Face recognition using Histograms of Oriented Gradients

这篇论文的主要内容是将Hog算子应用到人脸识别上。

转载请注明:http://blog.csdn.net/stdcoutzyx/article/details/40757997

1. Main Contribution

  • Extract Hog descriptors from a regular grid.

  • Fusion of HOG descriptors at different scales allows to capture important structure

  • Dimensionality reduction is necessary to make the classification less prone to over-fitting.

2. Feature Conclusion

Features includes geometric or photometric, latter seems to have prevailed in the literature:

  • Eigenfaces( Principal Component Analysis)
  • Gabor wavelets
  • Local Binary Patterns
  • Error-Correcting Output Codes
  • Independent Component Analysis

3. Improved Hog

Improved Hog for invariance to scale and rotation may be also achieved by extracting descriptors from only salient points (key points) in the scale space following a rotation normalization. The steps involved are:

  • Scale-space extrema detection. (achieve scale invariance)
  • Orientation assignment. (find the dominant gradient orientation)
  • Descriptor extraction.

4. Previous Hog representation for faces

In (Albiol et al., 2008), the authors successfully applied Hog to the face recognition.

  • In the 2008 paper, faces are previous normalized in scale and orientation, So the step for scale-space extrema detection were not necessary.
  • A set of 25 facial landmarks were localizaed using Active Apperence Models(AAMs).
  • Hog descriptors are extracted from the vicinity of each of these 25 landmarks.
  • Using nearest neighbor and Enclidean distance to classify.

Drawback of this method:

  • Final error may crucially depend on the reliability of the landmark localizations, and the landmarks are not precisely due to occlusions, strong illuminations or pose changes.

5. Improved Method by this paper

  • First normalize the face and then extract HOG features from a regular grid. The grid is formed by placing equal side patches around a first cell centered in the image, until the whole image is covered.
  • The paper hypothesize that a better result could be obtained by combining information from different patch sizes. And the paper considered a new fusion strategy that is the product combination of the classifiers at patch sizes.
  • Several overlapping patches are used, so the final feature representation will be highly redundant, So dimensionality reduction is necessary.

5.1 Detail of the fusion strategy

  • R individual classifications c_k (k=1,…,R), each one trained using Hog features with different patch sizes. Each classifier gives one input sample x_k a posterior probability vector:

  • The product rule cosists of fusing the final decision as:

6. Experiments

  • Effect of the facial feature localization error on the final recognition performance. Large error on the localization of facial features leads to bad classification performance.

    • Evaluate the performance of the method in 4.
    • Calculate the dispersion of coordinates(ellpse fitting) and the total sum of variances of the localized landmarks. Bigger variance, bad performance.
  • Extracting regular grids and patch size combination
    • Hog features are processed by PCA and LDA.
    • Nearest classifier with Enclidean and cosine distances is used.
    • Combination of 8×8, 12×12, 16×16, 20×20, 24×24, 28×28 patches.
    • Compare of computation time of the landmark method and the regular grid method.

7. Reference

  • [1]. Déniz O, Bueno G, Salido J, et al. Face recognition using histograms of oriented gradients[J]. Pattern Recognition Letters, 2011, 32(12): 1598-1603.

Face recognition using Histograms of Oriented Gradients的更多相关文章

  1. 行人检測之HOG特征(Histograms of Oriented Gradients)

    之前的文章行人计数.计次提到HOG特征这个概念,这两天看了一下原版的论文,了解了一下HOG特征的原理,并依据自己的理解将这种方法的流程写了下来,假设有不正确的地方欢迎指正. HOG(Histogram ...

  2. (转)梯度方向直方图HOG(Histograms of Oriented Gradients )

    HOG(Histograms of Oriented Gradients )梯度方向直方图 方向梯度直方图(Histogram of Oriented Gradient, HOG)特征是一种在计算机视 ...

  3. 机器视觉 Histogram of oriented gradients

    Histogram of oriented gradients 简称 HoG, 是计算机视觉和图像处理领域一种非常重要的特征,被广泛地应用于物体检测,人脸检测,人脸表情检测等. HoG 最早是在200 ...

