目录
1基于CNN的性别分类建模原理
1.1 人脸识别
1.2 性别预测
1.3 年龄预测
1.4 结果
2 代码
参考
本教程中,我们将讨论应用于面部的深层学习的有趣应用。我们将估计年龄,并从单个图像中找出该人的性别。模型由GilLevi和TalHassner训练(https://talhassner.github.io/home/publication/2015_CVPR)。本文介绍了如何在OpenCV中使用该模型的步骤说明。Opencv版本3.4.3以上。代码教程代码可以分为四个部分:
作者使用非常简单的卷积神经网络结构,类似于Caffenet和Alexnet。网络使用3个卷积层、2个全连接层和一个最终的输出层。下面给出了这些层的细节。COV1:第一卷积层具有96个内核大小7的节点。COV2:第二个卷积层Conv层具有256个具有内核大小5的节点。CONV3:第三个CONV层具有384个内核大小为3的节点。两个完全连接的层各自具有512个节点。
训练数据来源:https://talhassner.github.io/home/projects/Adience/Adience-data.html
检测程序主要有四块:检测人脸检测、性别检测、年龄显示和输出。
我们将使用人脸检测器(tensorflow模型)进行人脸检测。该模型很简单,即使在CPU上也是相当快的。详细见论文:
https://arxiv.org/pdf/1502.00046.pdf
将性别预测设定为一个分类问题。性别预测网络(caffe模型)中的输出层类型为两类,2个节点表示“男性”和“女性”两类。以这两个输出的最大值作为最终的性别。
理想情况下,年龄预测应该作为一个回归问题来处理。然而通过回归准确估计年龄是很有挑战性的。即使是人类也无法通过观察一个人来准确预测年龄。但是我们能够知道他们是20多岁还是30多岁。由于这个原因,把这个问题描述为一个分类问题是明智的,因为我们试图估计这个人所处的年龄组。例如,0-2范围内的年龄是一个类,4-6是另一个类,依此类推。因此数据集分为以下8个年龄组[(0-2)、(4-6)、(8-12)、(15-20)、(25-32)、(38-43)、(48-53)、(60-100)]。因此,年龄预测网络在最后一层有8个节点,表示所述年龄范围。
应该记住,从一幅图像中预测年龄并不是一个很容易解决的问题,因为感知到的年龄取决于许多因素,而同龄的人在世界各地可能看起来很不一样。而且,人们非常努力地隐藏他们的真实年龄!
我们加载年龄网络(caffe模型)并使用前向通道获得输出。由于网络结构类似于性别网络,所以我们可以从所有输出中提取出最大值来得到预测的年龄组
尽管性别预测网络表现良好,但年龄预测网络仍未达到我们的预期。所以添加人脸对齐算法或者数据样本很多时候,可以通过回归的模型来检测。但是性别人脸检测还是很准确的。
在VS2017下运行了C++代码,其中OpenCV版本至少要3.4.5以上。不然模型读取会有问题。三个模型文件太大,见下载链接:
https://download.csdn.net/download/luohenyj/10993309
https://github.com/luohenyueji/OpenCV-Practical-Exercise
如果没有积分(系统自动设定资源分数)看看参考链接。我搬运过来的,大修改没有。
其中tensorflow和caffe模型都可以用opencv中的readnet函数读取,流程很简单。看看代码就会。
代码提供了C++和Python版本,但是python版本没有运行,原因opencv版本太低,不想升级。代码都有详细的注释。
C++版本:
#include
#include
#include
#include
#include
using namespace cv;
using namespace cv::dnn;
using namespace std;
/**
* @brief Get the Face Box object 人脸定位
*
* @param net 人脸检测网络
* @param frame 检测图像
* @param conf_threshold 阈值
* @return tuple>> 元组容器,可返回多个值
*/
tuple>> getFaceBox(Net net, Mat &frame, double conf_threshold)
{
//图像复制
Mat frameOpenCVDNN = frame.clone();
int frameHeight = frameOpenCVDNN.rows;
int frameWidth = frameOpenCVDNN.cols;
//缩放尺寸
double inScaleFactor = 1.0;
//检测图大小
Size size = Size(300, 300);
// std::vector meanVal = {104, 117, 123};
Scalar meanVal = Scalar(104, 117, 123);
cv::Mat inputBlob;
inputBlob = cv::dnn::blobFromImage(frameOpenCVDNN, inScaleFactor, size, meanVal, true, false);
net.setInput(inputBlob, "data");
//四维矩阵输出
cv::Mat detection = net.forward("detection_out");
//提取结果信息
cv::Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr());
vector> bboxes;
for (int i = 0; i < detectionMat.rows; i++)
{
//预测概率
float confidence = detectionMat.at(i, 2);
if (confidence > conf_threshold)
{
//左上角点,坐标被归一化
int x1 = static_cast(detectionMat.at(i, 3) * frameWidth);
int y1 = static_cast(detectionMat.at(i, 4) * frameHeight);
//右下角角点,坐标被归一化
int x2 = static_cast(detectionMat.at(i, 5) * frameWidth);
int y2 = static_cast(detectionMat.at(i, 6) * frameHeight);
vector box = { x1, y1, x2, y2 };
//人脸坐标
bboxes.push_back(box);
//图像框选
cv::rectangle(frameOpenCVDNN, cv::Point(x1, y1), cv::Point(x2, y2), cv::Scalar(0, 255, 0), 2, 4);
}
}
return make_tuple(frameOpenCVDNN, bboxes);
