opencv - 使用 OpenCV 进行在线人脸识别

Question

我正在尝试使用网络摄像头实现在线人脸识别。我正在使用这两个网站作为引用

shervinemami.co.cc
cognotics.com

我有几个问题:

人脸识别有6个步骤:

1. 从相机中抓取一帧
2. 检测图像中的人脸
3. 裁剪框架以仅显示脸部
4. 将框架转换为灰度
5. 预处理图像
6. 认出图片中的人物。

我可以完成前五个步骤。最后一步我做不到。我不确定如何将第 5 步链接到第 6 步。

我已经创建了包含训练和测试图像信息的 train.txt 文件和 test.txt 文件。我已经在代码中添加了learn()、doPCA()等函数...

但关键是如何在main中使用这些函数来识别已经预处理过的图像。

需要一些帮助...

附上代码如下:

// Real-time.cpp : Defines the entry point for the console application.

#include "stdafx.h"
#include <cv.h>
#include <cxcore.h>
#include <highgui.h>
#include <cvaux.h>

IplImage ** faceImgArr        = 0; // array of face images
CvMat    *  personNumTruthMat = 0; // array of person numbers
int nTrainFaces               = 0; // the number of training images
int nEigens                   = 0; // the number of eigenvalues
IplImage * pAvgTrainImg       = 0; // the average image
IplImage ** eigenVectArr      = 0; // eigenvectors
CvMat * eigenValMat           = 0; // eigenvalues
CvMat * projectedTrainFaceMat = 0; // projected training faces


IplImage* getCameraFrame(CvCapture* &camera);
IplImage* detectFaces( IplImage *img ,CvHaarClassifierCascade* facecascade,CvMemStorage* storage );
CvRect detectFaceInImage(IplImage *inputImg, CvHaarClassifierCascade* cascade);
IplImage* preprocess( IplImage* inputImg);
IplImage* resizeImage(const IplImage *origImg, int newWidth,
    int newHeight, bool keepAspectRatio);
void learn();
void recognize();
void doPCA();
void storeTrainingData();
int  loadTrainingData(CvMat ** pTrainPersonNumMat);
int  findNearestNeighbor(float * projectedTestFace);
int  loadFaceImgArray(char * filename);

int _tmain(int argc, _TCHAR* argv[])
{
    CvCapture* camera = 0;  // The camera device.
    CvMemStorage            *storage;
    cvNamedWindow( "Realtime:", CV_WINDOW_AUTOSIZE);
    char *faceCascadeFilename = "C:/OpenCV2.1/data/haarcascades/haarcascade_frontalface_alt.xml";
    CvHaarClassifierCascade* faceCascade;
    faceCascade = (CvHaarClassifierCascade*)cvLoad(faceCascadeFilename, 0, 0, 0);
    storage = cvCreateMemStorage( 0 );

    learn();

    while ( cvWaitKey(10) != 27 )   // Quit on "Escape" key
        {   
        IplImage *frame = getCameraFrame(camera);
        //IplImage* resized=cvCreateImage(cvSize(420,240),frame->depth,3);
        //cvResizeWindow( "Image:", 640, 480);
        //cvResize(frame,resized);
        //cvShowImage( "Realtime:", resized );
        IplImage *imgA = resizeImage(frame, 420,240, true);
        IplImage *frame1 = detectFaces(imgA,faceCascade,storage);
        frame1 = preprocess(frame1);
        }   
    // Free the camera.
    cvReleaseCapture( &camera );
    cvReleaseMemStorage( &storage );
    return 0;
}

IplImage* getCameraFrame(CvCapture* &camera)
{
    IplImage *frame;
    int w, h;

    // If the camera hasn't been initialized, then open it.
    if (!camera) {
        printf("Acessing the camera ...\n");
        camera = cvCreateCameraCapture( 0 );
        if (!camera) {
            printf("Couldn't access the camera.\n");
            exit(1);
        }
        // Try to set the camera resolution to 320 x 240.
        cvSetCaptureProperty(camera, CV_CAP_PROP_FRAME_WIDTH, 320);
        cvSetCaptureProperty(camera, CV_CAP_PROP_FRAME_HEIGHT, 240);
        // Get the first frame, to make sure the camera is initialized.
        frame = cvQueryFrame( camera );
        if (frame) {
            w = frame->width;
            h = frame->height;
            printf("Got the camera at %dx%d resolution.\n", w, h);
        }
        // Wait a little, so that the camera can auto-adjust its brightness.
        Sleep(1000);    // (in milliseconds)
    }

