叙述性说明
所谓的性别识别推断检测到的面部是男性还是女性。它是一个二值分类问题。
识别算法可以用于SVM，BP神经网络。LDA，PCA，PCA+LDA等等。OpenCV官网给出的文档是基于Fisherfaces检測器（LDA）方法实现的。链接：http://docs.opencv.org/modules/contrib/doc/facerec/tutorial/facerec_gender_classification.html#id5 。这篇博文（http://www.bytefish.de/blog/gender_classification/）中也是採用OpenCV官网的方法。据称有98%的正确率，我在百度图片找了一些数据測试了下，仅仅有大概50%多的识别率。原因是他的数据集是经过严格标定的。好像是眼睛的是对齐的。
实际应用中不太可能会遇到这样的情况吧。CSDN还有两篇博客也介绍到这个性格识别（http://blog.csdn.net/kklots/article/details/8247738 http://blog.csdn.net/kklots/article/details/9285505）文章写得非常好，一看就是大牛。博文中也是測试了LDA的方法，正确率也是出奇的低。採用的是PCA+LDA的方法。通过改进能达到接近90%的正确率。
博文指出PCA+LDA比单纯的LDA和PCA识别率都高，但我对博文中的PCA+LDA程序和官网的PCA程序測试了下，发现PCA的正确率会高那么一两个点。难道又是数据的问题？
数据
採集数据一方面能够採用开源的人脸库。还有一方面能够自己去百度图片下载图片。去百度或谷歌图片分别搜索“男明星头像”“女明星头像”的关键字批量下载。这里当然须要批量下载利器。
然后利用人脸检測器过滤检測出头像，然后归一化检測出来的图像，保存在本地。这样主要的数据集就有了。
当然我也会附上我採集的数据和工程文件（特此声明，全部图片均来自网络）
測试程序
创建CSV文件的python代码:
import sys
import os.path
if __name__ == "__main__":
if len(sys.argv) != 3:
print "usage: create_csv <base_path> <SAVE_FILE_NAME>"
sys.exit(1)
BASE_PATH=sys.argv[1]
FILE_NAME = sys.argv[2]
SEPARATOR=";"
fh = open(FILE_NAME,'w')
label = 0
for dirname, dirnames, filenames in os.walk(BASE_PATH):
for subdirname in dirnames:
subject_path = os.path.join(dirname, subdirname)
for filename in os.listdir(subject_path):
abs_path = "%s/%s" % (subject_path, filename)
##print "%s%s%d" % (abs_path, SEPARATOR, label)
##print "%s %s" % (dirname, subject_path)
fh.write(abs_path)
fh.write(SEPARATOR)
if dirname.find("female") > 0 :
label = 1
else:
label = 0
fh.write(str(label))
fh.write("\n")
fh.close()測试性别识别的程序
// gender.cpp : 定义控制台应用程序的入口点。
//
#include "stdafx.h"
#include <opencv2/opencv.hpp>
#include <iostream>
#include <fstream>
#include <sstream>
#include <math.h>
int g_howManyPhotoForTraining = 260;
//每一个人取出8张作为训练
int g_photoNumberOfOnePerson = 279;
//ORL数据库每一个人10张图像
using namespace cv;
using namespace std;
static Mat norm_0_255(InputArray _src) {
Mat src = _src.getMat();
// 创建和返回一个归一化后的图像矩阵:
Mat dst;
switch(src.channels()) {
case1:
cv::normalize(_src, dst, 0,255, NORM_MINMAX, CV_8UC1);
break;
case3:
cv::normalize(_src, dst, 0,255, NORM_MINMAX, CV_8UC3);
break;
default:
src.copyTo(dst);
break;
}
return dst;
}
//使用CSV文件去读图像和标签，主要使用stringstream和getline方法
static void read_csv(const string& filename, vector<Mat>& images, vector<int>& labels, char separator =';') {
std::ifstream file(filename.c_str(), ifstream::in);
if (!file) {
string error_message ="No valid input file was given, please check the given filename.";
CV_Error(CV_StsBadArg, error_message);
}
string line, path, classlabel;
while (getline(file, line)) {
stringstream liness(line);
getline(liness, path, separator);
getline(liness, classlabel);
if(!path.empty()&&!classlabel.empty()) {
images.push_back(imread(path, 0));
labels.push_back(atoi(classlabel.c_str()));
}
}
}
void train_and_test_lda()
{
string fn_csv = string("at.txt");
//string fn_csv = string("feret.txt");
vector<Mat> allImages,train_images,test_images;