}
int main(void)
{
//人脸模型
string faceProto = "model/opencv_face_detector.pbtxt";
string faceModel = "model/opencv_face_detector_uint8.pb";
//年龄模型
string ageProto = "model/age_deploy.prototxt";
string ageModel = "model/age_net.caffemodel";
//性别模型
string genderProto = "model/gender_deploy.prototxt";
string genderModel = "model/gender_net.caffemodel";
//均值
Scalar MODEL_MEAN_VALUES = Scalar(78.4263377603, 87.7689143744, 114.895847746);
//年龄段标签
vector ageList = { "(0-2)", "(4-6)", "(8-12)", "(15-20)", "(25-32)",
"(38-43)", "(48-53)", "(60-100)" };
//性别标签
vector genderList = { "Male", "Female" };
//导入网络
Net ageNet = cv::dnn::readNet(ageProto, ageModel);
Net genderNet = cv::dnn::readNet(genderProto, genderModel);
Net faceNet = cv::dnn::readNetFromTensorflow(faceModel, faceProto);
//打开摄像头
VideoCapture cap;
cap.open(0);
if (cap.isOpened())
{
cout << "camera is opened!" << endl;
}
else
{
return 0;
}
int padding = 20;
while (waitKey(1) < 0)
{
// read frame 读图
Mat frame;
cap.read(frame);
if (frame.empty())
{
waitKey();
break;
}
frame = imread("./images/couple1.jpg");
//人脸坐标
vector> bboxes;
//人脸检测结果图
Mat frameFace;
//人脸定位
//tie()函数解包frameFace和bboxes
tie(frameFace, bboxes) = getFaceBox(faceNet, frame, 0.7);
//人脸判断
if (bboxes.size() == 0)
{
cout << "No face detected, checking next frame." << endl;
continue;
}
//逐个提取人脸检测
for (auto it = begin(bboxes); it != end(bboxes); ++it)
{
//框选人脸
Rect rec(it->at(0) - padding, it->at(1) - padding, it->at(2) - it->at(0) + 2 * padding, it->at(3) - it->at(1) + 2 * padding);
//避免人脸框选超过图像边缘
rec.width = ((rec.x + rec.width) > frame.cols) ? (frame.cols - rec.x - 1) : rec.width;
rec.height = ((rec.y + rec.height) > frame.rows) ? (frame.rows - rec.y - 1) : rec.height;
// take the ROI of box on the frame,原图中提取人脸
Mat face = frame(rec);
//性别检测
Mat blob;
blob = blobFromImage(face, 1, Size(227, 227), MODEL_MEAN_VALUES, false);
genderNet.setInput(blob);
// string gender_preds; 获取前向传播softmax结果
vector genderPreds = genderNet.forward();
// find max element index max_element用于找寻最大值
// distance function does the argmax() work in C++ distance返回最大值和第一个值下标的距离
int max_index_gender = std::distance(genderPreds.begin(), max_element(genderPreds.begin(), genderPreds.end()));
//获得检测结果
string gender = genderList[max_index_gender];
cout << "Gender: " << gender << endl;
//年龄识别
ageNet.setInput(blob);
vector agePreds = ageNet.forward();
// finding maximum indicd in the age_preds vector 找到年龄预测最大下表
int max_indice_age = std::distance(agePreds.begin(), max_element(agePreds.begin(), agePreds.end()));
string age = ageList[max_indice_age];
cout << "Age: " << age << endl;
// label 输出标签
string label = gender + ", " + age;
//在人脸定位图上显示结果
cv::putText(frameFace, label, Point(it->at(0), it->at(1) - 15), cv::FONT_HERSHEY_SIMPLEX, 0.9, Scalar(0, 255, 255), 2, cv::LINE_AA);
}
//保存结果
imshow("Frame", frameFace);
imwrite("out.jpg", frameFace);
}
}
python版本:
# Import required modules
import cv2 as cv
import time
import argparse
def getFaceBox(net, frame, conf_threshold=0.7):
frameOpencvDnn = frame.copy()
