Local Generic Representation for Face Recognition with Single Sample per Person (ACCV, 2014)

Abstract:

1. 每个类别单个样本的人脸识别（face recognition with single sample per person, SSPP）是一个非常有挑战性的任务，因为在这种情况下很难通过标准样本库（gallery set）里面的样本对待测样本（query sample）的人脸变化量（facial variation）进行预测;

2. 针对这个问题，这篇论文提出了一个基于局部通用表示（local generic representation）框架的人脸识别算法;

3. 该算法通过从标准样本库（gallery dataset）中抽取相邻的人脸图像块来建立一个局部标准字典（local gallery dictionary），并且利用外部的一个通用数据集（generic dataset)来建立一个类内变量字典（intra-class variation dictionary），从而实现的对可能的人脸变化量的预测（不同的光照，姿势，表情，遮挡物等）；

4. 该算法最小化待识别样本（query sample）与局部标准字典（local gallery dictionary）和通用变量字典（generic variation dictionary）的残差（residual），并且使用相关熵（correntropy）来每个图像块的表示残差（representation residual）。

算法框架

原文地址：https://www.cnblogs.com/wumh7/p/9345118.html

时间： 2024-10-18 13:54:33

Local Generic Representation for Face Recognition with Single Sample per Person (ACCV, 2014)的相关文章

{ICIP2014}{收录论文列表}

This article come from HEREARS-L1: Learning Tuesday 10:30–12:30; Oral Session; Room: Leonard de Vinci 10:30  ARS-L1.1—GROUP STRUCTURED DIRTY DICTIONARY LEARNING FOR CLASSIFICATION Yuanming Suo, Minh Dao, Trac Tran, Johns Hopkins University, USA; Hojj

56 Facial Recognition Research Groups to Watch

56 Facial Recognition Research Groups to Watch The research of facial recognition has been a fascinating journey. It began in the 1960s with Woody Bledsoe, Helen Chan Wolf, and Charles Bisson who created programs to assist with basic face recognition

Very Deep Convolutional Networks for Large-Scale Image Recognition

Very Deep Convolutional Networks for Large-Scale Image Recognition 转载请注明:http://blog.csdn.net/stdcoutzyx/article/details/39736509 这篇论文是今年9月份的论文[1],比較新,当中的观点感觉对卷积神经网络的參数调整大有指导作用,特总结之. 关于卷积神经网络(Convolutional Neural Network, CNN),笔者后会作文阐述之,读者若心急则或可用谷歌百度

深度学习笔记（二）Very Deep Convolutional Networks for Large-Scale Image Recognition

Very Deep Convolutional Networks for Large-Scale Image Recognition 1. 主要贡献 本文探究了参数总数基本不变的情况下,CNN随着层数的增加,其效果的变化.(thorough evaluation of networks of increasing depth using an architecture with very small (3×3) convolution filters, which shows that a si

配置 vCenter Single Sign-On 中

本篇是承接上一篇 编辑vCenter Single Sign-On 令牌策略     vCenter Single Sign-On 令牌策略指定时钟容错.续订次数以及其他令牌属性.您可以编辑 vCenter Single SignOn 令牌策略以确保令牌规范遵从贵公司的安全标准. 步骤    1 登录到vSphere Web Client. 2 选择管理> Single Sign-On,然后选择配置. 3 单击策略选项卡,然后选择令牌策略. vSphere Web Client 将显示当前的配置

Very Deep Convolutional Networks for Large-Scale Image Recognition—VGG论文翻译

Very Deep Convolutional Networks for Large-Scale Image Recognition Karen Simonyan∗ & Andrew Zisserman+ Visual Geometry Group, Department of Engineering Science, University of Oxford {karen,az}@robots.ox.ac.uk 摘要 在这项工作中,我们研究了在大规模的图像识别环境下卷积网络的深度对识别的准确率

总结一些机器视觉库

通用库/General Library OpenCV   无需多言. RAVL  Recognition And Vision Library. 线程安全.强大的IO机制.包含AAM. CImg  很酷的一个图像处理包.整个库只有一个头文件.包含一个基于PDE的光流算法. 图像,视频IO/Image, Video IO FreeImage DevIL ImageMagick FFMPEG VideoInput portVideo AR相关/Augmented Reality ARToolKit 

转载：2013计算机视觉代码合集

转载,原文地址http://blog.csdn.net/daoqinglin/article/details/23607079 -------------------------------------------------------------------------- 来源: http://www.yuanyong.org/cv/cv-code-one.html http://www.yuanyong.org/cv/cv-code-two.html http://www.yuanyong

机器视觉开源代码集合

来源:http://xilinx.eetrend.com/article/8919 一.特征提取Feature Extraction: SIFT [1] [Demo program][SIFT Library] [VLFeat] PCA-SIFT [2] [Project] Affine-SIFT [3] [Project] SURF [4] [OpenSURF] [Matlab Wrapper] Affine Covariant Features [5] [Oxford project] MS