进行训练,生成多个弱分类器,然后合并多个弱分类器形成一个强分类器,最后级联强分类器形成最终的分类器,以此作为人脸检测的依据。文章先介绍了人脸检测技术,采用Adaboost算法生成人脸分类器,最后利用OpenCV来实现人脸检测。     

Adaboost算法及其在实时视频流中的应用

针对Adaboost算法在实时视频流中的应用,本文基于Adaboost算法的人脸检测原理,即通过提取图像中的haar特征,在训练过程中选出最优特征,转换成弱分类器,优化组合于人脸检测.最终,利用opencv的开发包,通过VC++软件编程实现基于Adaboost算法实时视频流中的人脸检测.     

Adaboost算法及其在实时视频流中的应用

针对Adaboost算法在实时视频流中的应用,本文基于Adaboost算法的人脸检测原理,即通过提取图像中的haar特征,在训练过程中选出最优特征,转换成弱分类器,优化组合于人脸检测。最终,利用opencv的开发包,通过VC++软件编程实现基于Adaboost算法实时视频流中的人脸检测。     

基于Adaboost和最小割算法的视频人脸检测

Adaboost算法是一种被广泛应用于人脸检测的分类器学习方法,通过Haar-like特征和样本的学习和训练,形成一个强分类器,能有效地区分人脸跟非人脸.文中提出一种Adaboost结合最小割算法的人脸提取方法,该方法着眼于图像中的轮廓及肤色信息,对每个点设置一个权值,寻找一条权值最小的边界,准确提取出人脸.实验结果表明,Adaboost和最小割的人脸提取算法,分割效果较好,且耗时较小.     

基于局部人脸图像的ICA人脸识别方法

提出了一种基于局部人脸图像独立分量分析的特征提取方法.该方法将人脸图像分成若干个相等的部分,将分成的局部人脸图像矩阵作为训练样本,并先后从水平方向,垂直方向提取训练样本的独立分量.相较于传统的独立分量分析(ICA)方法,该方法具有如下优点:有效解决了传统ICA在进行特征抽取过程中的高维小样本问题;将局部人脸图像作为训练样本,这不仅增加了训练样本数,而且有利于提取人脸局部特征;依次从训练样本的水平方向、垂直方向提取训练样本特征,使得提取的特征不仅维数更小,而且能更有效地反映样本的局部信息.以上优点使得提出的算法较传统方法在人脸识别方面更稳定,识别率更高,在Yale人脸库和AR人脸库上验证了该算法的有效性.     

基于粒特征和连续Adaboost的人脸检测

提出了一种基于粒特征和连续Adaboost算法的人脸检测方法.它使用粒特征并扩展贝叶斯决策弱分类器,设计具有连续置信度输出的查找表型弱分类器形式,构造出弱分类空间,使用大规模的训练集和验证集,采用连续Adaboost算法学习得到Boosting动态级联型的人脸检测器.在CMU MIT正面人脸测试集上,误报20个时,检测率为90%以上.在一台Pentium Dual 1.2 GHz的PC上,处理一幅大小为320×240像素大小的图片平均需100 ms.实验结果表明该方法取得了比较好的精度和速度.     

融合人脸轮廓和区域信息改进人脸检测

基于人脸轮廓信息和面部区域信息的互补性，提出了一种新颖的基于融合算法的轮廓一区域人脸检测器：采用一种新的特征提取方法有效地刻画人脸轮廓模式；基于支持向量机分别训练人脸轮廓分类器和面部区域分类器；基于最小错误率Bayes决策规则融合人脸轮廓和面部区域分类器。该文分别在标准头部图像库、BioID人脸图像库(灰度人脸图像库)和彩色人脸图像库上测试了轮廓一区域人脸检测器．大量的实验结果表明了所提出的轮廓一区域人脸检测器通过引入轮廓信息有效地提高了人脸检测算法的精度。     

基于人脸检测与SIFT的播音员镜头检测

播音员镜头的检测是新闻视频结构化的关键步骤之一.提出了一种基于人脸检测与SIFT特征点匹配的播音员镜头自动检测算法.该方法首先利用人脸检测器过滤出具有人脸的候选镜头,然后利用颜色直方图判断镜头是否可能相似,再利用SIFT特征点匹配从候选镜头关键帧中找出相关的镜头组,最后利用各镜头组的信息判断出哪些是播音员镜头.对比传统的方法,该方法除了训练一个通用的人脸检测器外,不需要模板,也不需要针对某类新闻节目训练特别的分类器,可以直接利用算法对新类型的新闻节目提取播音员镜头.实验结果表明,该算法能够广泛地适应于各种不同种类的新闻节目、不同视觉质量的视频,可以有效地应用于新闻视频分析.     

