FalseAcceptRate = FalseAcceptCount / Length(AcceptScoresList) FalseRejectRate = FalseRejectCount / length(RejectScoresList) Add plot to error curve at (FalseRejectRate, FalseAcceptRate)
These two error rates express the inadequacies of the system when operating at a
specific threshold value. Ideally, both these figures should be zero, but in reality reducing either the FAR or FRR (by altering the threshold value) will inevitably result
in increasing the other. Therefore, in order to describe the full operating range of a particular system, we vary the threshold value through the entire range of scores produced. The application of each threshold value produces an additional FAR, FRR pair, which when plotted on a graph produces the error rate curve shown below.
6
Figure 4-5 - Example Error Rate Curve produced by the verification test.
The equal error rate (EER) can be seen as the point at which FAR is equal to FRR. This EER value is often used as a single figure representing the general recognition
performance of a biometric system and allows for easy visual comparison of multiple methods. However, it is important to note that the EER does not indicate the level of error that would be expected in a real world application. It is unlikely that any real system would use a threshold value such that the percentage of false acceptances were equal to the percentage of false rejections. Secure site access systems would typically set the threshold such that false acceptances were significantly lower than false rejections: unwilling to tolerate intruders at the cost of inconvenient access denials. Surveillance systems on the other hand would require low false rejection rates to
successfully identify people in a less controlled environment. Therefore we should bear in mind that a system with a lower EER might not necessarily be the better performer towards the extremes of its operating capability.
There is a strong connection between the above graph and the receiver operating characteristic (ROC) curves, also used in such experiments. Both graphs are simply two visualisations of the same results, in that the ROC format uses the True Acceptance Rate(TAR), where TAR = 1.0 – FRR in place of the FRR, effectively flipping the graph vertically. Another visualisation of the verification test results is to display both the FRR and FAR as functions of the threshold value. This presentation format provides a reference to determine the threshold value necessary to achieve a specific FRR and FAR. The EER can be seen as the point where the two curves intersect.
7
Figure 4-6 - Example error rate curve as a function of the score threshold
The fluctuation of these error curves due to noise and other errors is dependant on the number of face image comparisons made to generate the data. A small dataset that only allows for a small number of comparisons will results in a jagged curve, in which large steps correspond to the influence of a single image on a high proportion of the
comparisons made. A typical dataset of 720 images (as used in section 4.2.2) provides 258,840 verification operations, hence a drop of 1% EER represents an additional 2588 correct decisions, whereas the quality of a single image could cause the EER to fluctuate by up to 0.28.
4.2.2 Results
As a simple experiment to test the direct correlation method, we apply the technique described above to a test set of 720 images of 60 different people, taken from the AR Face Database [ 39 ]. Every image is compared with every other image in the test set to produce a likeness score, providing 258,840 verification operations from which to calculate false acceptance rates and false rejection rates. The error curve produced is shown in Figure 4-7.
Figure 4-7 - Error rate curve produced by the direct correlation method using no image preprocessing.
We see that an EER of 25.1% is produced, meaning that at the EER threshold
8
approximately one quarter of all verification operations carried out resulted in an incorrect classification. There are a number of well-known reasons for this poor level
of accuracy. Tiny changes in lighting, expression or head orientation cause the location in image space to change dramatically. Images in face space are moved far apart due to these image capture conditions, despite being of the same person’s face. The distance between images of different people becomes smaller than the area of face space covered by images of the same person and hence false acceptances and false rejections occur frequently. Other disadvantages include the large amount of storage necessary for holding many face images and the intensive processing required for each comparison, making this method unsuitable for applications applied to a large database. In section 4.3 we explore the eigenface method, which attempts to address some of these issues.
