快捷導(dǎo)航

Opencv EigenFace人臉識(shí)別算法詳解

更新時(shí)間：2019年05月21日 08:33:10 作者：東城青年

這篇文章主要為大家詳細(xì)介紹了Opencv EigenFace人臉識(shí)別算法的相關(guān)資料，具有一定的參考價(jià)值，感興趣的小伙伴們可以參考一下

簡要：

EigenFace是基于PCA降維的人臉識(shí)別算法，PCA是使整體數(shù)據(jù)降維后的方差最大，沒有考慮降維后類間的變化。它是將圖像每一個(gè)像素當(dāng)作一維特征，然后用SVM或其它機(jī)器學(xué)習(xí)算法進(jìn)行訓(xùn)練。但這樣維數(shù)太多，根本無法計(jì)算。我這里用的是ORL人臉數(shù)據(jù)庫，英國劍橋?qū)嶒?yàn)室拍攝的，有40位志愿者的人臉，在不同表情不同光照下每位志愿者拍攝10張，共有400張圖片，大小為112*92，所以如果把每個(gè)像素當(dāng)做特征拿來訓(xùn)練的話，一張人臉就有10304維特征，這么高維的數(shù)據(jù)根本無法處理。所以需要先對數(shù)據(jù)進(jìn)行降維，去掉一些冗余的特征。

第一步：將ORL人臉圖片的地址統(tǒng)一放在一個(gè)文件里，等會(huì)通過對該文件操作，將圖片全部加載進(jìn)來。

//ofstream一般對文件進(jìn)行讀寫操作，ifstream一般對文件進(jìn)行讀操作
ofstream file;
 file.open("path.txt");//新建并打開文件
 char str[50] = {};
 for (int i = 1; i <= 40; i++) {
 for (int j = 1; j <= 10; j++) { 
  sprintf_s(str, "orl_faces/s%d/%d.pgm;%d", i, j, i);//將數(shù)字轉(zhuǎn)換成字符
  file << str << endl;//寫入
 } 
 }

得到路勁文件如下圖所示：

第二步：讀入模型需要輸入的數(shù)據(jù)，即用來訓(xùn)練的圖像vector<Mat>images和標(biāo)簽vector<int>labels

string filename = string("path.txt");
 ifstream file(filename);
 if (!file) { 
    printf("could not load file"); 
  }
 vector<Mat>images;
 vector<int>labels;
 char separator = ';';
 string line,path, classlabel;
 while (getline(file,line)) {
 stringstream lines(line);
 getline(lines, path, separator);
 getline(lines, classlabel);
 images.push_back(imread(path, 0));
 labels.push_back(atoi(classlabel.c_str()));//atoi(ASCLL to int)將字符串轉(zhuǎn)換為整數(shù)型
 }

第三步：加載、訓(xùn)練、預(yù)測模型

Ptr<BasicFaceRecognizer> model = EigenFaceRecognizer::create();
 model->train(images, labels);
 int predictedLabel = model->predict(testSample);
 printf("actual label:%d,predict label :%d\n", testLabel, predictedLabel);

補(bǔ)充：

1、顯示平均臉

//計(jì)算特征值特征向量及平均值
 Mat vals = model->getEigenValues();//89*1
 printf("%d,%d\n", vals.rows, vals.cols);
 Mat vecs = model->getEigenVectors();//10324*89
 printf("%d,%d\n", vecs.rows, vecs.cols);
 Mat mean = model->getMean();//1*10304
 printf("%d,%d\n", mean.rows, mean.cols);
 
 //顯示平均臉
 Mat meanFace = mean.reshape(1, height);//第一個(gè)參數(shù)為通道數(shù)，第二個(gè)參數(shù)為多少行
 normalize(meanFace, meanFace, 0, 255, NORM_MINMAX, CV_8UC1);
 imshow("Mean Face", meanFace);

2、顯示前部分特征臉

//顯示特征臉
 for (int i = 0; i<min(10, vals.rows); i++) {
 Mat feature_vec = vecs.col(i).clone();
 Mat feature_face= feature_vec.reshape(1, height); 
 normalize(feature_face, feature_face, 0, 255, NORM_MINMAX, CV_8UC1); 
 Mat colorface;
 applyColorMap(feature_face, colorface, COLORMAP_BONE);
 