Boosting协方差特征的人脸检测方法

基于Harr式特征分层筛选的人脸检测方法速度快、检测率高。但Harr式特征对边缘、线段比较敏感,只能描述特定走向的图形结构。结合分层筛选技术,提出了Boosting协方差特征人脸检测方法。该方法先计算协方差矩阵特征,然后由这些特征构造弱分类器,最后借助Adaboost方法组合这些弱分类器的输出结果来对测试图片进行瀑布式分层筛选,从而获得最终判决结果。测试实验显示所提方法具有较强的抗噪能力,检测率相比原基于Harr式特征分层筛选的方法有显著提高。     

基于特征裁剪的双阈值Adaboost人脸检测算法

针对传统Adaboost算法存在训练耗时长的问题,提出一种基于特征裁剪的双阈值Adaboost算法人脸检测算法。一方面,使用双阈值的弱分类器代替传统的单阈值弱分类器,提升单个弱分类器的分类能力;另一方面,特征裁剪的Adaboost算法在每轮训练中仅仅利用错误率较小的特征进行训练。实验表明基于特征裁剪的双阈值Adaboost人脸检测算法通过使用较少的特征和减少训练时的特征数量的方式,提高了算法的训练速度。     

支持特征的非流形造型数据结构的研究

文章提出了一种新的数据结构,统一的表示了线框、表面和实体三种模型,及非几何特征信息,扩大传统实体造型的覆盖域,并可表示非流形模型。     

基于STEP的特征模型及重构算法

随着CAX技术的发展,特征技术得到越来越多的重视,特征技术的使用,大幅度提高了产品的设计、制造、集成等过程的效率。目前,基于特征的CAD、CAM系统是市场的主流,CAPP是完全基于特征的应用系统。但是在STEP的众多应用协议中,涉及机械设计、制造、管理的应用协议有很多,但是这些应用协议基本上没有提供对特征的支持。AP224是较早支持特征的STEP应用协议,主     

基于最大决策边界的局部在线流特征选择

现有的在线流特征选择算法通常选择一个最优的全局特征子集,并假设该子集适用于样本空间的所有区域.但是,样本空间的每个区域都使用独有的特征子集进行准确描述,这些特征子集的特征和大小可能有所不同.因此,文中提出基于最大决策边界的局部在线流特征选择算法.引入局部特征选择,在充分利用局部信息的基础上,设计基于最大决策边界的特征衡量标准,尽可能分开同类样本和不同类样本.同时,使用最大化平均决策边界、最大化决策边界和最小化冗余3种策略选择合适的特征.针对局部区域选择最优的特征子集,然后使用类相似度测量方法进行分类.在14个数据集上的实验结果和统计假设检验验证文中算法的分类有效性和稳定性.     

一种基于关联性的特征选择算法

目前在文本分类领域较常用到的特征选择算法中,仅仅考虑了特征与类别之间的关联性,而对特征与特征之间的关联性没有予以足够的重视.提出一种新的基于关联分析的特征选择算法,该方法以信息论量度为基本工具,综合考虑了计算代价以及特征评估的客观性等问题.算法在保留类别相关特征的同时识别并摒弃了冗余特征,取得了较好的约简效果.     