vector<int> allLabels,train_labels,test_labels;
try {
read_csv(fn_csv, allImages, allLabels);
} catch (cv::Exception& e) {
cerr <<"Error opening file "<< fn_csv <<". Reason: "<< e.msg << endl;
// 文件有问题，我们啥也做不了了。退出了
exit(1);
}
if(allImages.size()<=1) {
string error_message ="This demo needs at least 2 images to work. Please add more images to your data set!";
CV_Error(CV_StsError, error_message);
}
for(int i=0 ; i<allImages.size() ; i++)
equalizeHist(allImages[i],allImages[i]);
int photoNumber = allImages.size();
for(int i=0 ; i<photoNumber ; i++)
{
if((i%g_photoNumberOfOnePerson)<g_howManyPhotoForTraining)
{
train_images.push_back(allImages[i]);
train_labels.push_back(allLabels[i]);
}
else
{
test_images.push_back(allImages[i]);
test_labels.push_back(allLabels[i]);
}
}
/*Ptr<FaceRecognizer> model = createEigenFaceRecognizer();//定义pca模型 model->train(train_images, train_labels);//训练pca模型。这里的model包括了全部特征值和特征向量。没有损失 model->save("eigenface.yml");//保存训练结果。供检測时使用 */
Ptr<FaceRecognizer> fishermodel = createFisherFaceRecognizer();
fishermodel->train(train_images,train_labels);//用保存的降维后的图片来训练fishermodel，后面的内容与原始代码就没什么变化了
fishermodel->save("fisherlda.yml");
int iCorrectPrediction = 0;
int predictedLabel;
int testPhotoNumber = test_images.size();
for(int i=0;i<testPhotoNumber;i++)
{
predictedLabel = fishermodel->predict(test_images[i]);
if(predictedLabel == test_labels[i])
iCorrectPrediction++;
}
string result_message = format("Test Number = %d / Actual Number = %d.", testPhotoNumber, iCorrectPrediction);
cout << result_message << endl;
cout<<"accuracy = "<<float(iCorrectPrediction)/testPhotoNumber<<endl;
}
void train_and_test_pca()
{
string fn_csv = string("at.txt");
//string fn_csv = string("feret.txt");
vector<Mat> allImages,train_images,test_images;
vector<int> allLabels,train_labels,test_labels;
try {
read_csv(fn_csv, allImages, allLabels);
} catch (cv::Exception& e) {
cerr <<"Error opening file "<< fn_csv <<". Reason: "<< e.msg << endl;
// 文件有问题。我们啥也做不了了，退出了
exit(1);
}
if(allImages.size()<=1) {
string error_message ="This demo needs at least 2 images to work. Please add more images to your data set!";
CV_Error(CV_StsError, error_message);
}
for(int i=0 ; i<allImages.size() ; i++)
equalizeHist(allImages[i],allImages[i]);
int photoNumber = allImages.size();
for(int i=0 ; i<photoNumber ; i++)
{
if((i%g_photoNumberOfOnePerson)<g_howManyPhotoForTraining)
{
train_images.push_back(allImages[i]);
train_labels.push_back(allLabels[i]);
}
else
{
test_images.push_back(allImages[i]);
test_labels.push_back(allLabels[i]);
}
}
Ptr<FaceRecognizer> model = createEigenFaceRecognizer();//定义pca模型
model->train(train_images, train_labels);//训练pca模型，这里的model包括了全部特征值和特征向量。没有损失
model->save("eigenfacepca.yml");//保存训练结果，供检測时使用
int iCorrectPrediction = 0;
int predictedLabel;
int testPhotoNumber = test_images.size();
for(int i=0;i<testPhotoNumber;i++)
{
predictedLabel = model->predict(test_images[i]);
if(predictedLabel == test_labels[i])
iCorrectPrediction++;
}