    // Wait until the next camera frame is ready, then grab it.
    frame = cvQueryFrame( camera );
    if (!frame) {
        printf("Couldn't grab a camera frame.\n");
        exit(1);
    }
    return frame;
}

CvRect detectFaceInImage(IplImage *inputImg, CvHaarClassifierCascade* cascade)
{
    // Smallest face size.
    CvSize minFeatureSize = cvSize(20, 20);
    // Only search for 1 face.
    int flags = CV_HAAR_FIND_BIGGEST_OBJECT | CV_HAAR_DO_ROUGH_SEARCH;
    // How detailed should the search be.
    float search_scale_factor = 1.1f;
    IplImage *detectImg;
    IplImage *greyImg = 0;
    CvMemStorage* storage;
    CvRect rc;
    double t;
    CvSeq* rects;
    CvSize size;
    int i, ms, nFaces;

    storage = cvCreateMemStorage(0);
    cvClearMemStorage( storage );


    // If the image is color, use a greyscale copy of the image.
    detectImg = (IplImage*)inputImg;
    if (inputImg->nChannels > 1) {
        size = cvSize(inputImg->width, inputImg->height);
        greyImg = cvCreateImage(size, IPL_DEPTH_8U, 1 );
        cvCvtColor( inputImg, greyImg, CV_BGR2GRAY );
        detectImg = greyImg;    // Use the greyscale image.
    }

    // Detect all the faces in the greyscale image.
    t = (double)cvGetTickCount();
    rects = cvHaarDetectObjects( detectImg, cascade, storage,
            search_scale_factor, 3, flags, minFeatureSize);
    t = (double)cvGetTickCount() - t;
    ms = cvRound( t / ((double)cvGetTickFrequency() * 1000.0) );
    nFaces = rects->total;
    printf("Face Detection took %d ms and found %d objects\n", ms, nFaces);

    // Get the first detected face (the biggest).
    if (nFaces > 0)
        rc = *(CvRect*)cvGetSeqElem( rects, 0 );
    else
        rc = cvRect(-1,-1,-1,-1);   // Couldn't find the face.

    if (greyImg)
        cvReleaseImage( &greyImg );
    cvReleaseMemStorage( &storage );
    //cvReleaseHaarClassifierCascade( &cascade );

    return rc;  // Return the biggest face found, or (-1,-1,-1,-1).
}

IplImage* detectFaces( IplImage *img ,CvHaarClassifierCascade* facecascade,CvMemStorage* storage )
{
    int i;
    CvRect *r;
    CvSeq *faces = cvHaarDetectObjects(
            img,
            facecascade,
            storage,
            1.1,
            3,
            0 /*CV_HAAR_DO_CANNY_PRUNNING*/,
            cvSize( 40, 40 ) );

    int padding_width = 30; // pixels
    int padding_height = 30; // pixels

    for( i = 0 ; i < ( faces ? faces->total : 0 ) ; i++ ) {
        r = ( CvRect* )cvGetSeqElem( faces, i );
        cvRectangle( img,
                     cvPoint( r->x, r->y ),
                     cvPoint( r->x + r->width, r->y + r->height ),
                     CV_RGB( 255, 0, 0 ), 1, 8, 0 );
    }

    cvShowImage( "Realtime:", img );

    //cropping the face
    cvSetImageROI(img, cvRect(r->x,r->y,r->width,r->height));
    IplImage *img2 = cvCreateImage(cvGetSize(img), 
                            img->depth, 
                              img->nChannels);
    cvCopy(img, img2, NULL);
    cvResetImageROI(img);

    return img;
}

IplImage* preprocess( IplImage* inputImg){
    IplImage *detectImg, *greyImg = 0;
    IplImage *imageProcessed;
    CvSize size;
    detectImg = (IplImage*)inputImg;
    if (inputImg->nChannels > 1) {
        size = cvSize(inputImg->width, inputImg->height);
        greyImg = cvCreateImage(size, IPL_DEPTH_8U, 1 );
        cvCvtColor( inputImg, greyImg, CV_BGR2GRAY );
        detectImg = greyImg;    // Use the greyscale image.
    }

    imageProcessed = cvCreateImage(cvSize(inputImg->width, inputImg->height), IPL_DEPTH_8U, 1);
    cvResize(detectImg, imageProcessed, CV_INTER_LINEAR);
    cvEqualizeHist(imageProcessed, imageProcessed);
    return imageProcessed;
}

IplImage* resizeImage(const IplImage *origImg, int newWidth,
    int newHeight, bool keepAspectRatio)
{
    IplImage *outImg = 0;
    int origWidth;
    int origHeight;
    if (origImg) {
        origWidth = origImg->width;
        origHeight = origImg->height;
    }
    if (newWidth <= 0 || newHeight <= 0 || origImg == 0
        || origWidth <= 0 || origHeight <= 0) {
        //cerr << "ERROR: Bad desired image size of " << newWidth
        //  << "x" << newHeight << " in resizeImage().\n";
        exit(1);
    }

    if (keepAspectRatio) {
        // Resize the image without changing its aspect ratio,
        // by cropping off the edges and enlarging the middle section.
        CvRect r;
        // input aspect ratio
        float origAspect = (origWidth / (float)origHeight);
        // output aspect ratio
        float newAspect = (newWidth / (float)newHeight);
        // crop width to be origHeight * newAspect
        if (origAspect > newAspect) {
            int tw = (origHeight * newWidth) / newHeight;
            r = cvRect((origWidth - tw)/2, 0, tw, origHeight);
        }
        else {  // crop height to be origWidth / newAspect
            int th = (origWidth * newHeight) / newWidth;
            r = cvRect(0, (origHeight - th)/2, origWidth, th);
        }
        IplImage *croppedImg = cropImage(origImg, r);

        // Call this function again, with the new aspect ratio image.
        // Will do a scaled image resize with the correct aspect ratio.
        outImg = resizeImage(croppedImg, newWidth, newHeight, false);
        cvReleaseImage( &croppedImg );

    }
    else {

        // Scale the image to the new dimensions,
        // even if the aspect ratio will be changed.
        outImg = cvCreateImage(cvSize(newWidth, newHeight),
            origImg->depth, origImg->nChannels);
        if (newWidth > origImg->width && newHeight > origImg->height) {
            // Make the image larger
            cvResetImageROI((IplImage*)origImg);
            // CV_INTER_LINEAR: good at enlarging.
            // CV_INTER_CUBIC: good at enlarging.           
            cvResize(origImg, outImg, CV_INTER_LINEAR);
        }
        else {
            // Make the image smaller
            cvResetImageROI((IplImage*)origImg);
            // CV_INTER_AREA: good at shrinking (decimation) only.
            cvResize(origImg, outImg, CV_INTER_AREA);
        }

    }
    return outImg;
}

void learn()
{
    int i, offset;

    // load training data
    nTrainFaces = loadFaceImgArray("C:/Users/HP/Desktop/OpenCV/50_images_of_15_people.txt");
    if( nTrainFaces < 2 )
    {
        fprintf(stderr,
                "Need 2 or more training faces\n"
                "Input file contains only %d\n", nTrainFaces);
        return;
    }

    // do PCA on the training faces
    doPCA();

    // project the training images onto the PCA subspace
    projectedTrainFaceMat = cvCreateMat( nTrainFaces, nEigens, CV_32FC1 );
    offset = projectedTrainFaceMat->step / sizeof(float);
    for(i=0; i<nTrainFaces; i++)
    {
        //int offset = i * nEigens;
        cvEigenDecomposite(
            faceImgArr[i],
            nEigens,
            eigenVectArr,
            0, 0,
            pAvgTrainImg,
            //projectedTrainFaceMat->data.fl + i*nEigens);
            projectedTrainFaceMat->data.fl + i*offset);
    }

    // store the recognition data as an xml file
    storeTrainingData();
}

void recognize()
{
    int i, nTestFaces  = 0;         // the number of test images
    CvMat * trainPersonNumMat = 0;  // the person numbers during training
    float * projectedTestFace = 0;

    // load test images and ground truth for person number
    nTestFaces = loadFaceImgArray("C:/Users/HP/Desktop/OpenCV/test.txt");
    printf("%d test faces loaded\n", nTestFaces);

    // load the saved training data
    if( !loadTrainingData( &trainPersonNumMat ) ) return;

    // project the test images onto the PCA subspace
    projectedTestFace = (float *)cvAlloc( nEigens*sizeof(float) );
    for(i=0; i<nTestFaces; i++)
    {
        int iNearest, nearest, truth;