frameHeight = frameOpencvDnn.shape[0]
frameWidth = frameOpencvDnn.shape[1]
blob = cv.dnn.blobFromImage(frameOpencvDnn, 1.0, (300, 300), [104, 117, 123], True, False)
net.setInput(blob)
detections = net.forward()
bboxes = []
for i in range(detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence > conf_threshold:
x1 = int(detections[0, 0, i, 3] * frameWidth)
y1 = int(detections[0, 0, i, 4] * frameHeight)
x2 = int(detections[0, 0, i, 5] * frameWidth)
y2 = int(detections[0, 0, i, 6] * frameHeight)
bboxes.append([x1, y1, x2, y2])
cv.rectangle(frameOpencvDnn, (x1, y1), (x2, y2), (0, 255, 0), int(round(frameHeight/150)), 8)
return frameOpencvDnn, bboxes
parser = argparse.ArgumentParser(description='Use this script to run age and gender recognition using OpenCV.')
parser.add_argument('--input', help='Path to input image or video file. Skip this argument to capture frames from a camera.')
args = parser.parse_args()
faceProto = "age_gender/model/opencv_face_detector.pbtxt"
faceModel = "age_gender/model/opencv_face_detector_uint8.pb"
ageProto = "age_gender/model/age_deploy.prototxt"
ageModel = "age_gender/model/age_net.caffemodel"
genderProto = "age_gender/model/gender_deploy.prototxt"
genderModel = "age_gender/model/gender_net.caffemodel"
MODEL_MEAN_VALUES = (78.4263377603, 87.7689143744, 114.895847746)
ageList = ['(0-2)', '(4-6)', '(8-12)', '(15-20)', '(25-32)', '(38-43)', '(48-53)', '(60-100)']
genderList = ['Male', 'Female']
# Load network
ageNet = cv.dnn.readNet(ageModel, ageProto)
genderNet = cv.dnn.readNet(genderModel, genderProto)
faceNet = cv.dnn.readNet(faceModel, faceProto)
# Open a video file or an image file or a camera stream
cap = cv.VideoCapture(args.input if args.input else 0)
padding = 20
while cv.waitKey(1) < 0:
# Read frame
t = time.time()
hasFrame, frame = cap.read()
if not hasFrame:
cv.waitKey()
break
frameFace, bboxes = getFaceBox(faceNet, frame)
if not bboxes:
print("No face Detected, Checking next frame")
continue
for bbox in bboxes:
# print(bbox)
face = frame[max(0,bbox[1]-padding):min(bbox[3]+padding,frame.shape[0]-1),max(0,bbox[0]-padding):min(bbox[2]+padding, frame.shape[1]-1)]
blob = cv.dnn.blobFromImage(face, 1.0, (227, 227), MODEL_MEAN_VALUES, swapRB=False)
genderNet.setInput(blob)
genderPreds = genderNet.forward()
gender = genderList[genderPreds[0].argmax()]
# print("Gender Output : {}".format(genderPreds))
print("Gender : {}, conf = {:.3f}".format(gender, genderPreds[0].max()))
ageNet.setInput(blob)
agePreds = ageNet.forward()
age = ageList[agePreds[0].argmax()]
print("Age Output : {}".format(agePreds))
print("Age : {}, conf = {:.3f}".format(age, agePreds[0].max()))
label = "{},{}".format(gender, age)
cv.putText(frameFace, label, (bbox[0], bbox[1]-10), cv.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 255), 2, cv.LINE_AA)
cv.imshow("Age Gender Demo", frameFace)
# cv.imwrite("age-gender-out-{}".format(args.input),frameFace)
print("time : {:.3f}".format(time.time() - t))
https://www.learnopencv.com/age-gender-classification-using-opencv-deep-learning-c-python/