  4. 【翻译】HOG, Histogram of Oriented Gradients / 方向梯度直方图 介绍

    本文翻译自 SATYA MALLICK 的 "Histogram of Oriented Gradients" 原文链接: https://www.learnopencv.com/ ...

  5. SIFT(Scale-invariant feature transform) & HOG(histogram of oriented gradients)

    SIFT :scale invariant feature transform HOG:histogram of oriented gradients 这两种方法都是基于图像中梯度的方向直方图的特征提 ...

  6. 【笔记】HOG (Histogram of Oriented Gradients, 方向梯度直方图)的开源实现

    wiki上的介绍 OpenCV的实现 cv::HOGDescriptor Struct Reference opencv cv::HOGDescriptor 的调用例子 HOGDescriptor h ...

  7. 【计算机视觉】Selective Search for Object Recognition论文阅读3

    Selective Search for Object Recoginition surgewong@gmail.com http://blog.csdn.net/surgewong       在前 ...

  8. Histogram of Oriented Gridients(HOG) 方向梯度直方图

    Histogram of Oriented Gridients,缩写为HOG,是目前计算机视觉.模式识别领域很常用的一种描述图像局部纹理的特征.这个特征名字起的也很直白,就是说先计算图片某一区域中不同 ...

  9. 【计算机视觉】Histogram of Oriented Gridients(HOG) 方向梯度直方图

    Histogram of Oriented Gridients(HOG) 方向梯度直方图 Histogram of Oriented Gridients,缩写为HOG,是目前计算机视觉.模式识别领域很 ...

随机推荐

  1. CSS实现垂直居中的常用方法

    在前端开发过程中,盒子居中是常常用到的.其中 ,居中又可以分为水平居中和垂直居中.水平居中是比较容易的,直接设置元素的margin: 0 auto就可以实现.但是垂直居中相对来说是比较复杂一些的.下面 ...

  2. (转)安装 Apache 出现 <OS 10013> 以一种访问权限不允许的方式做了一个访问套接字的尝试

    在安装Apache的过程中出现: 仔细查看提示: make_sock: could not bind to address 0.0.0.0:80 恍然大悟,计算机上安装了IIS7,80端口已占用. 打 ...

  3. (转)jquery.validator规则

      登录|注册     收藏成功 确定 收藏失败,请重新收藏 确定 标题 标题不能为空 网址 标签 摘要   公开 取消收藏             分享资讯 传PPT/文档 提问题 写博客 传资源 ...

  4. [译]一个灵活的 Trello 敏捷工作流

    [译]一个灵活的 Trello 敏捷工作流 翻译自 An Agile Trello Workflow That Keeps Tasks Flexible Getting things done 可不只 ...

  5. android SQLite使用SQLiteOpenHelper类对数据库进行增删查改

    一个简单的例子,当点击按钮时进行相应的操作,效果图如下: 项目代码如下: DatabaseHelper类 package com.example.sqlitedatebasetest; import ...

  6. js 定义函数的几种方法 以及如何调用

    /*1.方法调用模式: 先定义一个对象,然后在对象的属性中定义方法,通过myobject.property来执行方法,this即指当前的myobject 对象.*/ var car = { carId ...

  7. Windows下查看端口被程序占用的方法

      有时安装程序时,会出现XX端口被占用的情况,可以通过CMD命令查看什么程序占用 1. netstat -ano 查看相应端口对应程序的PID 例如:   C:\>netstat -ano A ...

  8. MySQL的truncate table 和source 命令

    1. truncate table XXX     在测试时,我很讨厌某表的主键一直自增长下去,总觉得从1开始最舒服,^_^,truncate table 就可以帮我,相比delete from 来说 ...

  9. java的注释

    最近在做java项目开始关注和注意一些java规范,目的只是为了让自己和别人更容易理解自己写的代码和复用. 一个重要的原则就是:问你自己,你如果从来没有见过这段代码,你要快速地知道这段代码是干什么的, ...

  10. Delphi的IDHTTP的基本用法

    一.IDHTTP的基本用法 IDHttp和WebBrowser一样,都可以实现抓取远端网页的功能,但是http方式更快.更节约资源,缺点是需要手动维护cook,连接等 IDHttp的创建,需要引入ID ...