        // project the test image onto the PCA subspace
        cvEigenDecomposite(
            faceImgArr[i],
            nEigens,
            eigenVectArr,
            0, 0,
            pAvgTrainImg,
            projectedTestFace);

        iNearest = findNearestNeighbor(projectedTestFace);
        truth    = personNumTruthMat->data.i[i];
        nearest  = trainPersonNumMat->data.i[iNearest];

        printf("nearest = %d, Truth = %d\n", nearest, truth);
    }
}

int loadTrainingData(CvMat ** pTrainPersonNumMat)
{
    CvFileStorage * fileStorage;
    int i;

    // create a file-storage interface
    fileStorage = cvOpenFileStorage( "facedata.xml", 0, CV_STORAGE_READ );
    if( !fileStorage )
    {
        fprintf(stderr, "Can't open facedata.xml\n");
        return 0;
    }

    nEigens = cvReadIntByName(fileStorage, 0, "nEigens", 0);
    nTrainFaces = cvReadIntByName(fileStorage, 0, "nTrainFaces", 0);
    *pTrainPersonNumMat = (CvMat *)cvReadByName(fileStorage, 0, "trainPersonNumMat", 0);
    eigenValMat  = (CvMat *)cvReadByName(fileStorage, 0, "eigenValMat", 0);
    projectedTrainFaceMat = (CvMat *)cvReadByName(fileStorage, 0, "projectedTrainFaceMat", 0);
    pAvgTrainImg = (IplImage *)cvReadByName(fileStorage, 0, "avgTrainImg", 0);
    eigenVectArr = (IplImage **)cvAlloc(nTrainFaces*sizeof(IplImage *));
    for(i=0; i<nEigens; i++)
    {
        char varname[200];
        sprintf( varname, "eigenVect_%d", i );
        eigenVectArr[i] = (IplImage *)cvReadByName(fileStorage, 0, varname, 0);
    }

    // release the file-storage interface
    cvReleaseFileStorage( &fileStorage );

    return 1;
}

void storeTrainingData()
{
    CvFileStorage * fileStorage;
    int i;

    // create a file-storage interface
    fileStorage = cvOpenFileStorage( "facedata.xml", 0, CV_STORAGE_WRITE );

    // store all the data
    cvWriteInt( fileStorage, "nEigens", nEigens );
    cvWriteInt( fileStorage, "nTrainFaces", nTrainFaces );
    cvWrite(fileStorage, "trainPersonNumMat", personNumTruthMat, cvAttrList(0,0));
    cvWrite(fileStorage, "eigenValMat", eigenValMat, cvAttrList(0,0));
    cvWrite(fileStorage, "projectedTrainFaceMat", projectedTrainFaceMat, cvAttrList(0,0));
    cvWrite(fileStorage, "avgTrainImg", pAvgTrainImg, cvAttrList(0,0));
    for(i=0; i<nEigens; i++)
    {
        char varname[200];
        sprintf( varname, "eigenVect_%d", i );
        cvWrite(fileStorage, varname, eigenVectArr[i], cvAttrList(0,0));
    }

    // release the file-storage interface
    cvReleaseFileStorage( &fileStorage );
}

int findNearestNeighbor(float * projectedTestFace)
{
    //double leastDistSq = 1e12;
    double leastDistSq = DBL_MAX;
    int i, iTrain, iNearest = 0;

    for(iTrain=0; iTrain<nTrainFaces; iTrain++)
    {
        double distSq=0;

        for(i=0; i<nEigens; i++)
        {
            float d_i =
                projectedTestFace[i] -
                projectedTrainFaceMat->data.fl[iTrain*nEigens + i];
            //distSq += d_i*d_i / eigenValMat->data.fl[i];  // Mahalanobis
            distSq += d_i*d_i; // Euclidean
        }

        if(distSq < leastDistSq)
        {
            leastDistSq = distSq;
            iNearest = iTrain;
        }
    }

    return iNearest;
}

void doPCA()
{
    int i;
    CvTermCriteria calcLimit;
    CvSize faceImgSize;

    // set the number of eigenvalues to use
    nEigens = nTrainFaces-1;

    // allocate the eigenvector images
    faceImgSize.width  = faceImgArr[0]->width;
    faceImgSize.height = faceImgArr[0]->height;
    eigenVectArr = (IplImage**)cvAlloc(sizeof(IplImage*) * nEigens);
    for(i=0; i<nEigens; i++)
        eigenVectArr[i] = cvCreateImage(faceImgSize, IPL_DEPTH_32F, 1);

