Opencv 如何最大限度地减少人脸检测误差

下面是代码，我可以同时检测人脸和嘴巴，并且可以大致测量其边界框的距离有几个问题：

您不应该在

draw（）

中每秒多次加载OpenCV级联。您应该在

setup（）

中执行一次，然后在

draw（）中调用
detect（）

OpenCV for Processing似乎用在第一个实例中加载的级联覆盖在第二个实例中加载的级联

如果准确度不是一个大问题，你可以通过一个简单的级联来解决：嘴级联。请注意，您可以使用检测功能的选项/提示来帮助检测。例如，你可以告诉检测器只检测最大的物体，给它一个提示，告诉它嘴在你的设置中会有最小和最大的边界框，以及过滤掉多少结果

下面是上面的代码示例：

import gab.opencv.*;
import java.awt.Rectangle;
import org.opencv.objdetect.Objdetect;
import processing.video.*;

Capture video;
OpenCV opencv;

//cascade detections parameters - explanations from Mastering OpenCV with Practical Computer Vision Projects
int flags = Objdetect.CASCADE_FIND_BIGGEST_OBJECT;
// Smallest object size.
int minFeatureSize = 20;
int maxFeatureSize = 80;
// How detailed should the search be. Must be larger than 1.0.
float searchScaleFactor = 1.1f;
// How much the detections should be filtered out. This should depend on how bad false detections are to your system.
// minNeighbors=2 means lots of good+bad detections, and minNeighbors=6 means good detections are given but some are missed.
int minNeighbors = 6;

void setup() {
  size(320, 240);
  noFill();
  stroke(0, 192, 0);
  strokeWeight(3);

  video = new Capture(this,width,height);
  video.start();

  opencv  = new OpenCV(this,320,240);
  opencv.loadCascade(OpenCV.CASCADE_MOUTH);
}

void draw() {
  //feed cam image to OpenCV, it turns it to grayscale
  opencv.loadImage(video);
  opencv.equalizeHistogram();
  image(opencv.getOutput(), 0, 0 );

  Rectangle[] mouths = opencv.detect(searchScaleFactor,minNeighbors,flags,minFeatureSize, maxFeatureSize);
  for (int i = 0; i < mouths.length; i++) {
    text(mouths[i].x + "," + mouths[i].y + "," + mouths[i].width + "," + mouths[i].height,mouths[i].x, mouths[i].y);
    rect(mouths[i].x, mouths[i].y, mouths[i].width, mouths[i].height);
  }
}
void captureEvent(Capture c) {
  c.read();
}

导入gab.opencv.*；
导入java.awt.Rectangle；
导入org.opencv.objdetect.objdetect；
导入处理。视频。*；
捕获视频；
OpenCV-OpenCV；
//级联检测参数-使用实际计算机视觉项目掌握OpenCV的说明
int flags=Objdetect.CASCADE\u FIND\u max\u OBJECT；
//最小对象大小。
int minFeatureSize=20；
int maxFeatureSize=80；
//搜索应该有多详细。必须大于1.0。
浮点搜索比例因子=1.1f；
//应该过滤掉多少检测。这应该取决于错误检测对系统的影响程度。
//minNeighbors=2表示有很多好的+坏的检测，minNeighbors=6表示给出了好的检测，但遗漏了一些。
int-minNeighbors=6；
无效设置（）{
尺寸（320240）；
noFill（）；
冲程（0,192,0）；
冲程重量（3）；
视频=新捕获（此、宽度、高度）；
video.start（）；
opencv=新的opencv（这是320240）；
opencv.loadCascade（opencv.CASCADE\u嘴）；
}
作废提款（）{
//将cam图像馈送到OpenCV，它将其转换为灰度
opencv.loadImage（视频）；
opencv.直方图（）；
图像（opencv.getOutput（），0,0）；
矩形[]口=opencv.detect（searchScaleFactor、minNeighbors、flags、minFeatureSize、maxFeatureSize）；
for（int i=0；i

请注意，面部毛发可能会导致误报。 我在一篇文章中提供了更深入的注释。我建议将重点放在FaceOSC部分，因为它会更准确

import gab.opencv.*;
import java.awt.Rectangle;
import org.opencv.objdetect.Objdetect;
import processing.video.*;

Capture video;
OpenCV opencv;

//cascade detections parameters - explanations from Mastering OpenCV with Practical Computer Vision Projects
int flags = Objdetect.CASCADE_FIND_BIGGEST_OBJECT;
// Smallest object size.
int minFeatureSize = 20;
int maxFeatureSize = 80;
// How detailed should the search be. Must be larger than 1.0.
float searchScaleFactor = 1.1f;
// How much the detections should be filtered out. This should depend on how bad false detections are to your system.
// minNeighbors=2 means lots of good+bad detections, and minNeighbors=6 means good detections are given but some are missed.
int minNeighbors = 6;

void setup() {
  size(320, 240);
  noFill();
  stroke(0, 192, 0);
  strokeWeight(3);

  video = new Capture(this,width,height);
  video.start();

  opencv  = new OpenCV(this,320,240);
  opencv.loadCascade(OpenCV.CASCADE_MOUTH);
}

void draw() {
  //feed cam image to OpenCV, it turns it to grayscale
  opencv.loadImage(video);
  opencv.equalizeHistogram();
  image(opencv.getOutput(), 0, 0 );

  Rectangle[] mouths = opencv.detect(searchScaleFactor,minNeighbors,flags,minFeatureSize, maxFeatureSize);
  for (int i = 0; i < mouths.length; i++) {
    text(mouths[i].x + "," + mouths[i].y + "," + mouths[i].width + "," + mouths[i].height,mouths[i].x, mouths[i].y);
    rect(mouths[i].x, mouths[i].y, mouths[i].width, mouths[i].height);
  }
}
void captureEvent(Capture c) {
  c.read();
}