基于特征的CAD／CAM集成技术评述与研究

本文对特征识别，基于特征的设计和特征转换等方法进行了评述和研究，并据此提出了基于特征的ＣＡＤ／ＣＡＭ集成系统的总体设计方案。     

Stability of feature selection algorithms: a study on high-dimensional spaces

With the proliferation of extremely high-dimensional data, feature selection algorithms have become indispensable components of the learning process. Strangely, despite extensive work on the stability of learning algorithms, the stability of feature selection algorithms has been relatively neglected. This study is an attempt to fill that gap by quantifying the sensitivity of feature selection algorithms to variations in the training set. We assess the stability of feature selection algorithms based on the stability of the feature preferences that they express in the form of weights-scores, ranks, or a selected feature subset. We examine a number of measures to quantify the stability of feature preferences and propose an empirical way to estimate them. We perform a series of experiments with several feature selection algorithms on a set of proteomics datasets. The experiments allow us to explore the merits of each stability measure and create stability profiles of the feature selection algorithms. Finally, we show how stability profiles can support the choice of a feature selection algorithm. Alexandros Kalousis received the B.Sc. degree in computer science, in 1994, and the M.Sc. degree in advanced information systems, in 1997, both from the University of Athens, Greece. He received the Ph.D. degree in meta-learning for classification algorithm selection from the University of Geneva, Department of Computer Science, Geneva, in 2002. Since then he is a Senior Researcher in the same university. His research interests include relational learning with kernels and distances, stability of feature selection algorithms, and feature extraction from spectral data. Julien Prados is a Ph.D. student at the University of Geneva, Switzerland. In 1999 and 2001, he received the B.Sc. and M.Sc. degrees in computer science from the University Joseph Fourier (Grenoble, France). After a year of work in industry, he joined the Geneva Artificial Intelligence Laboratory, where he is working on bioinformatics and datamining tools for mass spectrometry data analysis. Melanie Hilario has a Ph.D. in computer science from the University of Paris VI and currently works at the University of Geneva’s Artificial Intelligence Laboratory. She has initiated and participated in several European research projects on neuro-symbolic integration, meta-learning, and biological text mining. She has served on the program committees of many conferences and workshops in machine learning, data mining, and artificial intelligence. She is currently an Associate Editor of theInternational Journal on Artificial Intelligence Toolsand a member of the Editorial Board of theIntelligent Data Analysis journal.     

Pedestrian Re-ID based on feature consistency and contrast enhancement

For robust person re-identification(Re-ID), the key is effectively learning the features of body parts and their long-distance dependence. ResNet and Transformer are respectively good at learning local dependence and long-distance dependence between region features due to their respective special structures. In order to fully integrate the advantages of the two models, we propose a novel person Re-ID framework that effectively incorporates pixel-level region features, posture-level relation features and the long-distance dependence of region features. Specifically, we design a Semantic Correction Module (SCM) that corrects pixel-level region features and posture-level relation features in a masked manner to generate discriminative fine-grained features with high pose semantics. Considering the semantic inconsistency between relation features and region features, we propose a Contrastive Association Module (CAM) to interactively enhances the long-distance correlation and local saliency of features in a self-attention way. Finally, to improve the robustness of local and global features, we construct a CAM layer to enhance the representation of features based on their potential relationships. Extensive experiment results on general and occlusion datasets demonstrate that our approach performs favorably against the state-of-the-art methods, e.g. 96% Rank-1 on Market-1501.     

An approach to identify design and manufacturing features from a data exchanged part model

Due to the large variety of CAD systems in the market, data exchange between different CAD systems is indispensable. Currently, data exchange standards such as STEP and IGES, etc. provide a unique approach for interfacing among different CAD platforms. Once the feature-based CAD model created in one CAD system is input into another via data exchange standards, many of the original features and the feature-related information may not exist any longer. The identification of the design features and their further decomposition into machining features for the downstream activities from a data exchanged part model is a bottleneck in integrated product and process design and development. In this paper, the feature panorama is succinctly articulated from the viewpoint of product design and manufacturing. To facilitate feature identification and extraction, a multiple-level feature taxonomy and hierarchy is proposed based on the characteristics of part geometry and topology entities. The relationships between the features and their geometric entities are established. A litany of algorithms for the identification of design and machining features are proposed. Besides, how to recognize the intersecting features or compound features based on the featureless chunks of geometry entities is critical and the issue is addressed in the paper. A multi-level compound feature representation and recognition approach are presented. Finally, case studies are used to illustrate the validity of the approach and algorithms proposed for the identification of the features from CAD part models in neutral format.     

一种基于几何特征的表情相似性度量方法

在表演驱动、表情克隆等人脸动画中,需要寻找最相似表情以提高动画真实感和逼真度。基于面部表情几何特征提出一种特征加权的表情相似性度量方法。首先,在主动外观模型上,利用链码描述各区域的形状特征以刻画局部表情细节,并根据区域特征点间的拓扑关系构建形变特征以反映整体表情信息。然后,采用特征加权方式对融合的几何特征进行相似性度量,并将权重的求解过程转化为加权目标函数最小化。最后,利用求解的权重以及特征加权函数度量表情间的相似性,寻找与之最相似的表情图像。在BU-3DFE数据库和FEEDTUM数据库上的实验结果表明,该方法在寻找相似表情的正确率方面明显高于现有的度量方法,并且对不同类型、不同强度的表情描述保持较好鲁棒性,尤其在嘴型、脸颊收缩、嘴开合幅度等表情细节维持较高相似度。     

基于AdaBoost的人脸特征挑选与特征融合算法研究

针对人脸识别中的特征挑选和特征融合问题进行研究。结合已有的基于AdaBoost的人脸特征挑选方法,挑选出最具分类能力的特征,并将挑选出的多类人脸特征在特征层进行融合,得到一个统一的人脸特征用于模式分类。通过在FERET人脸库上的实验表明,其识别方法具有良好的识别效果。