    // allocate the eigenvalue array
    eigenValMat = cvCreateMat( 1, nEigens, CV_32FC1 );

    // allocate the averaged image
    pAvgTrainImg = cvCreateImage(faceImgSize, IPL_DEPTH_32F, 1);

    // set the PCA termination criterion
    calcLimit = cvTermCriteria( CV_TERMCRIT_ITER, nEigens, 1);

    // compute average image, eigenvalues, and eigenvectors
    cvCalcEigenObjects(
        nTrainFaces,
        (void*)faceImgArr,
        (void*)eigenVectArr,
        CV_EIGOBJ_NO_CALLBACK,
        0,
        0,
        &calcLimit,
        pAvgTrainImg,
        eigenValMat->data.fl);

    cvNormalize(eigenValMat, eigenValMat, 1, 0, CV_L1, 0);
}

int loadFaceImgArray(char * filename)
{
    FILE * imgListFile = 0;
    char imgFilename[512];
    int iFace, nFaces=0;


    // open the input file
    if( !(imgListFile = fopen(filename, "r")) )
    {
        fprintf(stderr, "Can\'t open file %s\n", filename);
        return 0;
    }

    // count the number of faces
    while( fgets(imgFilename, 512, imgListFile) ) ++nFaces;
    rewind(imgListFile);

    // allocate the face-image array and person number matrix
    faceImgArr        = (IplImage **)cvAlloc( nFaces*sizeof(IplImage *) );
    personNumTruthMat = cvCreateMat( 1, nFaces, CV_32SC1 );

    // store the face images in an array
    for(iFace=0; iFace<nFaces; iFace++)
    {
        // read person number and name of image file
        fscanf(imgListFile,
            "%d %s", personNumTruthMat->data.i+iFace, imgFilename);

        // load the face image
        faceImgArr[iFace] = cvLoadImage(imgFilename, CV_LOAD_IMAGE_GRAYSCALE);

        if( !faceImgArr[iFace] )
        {
            fprintf(stderr, "Can\'t load image from %s\n", imgFilename);
            return 0;
        }
    }

    fclose(imgListFile);

    return nFaces;
}

Answer 1

我的回答可能来晚了，但如果我回答它可能对 friend 有用。我正在做一个类似的项目，我遇到了同样的问题。我通过编写一个函数来解决它，保存或写入检测到的，裁剪的和预处理图像到我的电脑的硬盘上(使用CvWrite)。并将保存的图像的参数提供给代码的识别部分。它让我的生活更轻松。我更难传递感兴趣区域矩形的参数。如果您或其他人这样做，与我们分享代码可能会很棒。 在使用代码中的 resizeimage 函数将图像调整为常量值后，您可以使用以下代码保存图像。

    void saveCroppedFaces(CvSeq* tempon,IplImage* DetectedImage)
{

        char* name;
        int nFaces;
        CvRect rect;
        nFaces=tempon->total;
        name =new char[nFaces];
        IplImage* cropped = 0;
        IplImage* croppedResized=0;
        Mat croped;
        for(int k=0;k<nFaces;k++)
        {
            itoa(k,(name+k),10);
            rect = *(CvRect*)cvGetSeqElem( tempon, k );
            cropped= cropImage(DetectedImage,rect);
            //i can resize the cropped faces in to a fixed size here

            //i can write a function to save images and call it so
                  //that it will save it in to hard drive 
            //cvNamedWindow((name+k),CV_WINDOW_AUTOSIZE);

            //cvShowImage((name+k),cropped);
            croppedResized=resizeImage(cropped,60,60);
            croped=IplToMatConverter(croppedResized);
            saveROI(croped,itoa(k,(name+k),10));
            cvReleaseImage(&cropped);
        }
    name=NULL;
    delete[] name;

}

void saveROI(Mat mat,String outputFileName)
{
    string store_path("C://Users/sizusuzu/Desktop/Images/FaceDetection2
                                                    /"+outputFileName+".jpg");
    bool write_success = imwrite(store_path,mat);

}

在此之后，您可以使用

将 IplImage* 更改为 Mat

      Mat IplToMatConverter(IplImage* imageToMat)
     {
    Mat mat = cvarrToMat(imageToMat);
    return mat;
     }

并在 FaceRecognizer API 中使用 Mat。或者只使用其他/更难的方法。谢谢