 sprintf_s(win_title, "eigenface%d", i);
 imshow(win_title, colorface);
 }

3、對第一張人臉在特征向量空間進(jìn)行人臉重建（分別基于前10,20,30,40,50,60個(gè)特征向量進(jìn)行人臉重建）

//重建人臉
 for (int i = min(10, vals.rows); i <min(61, vals.rows); i+=10) {
 Mat vecs_space = Mat(vecs, Range::all(), Range(0, i));
 Mat projection = LDA::subspaceProject(vecs_space, mean, images[0].reshape(1, 1));//投影到子空間
 Mat reconstruction = LDA::subspaceReconstruct(vecs_space, mean, projection);//重建
 Mat result = reconstruction.reshape(1, height);
 normalize(result, result, 0, 255, NORM_MINMAX, CV_8UC1);
 //char wintitle[40] = {};
 sprintf_s(win_title, "recon face %d", i);
 imshow(win_title, result);
 }

完整代碼如下：

#include<opencv2\opencv.hpp>
#include<opencv2\face.hpp>
using namespace cv;
using namespace face;
using namespace std;
char win_title[40] = {};
 
int main(int arc, char** argv) { 
 namedWindow("input",CV_WINDOW_AUTOSIZE);
 
 //讀入模型需要輸入的數(shù)據(jù)，用來訓(xùn)練的圖像vector<Mat>images和標(biāo)簽vector<int>labels
 string filename = string("path.txt");
 ifstream file(filename);
 if (!file) { printf("could not load file"); }
 vector<Mat>images;
 vector<int>labels;
 char separator = ';';
 string line,path, classlabel;
 while (getline(file,line)) {
 stringstream lines(line);
 getline(lines, path, separator);
 getline(lines, classlabel);
 //printf("%d\n", atoi(classlabel.c_str()));
 images.push_back(imread(path, 0));
 labels.push_back(atoi(classlabel.c_str()));//atoi(ASCLL to int)將字符串轉(zhuǎn)換為整數(shù)型
 }
 int height = images[0].rows;
 int width = images[0].cols;
 printf("height:%d,width:%d\n", height, width);
 //將最后一個(gè)樣本作為測試樣本
 Mat testSample = images[images.size() - 1];
 int testLabel = labels[labels.size() - 1];
 //刪除列表末尾的元素
 images.pop_back();
 labels.pop_back();
 
 //加載，訓(xùn)練，預(yù)測
 Ptr<BasicFaceRecognizer> model = EigenFaceRecognizer::create();
 model->train(images, labels);
 int predictedLabel = model->predict(testSample);
 printf("actual label:%d,predict label :%d\n", testLabel, predictedLabel);
 
 //計(jì)算特征值特征向量及平均值
 Mat vals = model->getEigenValues();//89*1
 printf("%d,%d\n", vals.rows, vals.cols);
 Mat vecs = model->getEigenVectors();//10324*89
 printf("%d,%d\n", vecs.rows, vecs.cols);
 Mat mean = model->getMean();//1*10304
 printf("%d,%d\n", mean.rows, mean.cols);
 
 //顯示平均臉
 Mat meanFace = mean.reshape(1, height);//第一個(gè)參數(shù)為通道數(shù)，第二個(gè)參數(shù)為多少行
 normalize(meanFace, meanFace, 0, 255, NORM_MINMAX, CV_8UC1);
 imshow("Mean Face", meanFace);
 
 //顯示特征臉
 for (int i = 0; i<min(10, vals.rows); i++) {
 Mat feature_vec = vecs.col(i).clone();
 Mat feature_face= feature_vec.reshape(1, height); 
 normalize(feature_face, feature_face, 0, 255, NORM_MINMAX, CV_8UC1); 
 Mat colorface;
 applyColorMap(feature_face, colorface, COLORMAP_BONE);
 
 sprintf_s(win_title, "eigenface%d", i);
 imshow(win_title, colorface);
 }
 
 //重建人臉
 for (int i = min(10, vals.rows); i <min(61, vals.rows); i+=10) {
 Mat vecs_space = Mat(vecs, Range::all(), Range(0, i));
 Mat projection = LDA::subspaceProject(vecs_space, mean, images[0].reshape(1, 1));
 Mat reconstruction = LDA::subspaceReconstruct(vecs_space, mean, projection);
 Mat result = reconstruction.reshape(1, height);
 normalize(result, result, 0, 255, NORM_MINMAX, CV_8UC1);
 //char wintitle[40] = {};
 sprintf_s(win_title, "recon face %d", i);
 imshow(win_title, result);
 }
 
 waitKey(0);
 return 0;
}

以上就是本文的全部內(nèi)容，希望對大家的學(xué)習(xí)有所幫助，也希望大家多多支持腳本之家。

您可能感興趣的文章: