我想使用 LBP 和 SVM 创建一个实时情绪识别程序。经过面部检测过程后，我将捕获的图像转换为 32x32 像素的灰度图像。 我很难为我的 LBP 创建和显示直方图(我使用简单的、未插值的 LBP)。到目前为止，我得到的是实时显示生成的 LBP 图像。

Ahonen 等。 al 的论文指出

divide the LBP image into m local regions and extract a histogram from each (region)

我们如何确定 m 个局部区域的数量？

我一直在努力寻找答案 here , 和 here但我无法理解它。我在这里看到了 berak 关于空间直方图的工作，但我仍然感到困惑。有人可以逐步教我吗(是的，我是新手 :/)。我真的需要计算并显示直方图，如第 14 页所示 here .

也许我应该在这里展示我凌乱的代码。

// Libraries included
#include "opencv2/core/core.hpp"
#include "opencv2/objdetect/objdetect.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include <iostream>
#include <stdio.h>

// Namespace declaration
using namespace std;
using namespace cv;

// Function Headers
void detectAndDisplay(Mat frame);
Mat LBP(Mat img);

// Global variables
String face_cascade_name = "haarcascade_frontalface_alt.xml";
String eyes_cascade_name = "haarcascade_eye_tree_eyeglasses.xml";
CascadeClassifier face_cascade;
CascadeClassifier eyes_cascade;


// Function main
int main(){
    // Start cvStartWindowThread to create a thread process. VERY IMPORTANT
    cvStartWindowThread();

    // Initializing local variables
    int k=1;
    CvCapture* capture;
    Mat frame;

    // Load the cascade, use ifs (if more than one xml files are used) to prevent segmentation fault
    if (!face_cascade.load(face_cascade_name)){
        printf("--(!)Error loading\n");
        return (-1);
    }
    if( !eyes_cascade.load( eyes_cascade_name ) ){
        printf("--(!)Error loading\n");
        return -1;
    };

    // Start the program, capture from CAM with CAMID =0    
    capture = cvCaptureFromCAM(0 );
    if( capture !=0){   
        while(k==1){
            frame = cvQueryFrame( capture );
            cv::flip(frame,frame,1);
            //-- 3. Apply the classifier to the frame
            if( !frame.empty() ){
                detectAndDisplay( frame );
            }
            else{
                printf(" --(!) No captured frame -- Break!");
                break;
            }
            int c = waitKey(1);
            if( (char)c == 'c' ) {
                k=0;
                destroyWindow("FYP Live Camera");
                break;
            }
        }
    }
    else{
        printf("CvCaptureFromCAM ERROR\n");
    }
    cvReleaseCapture(&capture);
    return 0;
}

// Function detectAndDisplay
void detectAndDisplay(Mat frame){
    std::vector<Rect> faces;
    std::vector<Rect> eyes;
    Mat frame_gray;
    Mat crop;
    Mat crop2;
    Mat res;
    Mat gray;
    Mat dst;
    string text;
    stringstream sstm;


    cvtColor(frame, frame_gray, COLOR_BGR2GRAY);
    equalizeHist(frame_gray, frame_gray);

    // Detect faces
    face_cascade.detectMultiScale(frame_gray, faces, 1.1, 4, 0 | CV_HAAR_FIND_BIGGEST_OBJECT, Size(60, 60));

    // Set Region of Interest
    cv::Rect roi_b;
    cv::Rect roi_c;

    size_t ic = 0; // ic is index of current element


    if (faces.size() !=0){
        for (ic = 0; ic < faces.size(); ic++) // Iterate through all current elements (detected faces)
        {
            roi_b.x = faces[ic].x;
            roi_b.y = faces[ic].y;
            roi_b.width = faces[ic].width;
            roi_b.height = faces[ic].height;

            crop = frame(roi_b);
            resize(crop, res, Size(256, 256), 0, 0, INTER_LINEAR); // This will be needed later while saving images

