說到人臉檢測,首先要了解Haar特征分類器。Haar特征分類器說白了就是一個個的xml文件,不同的xml里面描述人體各個部位的特征值,比如人臉、眼睛等等。OpenCV3.2.0中提供了如下特征文件:
haarcascade_eye.xml
haarcascade_eye_tree_eyeglasses.xml
haarcascade_frontalcatface.xml
haarcascade_frontalcatface_extended.xml
haarcascade_frontalface_alt.xml
haarcascade_frontalface_alt_tree.xml
haarcascade_frontalface_alt2.xml
haarcascade_frontalface_default.xml
haarcascade_fullbody.xml
haarcascade_lefteye_2splits.xml
haarcascade_licence_plate_rus_16stages.xml
haarcascade_lowerbody.xml
haarcascade_profileface.xml
haarcascade_righteye_2splits.xml
haarcascade_russian_plate_number.xml
haarcascade_smile.xml
haarcascade_upperbody.xml
通過加載不同的特征文件,就能達到相應的檢測效果。
OpenCV3.2.0中detectMultiScale函數參數說明:
detectMultiScale(Mat image, MatOfRect objects, double scaleFactor, int minNeighbors, int flags, Size minSize, Size maxSize)
image:待檢測圖片,一般為灰度圖(提高效率)
objects:被檢測物體的矩形框向量組
scaleFactor:前后兩次相繼的掃描中,搜索窗口的比例系數。默認為1.1即每次搜索窗口依次擴大10%
minNeighbors:構成檢測目標的相鄰矩形的最小個數(默認為3個)
flags:要么使用默認值,要么使用CV_HAAR_DO_CANNY_PRUNING,如果設置為CV_HAAR_DO_CANNY_PRUNING,那么函數將會使用Canny邊緣檢測來排除邊緣過多或過少的區域,因此這些區域通常不會是人臉所在區域
minSize:得到的目標區域的最小范圍
maxSize:得到的目標區域的最大范圍
人臉檢測示例代碼:
import org.opencv.core.Core;
import org.opencv.core.Mat;
import org.opencv.core.MatOfRect;
import org.opencv.core.Point;
import org.opencv.core.Rect;
import org.opencv.core.Scalar;
import org.opencv.imgcodecs.Imgcodecs;
import org.opencv.imgproc.Imgproc;
import org.opencv.objdetect.CascadeClassifier;
public class FaceDetect
{
public static void main(String[] args)
{
// TODO Auto-generated method stub
System.loadLibrary(Core.NATIVE_LIBRARY_NAME);
System.out.println("\nRunning FaceDetector");
CascadeClassifier faceDetector = new CascadeClassifier();
faceDetector.load(
"C:\\Program Files\\opencv\\sources\\data\\haarcascades\\haarcascade_frontalface_alt.xml");
Mat image = Imgcodecs.imread("F:\\1114.jpg");
MatOfRect faceDetections = new MatOfRect();
faceDetector.detectMultiScale(image, faceDetections);
System.out.println(String.format("Detected %s faces", faceDetections.toArray().length));
for (Rect rect : faceDetections.toArray())
{
Imgproc.rectangle(image, new Point(rect.x, rect.y),
new Point(rect.x + rect.width, rect.y + rect.height), new Scalar(0, 255, 0));
}
String filename = "F:\\ouput.jpg";
Imgcodecs.imwrite(filename, image);
}
}
源圖像與結果圖: