前几天逛知乎看到有免费的工具来做人脸识别，觉得很有意思；心血来潮，想自己也搞一个人脸识别；不得不说虹软ArcFace真的是太好用了；对于我这种完全不懂人脸识别算法的人，也可以构建出人脸识别的应用；只需要调用封装好的API就行了。
环境准备：

1.到虹软ArcFace官网下载虹软ArcFacezip格式的压缩文件，解压后将libs文件夹copy到自己的工程下，注意libs文件下有一个：arcsoft-sdk-face-3.0.0.0.jar，添加工程对jar的路径依赖；
2.maven下载opencv;

    <!--opencv--><dependency><groupId>org.bytedeco</groupId><artifactId>javacv-platform</artifactId><version>1.4.1</version></dependency><dependency><groupId>org.bytedeco.javacpp-presets</groupId><artifactId>opencv-platform</artifactId><version>3.4.1-1.4.1</version></dependency><!-- jna:调用windows系统的API~--><dependency><groupId>net.java.dev.jna</groupId><artifactId>jna</artifactId><version>5.8.0</version></dependency><dependency><groupId>net.java.dev.jna</groupId><artifactId>jna-platform</artifactId><version>5.8.0</version></dependency>

项目的结构：

arcFace

从官方下载的zip文件节后，samplecode文件夹下FaceEngineTest.java是官方给出的示例代码；下面是人脸特征对比部分的代码：

        //从官网获取String appId = "";String sdkKey = "";//加载dll文件，就是最开始准备的libs下面的dll文件路径；      FaceEngine faceEngine = new FaceEngine("E:/Project/2021/face-learning/libs/WIN64");//激活引擎int errorCode = faceEngine.activeOnline(appId, sdkKey);if (errorCode != ErrorInfo.MOK.getValue() && errorCode != ErrorInfo.MERR_ASF_ALREADY_ACTIVATED.getValue()) {System.out.println("引擎激活失败");}ActiveFileInfo activeFileInfo=new ActiveFileInfo();errorCode = faceEngine.getActiveFileInfo(activeFileInfo);if (errorCode != ErrorInfo.MOK.getValue() && errorCode != ErrorInfo.MERR_ASF_ALREADY_ACTIVATED.getValue()) {System.out.println("获取激活文件信息失败");}//引擎配置EngineConfiguration engineConfiguration = new EngineConfiguration();engineConfiguration.setDetectMode(DetectMode.ASF_DETECT_MODE_IMAGE);engineConfiguration.setDetectFaceOrientPriority(DetectOrient.ASF_OP_ALL_OUT);engineConfiguration.setDetectFaceMaxNum(10);engineConfiguration.setDetectFaceScaleVal(16);//功能配置FunctionConfiguration functionConfiguration = new FunctionConfiguration();functionConfiguration.setSupportAge(true);functionConfiguration.setSupportFace3dAngle(true);functionConfiguration.setSupportFaceDetect(true);functionConfiguration.setSupportFaceRecognition(true);functionConfiguration.setSupportGender(true);functionConfiguration.setSupportLiveness(true);functionConfiguration.setSupportIRLiveness(true);engineConfiguration.setFunctionConfiguration(functionConfiguration);//初始化引擎errorCode = faceEngine.init(engineConfiguration);if (errorCode != ErrorInfo.MOK.getValue()) {System.out.println("初始化引擎失败");}//人脸检测ImageInfo imageInfo = ImageFactory.getRGBData(new File("C:\\Users\\Pictures\\b0488b9ed27271eab692bd0097fe67ce.jpeg"));List<FaceInfo> faceInfoList = new ArrayList<FaceInfo>();errorCode = faceEngine.detectFaces(imageInfo.getImageData(), imageInfo.getWidth(), imageInfo.getHeight(), imageInfo.getImageFormat(), faceInfoList);System.out.println(faceInfoList);//特征提取FaceFeature faceFeature = new FaceFeature();errorCode = faceEngine.extractFaceFeature(imageInfo.getImageData(), imageInfo.getWidth(), imageInfo.getHeight(), imageInfo.getImageFormat(), faceInfoList.get(0), faceFeature);System.out.println("特征值1大小：" + faceFeature.getFeatureData().length);//人脸检测2ImageInfo imageInfo2 = ImageFactory.getRGBData(new File("C:\\Users\\Pictures\\WIN_20210628_13_25_19_Pro.jpg"));List<FaceInfo> faceInfoList2 = new ArrayList<FaceInfo>();errorCode = faceEngine.detectFaces(imageInfo2.getImageData(), imageInfo2.getWidth(), imageInfo2.getHeight(),imageInfo.getImageFormat(), faceInfoList2);System.out.println(faceInfoList);//特征提取2FaceFeature faceFeature2 = new FaceFeature();errorCode = faceEngine.extractFaceFeature(imageInfo2.getImageData(), imageInfo2.getWidth(), imageInfo2.getHeight(), imageInfo.getImageFormat(), faceInfoList2.get(0), faceFeature2);System.out.println("特征值2大小：" + faceFeature2.getFeatureData().length);//特征比对FaceSimilar faceSimilar = new FaceSimilar();errorCode = faceEngine.compareFaceFeature(faceFeature, faceFeature2, faceSimilar);System.out.println("相似度：" + faceSimilar.getScore());

上面这段代码流程：

1.FaceEngine引擎对象创建（加载dll文件）
2.激活引擎
3.引擎配置,功能配置
4.初始化引擎
5.分别做2张图片的：人脸检测：imageInfo（人脸信息），特征提取：faceFeatur（人脸特征）
6.对比2张图片的人脸特征，得出相似度FaceSimilar

opencv

用opencv调用摄像头，获取实时的人脸信息；

OpenCVFrameGrabber grabber = new OpenCVFrameGrabber(0);Java2DFrameConverter converter =  new Java2DFrameConverter();grabber.start();   //开始获取摄像头数据Frame frame = grabber.grab();//获取此刻的图像数据BufferedImage bufferedImage = converter.convert(frame);//opencv：用Java2DFrameConverter将Frame转化成BufferedImage ImageInfo imageInfo =ImageFactory.bufferedImage2ImageInfo(bufferedImage);//ArcFace：获取到人脸信息；

opencv_ArcFace

将上面的代码整合一下


public class TestArcFace{static  String appId = "";static String sdkKey = "";static String enginePath ="E:/Project/2021/face-learning/libs/WIN64";static OpenCVFrameGrabber grabber = new OpenCVFrameGrabber(0);static Java2DFrameConverter converter =  new Java2DFrameConverter();public static void main(String[] args) throws Throwable{FaceEngine faceEngine = getFaceEngine();//获取FaceEnginegrabber.start();//开启摄像头FaceFeature bossFace = getFaceFeature(faceEngine,getImageInfoFromPicture("")).get(0);//从boss的单人照中获取boss脸部特征boolean bossComing=false;while(!bossComing){//检测boss是否出现摄像头中；List<FaceFeature> captureFaces  = getFaceFeature(faceEngine,getImageInfoFromCamera());//捕获出现在镜头中的人脸特征for (FaceFeature captureFace : captureFaces) {//遍历list检测捕获到的人脸特征FaceSimilar faceSimilar = getFaceSimilar(faceEngine,captureFace,bossFace);if(samePeople(faceSimilar,0.8f)){//boss出现bossComing=true;break;}}Thread.sleep(100);//每隔100ms检测一次，检测boss是否出现在镜头中。。}User32.INSTANCE.LockWorkStation();//锁屏grabber.stop();faceEngine.unInit();
}public static FaceEngine getFaceEngine(){FaceEngine faceEngine = new FaceEngine(enginePath);int errorCode = faceEngine.activeOnline(appId, sdkKey);if (errorCode != ErrorInfo.MOK.getValue() && errorCode != ErrorInfo.MERR_ASF_ALREADY_ACTIVATED.getValue()) {System.out.println("引擎激活失败");}ActiveFileInfo activeFileInfo=new ActiveFileInfo();errorCode = faceEngine.getActiveFileInfo(activeFileInfo);if (errorCode != ErrorInfo.MOK.getValue() && errorCode != ErrorInfo.MERR_ASF_ALREADY_ACTIVATED.getValue()) {System.out.println("获取激活文件信息失败");}//引擎配置EngineConfiguration engineConfiguration = new EngineConfiguration();engineConfiguration.setDetectMode(DetectMode.ASF_DETECT_MODE_IMAGE);engineConfiguration.setDetectFaceOrientPriority(DetectOrient.ASF_OP_ALL_OUT);engineConfiguration.setDetectFaceMaxNum(10);//图片中人脸数engineConfiguration.setDetectFaceScaleVal(30);//人脸相对于所在图片的长边的占比,建议16//功能配置FunctionConfiguration functionConfiguration = new FunctionConfiguration();functionConfiguration.setSupportAge(true);functionConfiguration.setSupportFace3dAngle(true);functionConfiguration.setSupportFaceDetect(true);functionConfiguration.setSupportFaceRecognition(true);functionConfiguration.setSupportGender(true);functionConfiguration.setSupportLiveness(true);functionConfiguration.setSupportIRLiveness(true);engineConfiguration.setFunctionConfiguration(functionConfiguration);//初始化引擎errorCode = faceEngine.init(engineConfiguration);if(ErrorInfo.MOK.getValue()!= errorCode){throw new RuntimeException("初始化引擎失败。。。errorCode："+errorCode);}return faceEngine;}/*获取图片中人脸信息*/public static ImageInfo getImageInfoFromPicture(String picturePath){return ImageFactory.getRGBData(new File(picturePath));}/*从摄像头中获取到人脸信息;*/public static ImageInfo getImageInfoFromCamera() throws FrameGrabber.Exception {Frame frame = grabber.grab();BufferedImage bufferedImage = converter.convert(frame);return ImageFactory.bufferedImage2ImageInfo(bufferedImage);}/*获取ImageInfo人脸特征*/public  static List<FaceFeature> getFaceFeature(FaceEngine faceEngine,ImageInfo imageInfo){List<FaceInfo> faceInfoList = new ArrayList<FaceInfo>();List<FaceFeature> faceFeatures = new ArrayList<>();//提取人脸信息faceEngine.detectFaces(imageInfo.getImageData(),imageInfo.getWidth(),imageInfo.getHeight(),imageInfo.getImageFormat(),faceInfoList);if(!faceInfoList.isEmpty()){//提取人脸特征for (FaceInfo faceInfo : faceInfoList) {FaceFeature faceFeature = new FaceFeature();faceEngine.extractFaceFeature(imageInfo.getImageData(),imageInfo.getWidth(),imageInfo.getHeight(),imageInfo.getImageFormat(),faceInfo,faceFeature);faceFeatures.add(faceFeature);}}else{System.out.println("faceInfoList is empty");}return faceFeatures;}/*对比FaceFeature，获取相似度*/public static FaceSimilar getFaceSimilar(FaceEngine faceEngine,FaceFeature captureFaceFeature,FaceFeature target){FaceSimilar faceSimilar = new FaceSimilar();faceEngine.compareFaceFeature(captureFaceFeature,target,faceSimilar);return faceSimilar;}/*判断是否是同一个人，score：自定义设置 ；当相似度超过score，判定是同一人；*/public static boolean samePeople(FaceSimilar faceSimilar,float score){return faceSimilar.getScore()>score?true:false;}}

opencv+ArcFace人脸识别相关推荐

怎样使用OpenCV进行人脸识别
不断维护的地址:http://plzcoding.com/face-recognition-with-opencv/ 怎样使用OpenCV进行人脸识别本文大部分来自OpenCV官网上的Face Re ...
Java使用OpenCV实现人脸识别
通过OpenCV实现人脸识别,包括图片,视频,摄像头中人脸识别. 首先看一下效果(在网上随便找的一张图片): 下面开始说一下如何实现的: 第一步: 需要安装OpenCV 下载链接:https://o ...
python使用opencv实现人脸识别系统
1.首先安装过python环境,在这里就不过说检测是否安装成功如下,在cmd中输入Python 2.安装numpy 现在开始安装numpy,打开cmd,输入pip install nu ...
基于OpenCV实现人脸识别--Python
目录前言第一章 OpenCV介绍第二章功能描述 2.1 对已有的数据进行检测 2.2 陌生人检测并发出警告 2.3 保存陌生人的视频 2.4 输入图片进行检测 2.5 现场录用信息第三章功 ...
java调起本地摄像头，利用openCV进行人脸识别（一）
嗨咯,又好久没有更新了.今天写个前阵子做的人脸识别程序.该程序客户端基于Jave JFrame 客户端的主要作用是,调用电脑的摄像头(我的直接调用笔记本摄像头),然后回显摄像头录取的信息,再利用ope ...
python视频图片识别算法_python利用Opencv进行人脸识别（视频流+图片）
首先:需要在在自己本地安装opencv具体步骤可以问度娘如果从事于开发中的话建议用第三方的人脸识别(推荐阿里) 1.视频流中进行人脸识别 # -*- coding: utf-8 -*- import ...
opencv + face_recognition —— 人脸识别案例
文章目录 opencv + face_recognition -- 人脸识别案例 0. 版本信息 1. 导包 2. 识别图片中的面部 3. 实现摄像头中的面部追踪 4. 人脸追踪+识别,分析出不同的人 ...
树莓派与OpenCV实现人脸识别（OpenCV安装篇）
主要看了以下两位博客的文章完成的,也遇到了不少的坑,在这里一一填补说明. 链接: https://blog.csdn.net/weixin_42163073/article/details/10730 ...
使用OpenCV进行人脸识别的三种算法（官方网翻译）
怎样使用OpenCV进行人脸识别本文大部分来自OpenCV官网上的Face Reconition with OpenCV这节内容(http://docs.opencv.org/modules/con ...
基于OpenCV的人脸识别自助商店（源码＆部署视频）
1.模块功能介绍实现人脸识别模块.人脸登录与注册功能.商店显示和用户余额页显示功能用GUl图形界面实现(pyqt)语言python windows下软件pycharm 1.用户登录模块:刷脸登录 ...

opencv+ArcFace人脸识别

arcFace

opencv

opencv_ArcFace

opencv+ArcFace人脸识别相关推荐

最新文章

热门文章