            cvtColor(res, gray, CV_BGR2GRAY); // Convert cropped image to Grayscale

            eyes_cascade.detectMultiScale(gray, eyes, 1.1, 4, 0 |CV_HAAR_SCALE_IMAGE, Size(15, 15) );
            if (eyes.size() == 2){
                if ( eyes[0].x <= eyes[1].x ){
                    roi_c.x = eyes[0].x*0.75;
                    roi_c.y = eyes[0].y*0.7;
                    roi_c.width = (eyes[1].x+65)-roi_c.x;
                    roi_c.height = 190;
                }
                else if ( eyes[0].x >= eyes[1].x ) {
                    roi_c.x = eyes[1].x*0.75;
                    roi_c.y = eyes[1].y*0.7;
                    roi_c.width = (eyes[0].x+65)-roi_c.x;
                    roi_c.height = 190;
                }
                crop2 = gray(roi_c);
                resize(crop2, crop2, Size(128, 128), 0, 0, INTER_LINEAR); // This will be needed later while saving images

                dst= LBP(crop2);

                Point centerEye1( eyes[0].x + eyes[0].width*0.5, eyes[0].y + eyes[0].height*0.5 );
                int radiusEye1 = cvRound( (eyes[0].width + eyes[0].height)*0.25 );
                circle( gray, centerEye1, radiusEye1, Scalar( 0, 0, 255 ), 1, 8, 0 );

                Point centerEye2( eyes[1].x + eyes[1].width*0.5, eyes[1].y + eyes[1].height*0.5 );
                int radiusEye2 = cvRound( (eyes[1].width + eyes[1].height)*0.25 );
                circle( gray, centerEye2, radiusEye2, Scalar( 0, 0, 255 ), 1, 8, 0 );

            }

            Point pt1(faces[ic].x, faces[ic].y); // Display detected faces on main window - live stream from camera
            Point pt2((faces[ic].x + faces[ic].height), (faces[ic].y + faces[ic].width));
            rectangle(frame, pt1, pt2, Scalar(0, 255, 0), 1, 8, 0);
            putText(frame, "Auto-focused", cvPoint((faces[ic].x+faces[ic].width/4), faces[ic].y-10), FONT_HERSHEY_COMPLEX_SMALL, 0.8, cvScalar(0, 0, 255), 1, CV_AA);
        }

    }


    imshow("Live Camera", frame);
    if (!crop2.empty())
    {
        imshow("Gray2", dst);
        imshow("Gray3", crop2);
    }
    else{
        destroyWindow("Gray2");
        destroyWindow("Gray3");
    }   
}
Mat LBP(Mat img){
    Mat dst = Mat::zeros(img.rows-2, img.cols-2, CV_8UC1);
    for(int i=1;i<img.rows-1;i++) {
        for(int j=1;j<img.cols-1;j++) {
            uchar center = img.at<uchar>(i,j);
            unsigned char code = 0;
            code |= ((img.at<uchar>(i-1,j-1)) > center) << 7;
                code |= ((img.at<uchar>(i-1,j)) > center) << 6;
            code |= ((img.at<uchar>(i-1,j+1)) > center) << 5;
            code |= ((img.at<uchar>(i,j+1)) > center) << 4;
            code |= ((img.at<uchar>(i+1,j+1)) > center) << 3;
            code |= ((img.at<uchar>(i+1,j)) > center) << 2;
            code |= ((img.at<uchar>(i+1,j-1)) > center) << 1;
            code |= ((img.at<uchar>(i,j-1)) > center) << 0;
            dst.at<uchar>(i-1,j-1) = code;
        }
    }
    return dst;
}

显然我无法发布我的屏幕截图，因为我没有足够的信誉点:(

最佳答案

嗯，首先，您要计算的只是 LBP 模式，而不是直方图 - 您需要为此创建一个 bin 数组并生成 LBP 特征的直方图。 在 bytefish 的代码中，如果您查看 github，您还会找到用于生成具有 59 个 bin 的直方图的代码。

关于c++ - 在 openCV 中计算并显示 LBP 直方图，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/23752507/