string result_message = format("Test Number = %d / Actual Number = %d.", testPhotoNumber, iCorrectPrediction);
cout << result_message << endl;
cout<<"accuracy = "<<float(iCorrectPrediction)/testPhotoNumber<<endl;
}
void train_and_test()
{
string fn_csv = string("at.txt");
//string fn_csv = string("feret.txt");
vector<Mat> allImages,train_images,test_images;
vector<int> allLabels,train_labels,test_labels;
try {
read_csv(fn_csv, allImages, allLabels);
} catch (cv::Exception& e) {
cerr <<"Error opening file "<< fn_csv <<". Reason: "<< e.msg << endl;
// 文件有问题，我们啥也做不了了。退出了
exit(1);
}
if(allImages.size()<=1) {
string error_message ="This demo needs at least 2 images to work. Please add more images to your data set!";
CV_Error(CV_StsError, error_message);
}
for(int i=0 ; i<allImages.size() ; i++)
equalizeHist(allImages[i],allImages[i]);
int photoNumber = allImages.size();
for(int i=0 ; i<photoNumber ; i++)
{
if((i%g_photoNumberOfOnePerson)<g_howManyPhotoForTraining)
{
train_images.push_back(allImages[i]);
train_labels.push_back(allLabels[i]);
}
else
{
test_images.push_back(allImages[i]);
test_labels.push_back(allLabels[i]);
}
}
Ptr<FaceRecognizer> model = createEigenFaceRecognizer();//定义pca模型
model->train(train_images, train_labels);//训练pca模型。这里的model包括了全部特征值和特征向量，没有损失
model->save("eigenface.yml");//保存训练结果。供检測时使用
Mat eigenvalues = model->getMat("eigenvalues");//提取model中的特征值。该特征值默认由大到小排列
Mat W = model->getMat("eigenvectors");//提取model中的特征向量，特征向量的排列方式与特征值排列顺序一一相应
int xth = 121;//打算保留前121个特征向量，代码中没有体现原因。但选择121是经过斟酌的，首先，在我的实验中。"前121个特征值之和/全部特征值总和>0.97"。其次，121=11^2，能够将结果表示成一个11*11的2维图像方阵，交给fisherface去计算。 vector<Mat> reduceDemensionimages;//降维后的图像矩阵 vector<Mat> testreduceDemensionimages; Mat evs = Mat(W, Range::all(), Range(0, xth));//选择前xth个特征向量，其余舍弃 Mat mean = model->getMat("mean"); for(int i=0;i<train_images.size();i++) { Mat projection = subspaceProject(evs, mean, train_images[i].reshape(1,1));//做子空间投影 reduceDemensionimages.push_back(projection.reshape(1,sqrt(xth*1.0)));//将获得的子空间系数表示映射成2维图像，并保存起来 } for(int i=0;i<test_images.size();i++) { Mat projection = subspaceProject(evs, mean, test_images[i].reshape(1,1));//做子空间投影 testreduceDemensionimages.push_back(projection.reshape(1,sqrt(xth*1.0)));//将获得的子空间系数表示映射成2维图像。并保存起来 } Ptr<FaceRecognizer> fishermodel = createFisherFaceRecognizer(); fishermodel->train(reduceDemensionimages,train_labels);//用保存的降维后的图片来训练fishermodel。后面的内容与原始代码就没什么变化了 fishermodel->save("fisher.yml"); int iCorrectPrediction = 0; int predictedLabel; int testPhotoNumber = test_images.size(); for(int i=0;i<testPhotoNumber;i++) { predictedLabel = fishermodel->predict(testreduceDemensionimages[i]); if(predictedLabel == test_labels[i]) iCorrectPrediction++; } string result_message = format("Test Number = %d / Actual Number = %d.", testPhotoNumber, iCorrectPrediction); cout << result_message << endl; cout<<"accuracy = "<<float(iCorrectPrediction)/testPhotoNumber<<endl; } void test_pca() { string fn_csv = string("test.txt"); vector<Mat> allImages; vector<int> allLabels; try { read_csv(fn_csv, allImages, allLabels); } catch (cv::Exception& e) { cerr <<"Error opening file "<< fn_csv <<". Reason: "<< e.msg << endl; // 文件有问题，我们啥也做不了了，退出了 exit(1); } if(allImages.size()<=1) { string error_message ="This demo needs at least 2 images to work. Please add more images to your data set!"; CV_Error(CV_StsError, error_message); } Ptr<FaceRecognizer> model = createEigenFaceRecognizer();//定义pca模型 model->load("eigenfacepca.yml");//保存训练结果。供检測时使用 int iCorrectPrediction = 0; int predictedLabel; int testPhotoNumber = allImages.size(); for(int i=0;i<testPhotoNumber;i++) { predictedLabel = model->predict(allImages[i]); if(predictedLabel == allLabels[i]) iCorrectPrediction++; } string result_message = format("Test Number = %d / Actual Number = %d.", testPhotoNumber, iCorrectPrediction); cout << result_message << endl; cout<<"accuracy = "<<float(iCorrectPrediction)/testPhotoNumber<<endl; } void test() { string fn_csv = string("test.txt"); vector<Mat> allImages; vector<int> allLabels; try { read_csv(fn_csv, allImages, allLabels); } catch (cv::Exception& e) { cerr <<"Error opening file "<< fn_csv <<". Reason: "<< e.msg << endl; // 文件有问题。我们啥也做不了了，退出了 exit(1); } if(allImages.size()<=1) { string error_message ="This demo needs at least 2 images to work. Please add more images to your data set!"; CV_Error(CV_StsError, error_message); } Ptr<FaceRecognizer> model = createEigenFaceRecognizer();//定义pca模型 model->load("eigenface.yml");//保存训练结果。供检測时使用 Mat eigenvalues = model->getMat("eigenvalues");//提取model中的特征值，该特征值默认由大到小排列 Mat W = model->getMat("eigenvectors");//提取model中的特征向量，特征向量的排列方式与特征值排列顺序一一相应 int xth = 121;//打算保留前121个特征向量，代码中没有体现原因，但选择121是经过斟酌的，首先，在我的实验中。"前121个特征值之和/全部特征值总和>0.97"；其次，121=11^2，能够将结果表示成一个11*11的2维图像方阵，交给fisherface去计算。 vector<Mat> reduceDemensionimages;//降维后的图像矩阵 Mat evs = Mat(W, Range::all(), Range(0, xth));//选择前xth个特征向量。其余舍弃 Mat mean = model->getMat("mean"); for(int i=0;i<allImages.size();i++) { Mat projection = subspaceProject(evs, mean, allImages[i].reshape(1,1));//做子空间投影 reduceDemensionimages.push_back(projection.reshape(1,sqrt(xth*1.0)));//将获得的子空间系数表示映射成2维图像，并保存起来 } Ptr<FaceRecognizer> fishermodel = createFisherFaceRecognizer(); fishermodel->load("fisher.yml"); int iCorrectPrediction = 0; int predictedLabel; int testPhotoNumber = allImages.size(); for(int i=0;i<testPhotoNumber;i++) { predictedLabel = fishermodel->predict(reduceDemensionimages[i]); if(predictedLabel == allLabels[i]) iCorrectPrediction++; } string result_message = format("Test Number = %d / Actual Number = %d.", testPhotoNumber, iCorrectPrediction); cout << result_message << endl; cout<<"accuracy = "<<float(iCorrectPrediction)/testPhotoNumber<<endl; } int main() { cout<<"lda = "<<endl; train_and_test_lda(); cout<<"pca = "<<endl; train_and_test_pca(); cout<<"pca+lda = "<<endl; train_and_test(); /*test(); test_pca();*/ return 0 ; }
整个工程文件和数据下载链接 http://download.csdn.net/detail/zwhlxl/8510649
版权声明：本文博主原创文章，博客，未经同意不得转载。