Java 基于OpenCV的不稳定人脸识别

Java 基于OpenCV的不稳定人脸识别,java,android,opencv,javacv,face-recognition,Java,Android,Opencv,Javacv,Face Recognition,我正在开发一个用于人脸识别的android应用程序,它是OpenCV的非官方包装。导入com.googlecode.javacv.cpp.opencv\u contrib.FaceRecognizer后, 我应用并测试以下已知方法: 使用createLBPHFaceRecognizer()方法创建LBPH 使用createFisherFaceRecognizer()方法的FisherFace 使用CreateEigenFaceRecognitor()方法的特征脸 在识别检测到的人脸之前,我先

我正在开发一个用于人脸识别的android应用程序,它是OpenCV的非官方包装。导入
com.googlecode.javacv.cpp.opencv\u contrib.FaceRecognizer
后, 我应用并测试以下已知方法:

  • 使用createLBPHFaceRecognizer()方法创建LBPH
  • 使用createFisherFaceRecognizer()方法的FisherFace
  • 使用CreateEigenFaceRecognitor()方法的特征脸
在识别检测到的人脸之前,我先纠正旋转的人脸,然后裁剪出合适的区域,从

一般来说,当我把数据库中已经存在的人脸传递给摄像机时,识别就可以了。但这并不总是正确的。有时,它以很高的概率识别未知人脸(在训练样本数据库中找不到)。当我们在DB中有两张或两张以上具有相似特征的脸(胡须、胡子、眼镜……)时,这些脸之间的识别可能是高度错误的

为了使用测试人脸图像预测结果,我应用以下代码:

public String predict(Mat m) {

        int n[] = new int[1];
        double p[] = new double[1];
        IplImage ipl = MatToIplImage(m,WIDTH, HEIGHT);

        faceRecognizer.predict(ipl, n, p);

        if (n[0]!=-1)
         mProb=(int)p[0];
        else
            mProb=-1;
            if (n[0] != -1)
            return labelsFile.get(n[0]);
        else
            return "Unkown";
    }
我无法控制概率p的阈值,因为:

  • 小p<50可以预测正确的结果
  • 高p>70可预测错误结果
  • 中间p可以预测正确或错误
同样,我不明白为什么predict()函数在使用LBPH的情况下给出的概率有时大于100???对于Fisher和Eigen,它给出了非常大的值(>2000)?? 有人能帮我找到解决这些奇怪问题的办法吗? 有什么建议可以提高识别的稳健性吗?特别是在两个不同面相似的情况下

以下是使用Facesrecognizer的整个类:

package org.opencv.javacv.facerecognition;

import static  com.googlecode.javacv.cpp.opencv_highgui.*;
import static  com.googlecode.javacv.cpp.opencv_core.*;

import static  com.googlecode.javacv.cpp.opencv_imgproc.*;
import static com.googlecode.javacv.cpp.opencv_contrib.*;

import java.io.File;
import java.io.FileOutputStream;
import java.io.FilenameFilter;
import java.util.ArrayList;

import org.opencv.android.Utils;
import org.opencv.core.Mat;

import com.googlecode.javacv.cpp.opencv_imgproc;
import com.googlecode.javacv.cpp.opencv_contrib.FaceRecognizer;
import com.googlecode.javacv.cpp.opencv_core.IplImage;
import com.googlecode.javacv.cpp.opencv_core.MatVector;

import android.graphics.Bitmap;
import android.os.Environment;
import android.util.Log;
import android.widget.Toast;

public  class PersonRecognizer {

    public final static int MAXIMG = 100;
    FaceRecognizer faceRecognizer;
    String mPath;
    int count=0;
    labels labelsFile;

     static  final int WIDTH= 128;
     static  final int HEIGHT= 128;;
     private int mProb=999;


    PersonRecognizer(String path)
    {
      faceRecognizer =  com.googlecode.javacv.cpp.opencv_contrib.createLBPHFaceRecognizer(2,8,8,8,200);
     // path=Environment.getExternalStorageDirectory()+"/facerecog/faces/";
     mPath=path;
     labelsFile= new labels(mPath);


    }

    void changeRecognizer(int nRec)
    {
        switch(nRec) {
        case 0: faceRecognizer = com.googlecode.javacv.cpp.opencv_contrib.createLBPHFaceRecognizer(1,8,8,8,100);
                break;
        case 1: faceRecognizer = com.googlecode.javacv.cpp.opencv_contrib.createFisherFaceRecognizer();
                break;
        case 2: faceRecognizer = com.googlecode.javacv.cpp.opencv_contrib.createEigenFaceRecognizer();
                break;
        }
        train();

    }

    void add(Mat m, String description) {
        Bitmap bmp= Bitmap.createBitmap(m.width(), m.height(), Bitmap.Config.ARGB_8888);

        Utils.matToBitmap(m,bmp);
        bmp= Bitmap.createScaledBitmap(bmp, WIDTH, HEIGHT, false);

        FileOutputStream f;
        try {
            f = new FileOutputStream(mPath+description+"-"+count+".jpg",true);
            count++;
            bmp.compress(Bitmap.CompressFormat.JPEG, 100, f);
            f.close();

        } catch (Exception e) {
            Log.e("error",e.getCause()+" "+e.getMessage());
            e.printStackTrace();

        }
    }

    public boolean train() {

        File root = new File(mPath);
        Log.i("mPath",mPath);
        FilenameFilter pngFilter = new FilenameFilter() {
            public boolean accept(File dir, String name) {
                return name.toLowerCase().endsWith(".jpg");

        };
        };

        File[] imageFiles = root.listFiles(pngFilter);

        MatVector images = new MatVector(imageFiles.length);

        int[] labels = new int[imageFiles.length];

        int counter = 0;
        int label;

        IplImage img=null;
        IplImage grayImg;

        int i1=mPath.length();


        for (File image : imageFiles) {
            String p = image.getAbsolutePath();
            img = cvLoadImage(p);

            if (img==null)
                Log.e("Error","Error cVLoadImage");
            Log.i("image",p);

            int i2=p.lastIndexOf("-");
            int i3=p.lastIndexOf(".");
            int icount=Integer.parseInt(p.substring(i2+1,i3)); 
            if (count<icount) count++;

            String description=p.substring(i1,i2);

            if (labelsFile.get(description)<0)
                labelsFile.add(description, labelsFile.max()+1);

            label = labelsFile.get(description);

            grayImg = IplImage.create(img.width(), img.height(), IPL_DEPTH_8U, 1);

            cvCvtColor(img, grayImg, CV_BGR2GRAY);

            images.put(counter, grayImg);

            labels[counter] = label;

            counter++;
        }
        if (counter>0)
            if (labelsFile.max()>1)
                faceRecognizer.train(images, labels);
        labelsFile.Save();
    return true;
    }

    public boolean canPredict()
    {
        if (labelsFile.max()>1)
            return true;
        else
            return false;

    }

    public String predict(Mat m) {
        if (!canPredict())
            return "";
        int n[] = new int[1];
        double p[] = new double[1];
        IplImage ipl = MatToIplImage(m,WIDTH, HEIGHT);
//      IplImage ipl = MatToIplImage(m,-1, -1);

        faceRecognizer.predict(ipl, n, p);

        if (n[0]!=-1)
         mProb=(int)p[0];
        else
            mProb=-1;
    //  if ((n[0] != -1)&&(p[0]<95))
        if (n[0] != -1)
            return labelsFile.get(n[0]);
        else
            return "Unkown";
    }




      IplImage MatToIplImage(Mat m,int width,int heigth)
      {


           Bitmap bmp=Bitmap.createBitmap(m.width(), m.height(), Bitmap.Config.ARGB_8888);


           Utils.matToBitmap(m, bmp);
           return BitmapToIplImage(bmp,width, heigth);

      }

    IplImage BitmapToIplImage(Bitmap bmp, int width, int height) {

        if ((width != -1) || (height != -1)) {
            Bitmap bmp2 = Bitmap.createScaledBitmap(bmp, width, height, false);
            bmp = bmp2;
        }

        IplImage image = IplImage.create(bmp.getWidth(), bmp.getHeight(),
                IPL_DEPTH_8U, 4);

        bmp.copyPixelsToBuffer(image.getByteBuffer());

        IplImage grayImg = IplImage.create(image.width(), image.height(),
                IPL_DEPTH_8U, 1);

        cvCvtColor(image, grayImg, opencv_imgproc.CV_BGR2GRAY);

        return grayImg;
    }



    protected void SaveBmp(Bitmap bmp,String path)
      {
            FileOutputStream file;
            try {
                file = new FileOutputStream(path , true);

            bmp.compress(Bitmap.CompressFormat.JPEG,100,file);  
            file.close();
            }
            catch (Exception e) {
                // TODO Auto-generated catch block
                Log.e("",e.getMessage()+e.getCause());
                e.printStackTrace();
            }

      }


    public void load() {
        train();

    }

    public int getProb() {
        // TODO Auto-generated method stub
        return mProb;
    }


}
package org.opencv.javacv.facerecognition;
导入静态com.googlecode.javacv.cpp.opencv_highgui.*;
导入静态com.googlecode.javacv.cpp.opencv_core.*;
导入静态com.googlecode.javacv.cpp.opencv_imgproc.*;
导入静态com.googlecode.javacv.cpp.opencv_contrib.*;
导入java.io.File;
导入java.io.FileOutputStream;
导入java.io.FilenameFilter;
导入java.util.ArrayList;
导入org.opencv.android.Utils;
导入org.opencv.core.Mat;
导入com.googlecode.javacv.cpp.opencv_imgproc;
导入com.googlecode.javacv.cpp.opencv_contrib.FaceRecognizer;
导入com.googlecode.javacv.cpp.opencv_core.IplImage;
导入com.googlecode.javacv.cpp.opencv_core.MatVector;
导入android.graphics.Bitmap;
导入android.os.Environment;
导入android.util.Log;
导入android.widget.Toast;
公共类人员识别器{
公共最终静态整数最大值=100;
人脸识别器;
字符串mPath;
整数计数=0;
标签标签文件;
静态最终整数宽度=128;
静态最终整数高度=128;;
私有int mProb=999;
个人识别器(字符串路径)
{
faceRecognizer=com.googlecode.javacv.cpp.opencv_contrib.createLBPHFaceRecognizer(2,8,8,8200);
//path=Environment.getExternalStorageDirectory()+“/facerecog/faces/”;
mPath=路径;
labelsFile=新标签(mPath);
}
无效变更识别器(int nRec)
{
开关(nRec){
案例0:faceRecognizer=com.googlecode.javacv.cpp.opencv_contrib.createLBPHFaceRecognizer(1,8,8,8100);
打破
案例1:faceRecognizer=com.googlecode.javacv.cpp.opencv_contrib.createFisherFaceRecognizer();
打破
案例2:faceRecognizer=com.googlecode.javacv.cpp.opencv_contrib.createEigenFaceRecognizer();
打破
}
火车();
}
无效添加(材料m,字符串描述){
位图bmp=Bitmap.createBitmap(m.width(),m.height(),Bitmap.Config.ARGB_8888);
matToBitmap(m,bmp);
bmp=Bitmap.createScaledBitmap(bmp,宽度,高度,false);
文件输出流f;
试一试{
f=新的FileOutputStream(mPath+description+“-”+count+“.jpg”,true);
计数++;
bmp.compress(Bitmap.CompressFormat.JPEG,100,f);
f、 close();
}捕获(例外e){
Log.e(“错误”,e.getCause()+“”+e.getMessage());
e、 printStackTrace();
}
}
公共布尔序列(){
文件根=新文件(mPath);
对数i(“兆帕”,兆帕);
FilenameFilter pngFilter=新FilenameFilter(){
公共布尔接受(文件目录,字符串名称){
返回name.toLowerCase().endsWith(“.jpg”);
};
};
File[]imageFiles=root.listFiles(pngFilter);
MatVector images=新的MatVector(imageFiles.length);
int[]labels=新的int[imageFiles.length];
int计数器=0;
int标签;
IplImage img=null;
IplImage-grayImg;
int i1=mPath.length();
用于(文件图像:imageFiles){
字符串p=image.getAbsolutePath();
img=cvLoadImage(p);
如果(img==null)
Log.e(“错误”,“错误cVLoadImage”);
Log.i(“图像”,p);
int i2=p.lastIndexOf(“-”);
int i3=p.lastIndexOf(“.”);
int icount=Integer.parseInt(p.substring(i2+1,i3));
if(count1)
人脸识别器。序列(图像、标签);
labelfile.Save();
返回true;
}
公共布尔值canPredict()
{
如果(labelfile.max()>1)
返回true;
其他的
返回false;
}
公共字符串预测(Mat m){
如果(!canPredict())
返回“”;
int n[]=新int[1];
双p[]=新的双p[1];
IplImage ipl=MatToIplImage(米、宽、高);
//IplImage ipl=MatToIplImage(m,-1,-1);
人脸识别器预测(ipl,n,p);
如果(n[0]!=-1)
mProb=(int)p[0];
其他的
mProb=-1;

//如果((n[0]!=-1)和&(p[0]我认为您需要实现一些对照明变化更鲁棒的功能。请参阅:

然后,为了管理图像之间的相似性,您可以使用