4 二维人脸识别 4.1 功能定位
在讨论比较两个人脸图像，我们现在就简要介绍的方法一些在人脸特征的初步调整过程。这一过程通常两个阶段组成：人脸检测和眼睛定位。根据不同的申请时，如果在面部图像的立场是众所周知事先（对于合作的主题，例如在门禁系统），那么人脸检测阶段通常可以跳过，作为地区的利益是已知的。因此，我们讨论眼睛定位在这里，有一个人脸检测的文献简短讨论（第3.1.1）。眼睛定位方法用于对齐的各种测试二维人脸图像集通篇使用这一节。但是，为了确保所有的结果都呈现代表面部识别准确率，而不是对产品的性能例行的眼睛定位，所有图像路线是手动检查，若有错误更正前的测试和评价。我们发现在一个使用图像的眼睛一个简单的基于模板的位置方法。训练集的前脸手动对齐图像是采取和各图片进行裁剪，以两只眼睛周围的地区。平均计算，用形象作为一个模板。
图4-1 - 平均眼睛，用作模板的眼睛检测
两个眼睛都包括在一个模板，而不是单独为每个搜索，因为眼睛的任一鼻子两边对称的特点，提供了一个有用的功能，可以帮助区分眼睛和其他可能误报被拾起的背景。虽然这种方法在介绍了假设眼近水平的形象出现后很容易受到规模（即主体距离相机）的影响，但一些初步试验还显示，还是有利于包括眼睛下方的皮肤区域得，因为在某些情况下，眉毛可以密切配合模板，特别是如果有在眼插座的阴影。此外眼睛以下的皮肤面积有助于区分从眉毛（眉毛下方的面积眼中包含的眼睛，而该地区眼睛下面的皮肤只含有纯）。窗口
9
是通过对测试图像和绝对差采取的这一平均眼睛上面显示的图像。图像的最低差额面积作为含有眼中感兴趣的区域。运用同样的程序使用小模板个人左，右眼，然后提炼每只眼睛的位置。
这个基本模板的眼睛定位方法，尽管提供相当精确的本地化，往往不能找到完全的眼睛。但是，我们能够改善计划包括加权性能。
眼睛定位是在执行训练图像，然后被分成集两套：在哪些眼检测成功的，和那些在其中眼检测失败的。以成功的本地化设置，我们在计算平均距离眼睛模板（图4-2顶部）时，请注意，该图像是非常黑暗的，这表明发现眼睛密切相关的眼睛模板，正如我们期望的那样。然而，亮点确实发生靠近眼睛的白人，这表明这方面经常是不一致的，不同于普通模板。
图4-2 - 距离对眼睛模板成功检测（上），指出由于方差噪音和失败的检测（下）显示，
由于错过可信的差异，检测功能。
在较低的图像（图4-2下），我们已经采取了失败的本地化设置（在前额，鼻子图像，脸颊，背景等虚假的检测本地化例程），并再次从眼睛计算的平均距离模板。明亮的学生由暗区包围表明，一个失败的匹配往往由于鼻子和颧骨地区绝大多数的高相关性差相关的学生。想强调地区差异的学生为这些失败的比赛，尽量减少对眼睛的白人成功的变异比赛中，我们除以上的形象价值较低的图像产生重矢量，如图4-3所示。当应用到差分图像在总结前一总误差，这个比重计划提供了一个很大的提高检出率。
图 4-3
4.2直接相关方法
我们把最简单的方法人脸识别调查称为直接相关方法（也称为模板匹配的布鲁内利和波焦[29]）所涉及的像素亮度值直接比较取自面部图像。我们使用的术语'直接关系'，以涵盖所有在图像技术所面临的直接比较，没有任何形式的形象空间分析，加权计划或特征提取，无论距离
度量使用。因此，我们并不推断，皮尔逊的相关性，作为应用相似的功能（尽管这种做法显然会受到我们的直接相关的定义）。我们通常使用欧氏距离度量作为我们的在这些调查（负相关，Pearson相关，可以考虑作为一个规模和翻译的图像相关敏感的形式），因为这
10
毕业论文设计--人脸识别论文文献翻译中英文
