Java OpenCV实现人脸识别过程详解

Java OpenCV实现人脸识别过程详解

准备 :

下载openCV安装包 :  https://opencv.org/

安装包安装之后支持多种语言环境，此处使用java，在Eclipse中引入 openCV目录下的java/opencv-320.jar，同时配置openCV库路径。

Eclipse配置openCV

代码实现 :

package test;

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.objdetect.CascadeClassifier;

import org.opencv.imgcodecs.Imgcodecs;

import org.opencv.imgproc.Imgproc;

public class Test {

//引入训练好的人脸识别XML文件

static String PAHT = "E:/GOF/OpenCV/bin/test/haarcascade_frontalface_alt.xml";

static String IMAGE_PATH = "E:/GOF/OpenCV/src/test/a.jpg";http://

static String productPath = "E:/GOF/OpenCV";

public static void main(String[] args) {

System.loadLibrary(Core.NATIVE_LIBRARY_NAME);

String Path = Test.class.getResource("haarcascade_frontalface_alt.xml").getPath();

System.out.println(Path);

CascadeClassifier faceDetector = new CascadeClassifier(PAHT);

Mat image = Imgcodecs.imread(IMAGE_PATH);

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 = "ouput.png";

System.out.println(String.format("Writing %s", filename));

boolean flag = Imgcodecs.imwrite(filename, image);

}

}

实现效果 :

对人脸区域写入边框

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。