简体   繁体   English

哈尔级联 XML

[英]Haar Cascade XML

I am interested in what everything in the xml file below means:我对以下 xml 文件中的所有内容感兴趣:

<stages>
<trees>
<feature>
<rects>
<_>
<tilted>
<threshold>
<left_val>
<right_val>

and what the five integers in between rects mean.以及矩形之间的五个整数是什么意思。

        <feature>
          <rects>
            <_>
              14 18 1 2 -1.</_>
            <_>
              14 19 1 1 2.</_></rects>
          <tilted>0</tilted></feature>
        <threshold>-4.3883759644813836e-005</threshold>
        <left_val>0.3130159080028534</left_val>

OK, you are making this a bit harder than it has to be, but I'll try.好吧,你让这变得比它必须的更难了,但我会试试的。 I guess, you are asking about object detectors in OpnenCV.我想,您是在询问 OpnenCV 中的 object 检测器。 These are cascades of boosted classifiers which originate from Viola&Jones face detector which classify each image region/patch into object/background classes and are called scanning window object detectors .这些是源自Viola&Jones 人脸检测器级联增强分类器,将每个图像区域/补丁分类为对象/背景类,称为扫描 window object 检测器

  • <stages> is a series of more and more complex classifiers which try identify if an image patch contains a face (with higher and higher confidence). <stages>是一系列越来越复杂的分类器,它们尝试识别图像块是否包含人脸(具有越来越高的置信度)。
  • <trees> should be even simpler classifiers which the stages are composed of. <trees>应该是组成阶段的更简单的分类器。
  • <feature> is a simple hand-coded feature which extracts single value from an image. <feature>是一个简单的手工编码特征,它从图像中提取单个值。
  • <rects> are rectangular regions a feature is composed of. <rects>是组成特征的矩形区域。
  • <tilted> could be a binary value - if the feature is 45° rotated. <tilted>可以是二进制值 - 如果特征旋转 45°。
  • <threshod> is a threhold of the value of the feature . <threshod>特征值的阈值。
  • <left_val> is a vote about the probability that the classified region contains face if the value of the feature is below the <threshold> . <left_val>是关于如果特征值低于<threshold>分类区域包含人脸的概率投票
  • <right_val> is a vote about the probability that the classified region contains face if the value of the feature is above the <threshold> . <right_val>是关于如果特征值高于<threshold>分类区域包含人脸的概率投票

PS: I could be wrong, I did my Ph.D. PS:我可能错了,我读的是博士学位。 on this type of classifiers, I did not write OpenCV.在这类分类器上,我没有写 OpenCV。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM