[mcj]使用OpenCV深度学习进行性别和年龄分类（C++/Python）-马春杰杰

文章目录

在本教程中，我们将讨论应用于面部的深度学习的有趣应用。我们将估计年龄并从单个图像中找出该人的性别。该模型由Gil Levi和Tal Hassner训练。我们将简要讨论本文的主要思想，并提供有关如何在OpenCV中使用该模型的分步说明。

1.使用CNN的性别和年龄分类

作者使用了一种非常简单的卷积神经网络架构，类似于CaffeNet和AlexNet。该网络使用3个卷积层，2个完全连接的层和最终的输出层。层的细节如下。
Conv1：第一个卷积层有96个内核大小为7的节点。
Conv2：第二个conv层有256个节点，内核大小为5。
Conv3：第三个转换层有384个节点，内核大小为3。

两个完全连接的层各有512个节点。
他们使用Adience数据集来训练模型。

1.1 性别预测

他们将性别预测定为分类问题。性别预测网络中的输出层是softmax类型，其中2个节点指示两个类“男性”和“女性”。

1.2 年龄预测

理想情况下，年龄预测应该作为回归问题来处理，因为我们期望将实数作为输出。但是，使用回归准确估计年龄具有挑战性。甚至人类也无法根据一个人的情况准确预测年龄。但是，我们知道他们是20岁还是30多岁。由于这个原因，将这个问题构建为一个分类问题是明智的，我们试图估计这个人所处的年龄组。例如，0-2范围内的年龄是单个类别，4-6是另一个类别上课等。

Adience数据集有8个类别，分为以下年龄组[（0 – 2），（4 – 6），（8 – 12），（15 – 20），（25 – 32），（38 – 43），（ 48 – 53），（60 – 100）]。因此，年龄预测网络在最终softmax层中具有8个节点，指示所述年龄范围。
应该记住，单个图像的年龄预测不是一个很容易解决的问题，因为感知年龄取决于很多因素，同一年龄的人在世界各地可能看起来很不一样。此外，人们非常努力地隐藏自己的真实年龄！
例如，你能猜出这两位知名人士的年龄吗？
[mcj]使用OpenCV深度学习进行性别和年龄分类（C++/Python）

Narendra Modi是68岁，Ajit Doval是74岁！想象一下机器正确预测其年龄有多难。

2.代码教程

代码可以分为四个部分：

检测面孔
检测性别
检测年龄
显示输出

注意：请下载未随代码一起提供的模型权重文件（性别，年龄）。下载文件并将其与本文提供的其他代码文件一起保存。

下载代码后，您可以使用提供的示例图像或使用网络摄像头运行代码。

#Using sample image 
./AgeGender sample1.jpg

1 2	#Using sample image ./AgeGender sample1.jpg

#Using sample image 
python AgeGender.py --input sample1.jpg

1 2	#Using sample image python AgeGender.py --input sample1.jpg

最终代码在文末！

2.1检测脸部

我们将使用DNN人脸检测器进行人脸检测。该型号仅为2.7MB，即使在CPU上也非常快。关于脸部检测装置的更多细节可以在我们的博客上找到的人脸检测。使用函数getFaceBox完成面部检测，如下所示。

tuple&lt;Mat, vector&lt;vector&lt;int&gt;&gt;&gt; getFaceBox(Net net, Mat &amp;amp;frame, double conf_threshold)
{
    Mat frameOpenCVDNN = frame.clone();
    int frameHeight = frameOpenCVDNN.rows;
    int frameWidth = frameOpenCVDNN.cols;
    double inScaleFactor = 1.0;
    Size size = Size(300, 300);
    // std::vector&lt;int&gt; meanVal = {104, 117, 123};
    Scalar meanVal = Scalar(104, 117, 123);
 
    cv::Mat inputBlob;
    cv::dnn::blobFromImage(frameOpenCVDNN, inputBlob, inScaleFactor, size, meanVal, true, false);
 
    net.setInput(inputBlob, "data");
    cv::Mat detection = net.forward("detection_out");
 
    cv::Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr&lt;float&gt;());
 
    vector&lt;vector&lt;int&gt;&gt; bboxes;
 
    for(int i = 0; i &lt; detectionMat.rows; i++)
    {
        float confidence = detectionMat.at&lt;float&gt;(i, 2);
 
        if(confidence &gt; conf_threshold)
        {
            int x1 = static_cast&lt;int&gt;(detectionMat.at&lt;float&gt;(i, 3) * frameWidth);
            int y1 = static_cast&lt;int&gt;(detectionMat.at&lt;float&gt;(i, 4) * frameHeight);
            int x2 = static_cast&lt;int&gt;(detectionMat.at&lt;float&gt;(i, 5) * frameWidth);
            int y2 = static_cast&lt;int&gt;(detectionMat.at&lt;float&gt;(i, 6) * frameHeight);
            vector&lt;int&gt; box = {x1, y1, x2, y2};
            bboxes.push_back(box);
            cv::rectangle(frameOpenCVDNN, cv::Point(x1, y1), cv::Point(x2, y2), cv::Scalar(0, 255, 0),2, 4);
        }
    }
 
    return make_tuple(frameOpenCVDNN, bboxes);
}

tuple<Mat, vector<vector<int>>> getFaceBox(Net net, Mat &amp;frame, double conf_threshold)

{

Mat frameOpenCVDNN = frame.clone();

int frameHeight = frameOpenCVDNN.rows;

int frameWidth = frameOpenCVDNN.cols;

double inScaleFactor = 1.0;

Size size = Size(300, 300);

// std::vector<int> meanVal = {104, 117, 123};

Scalar meanVal = Scalar(104, 117, 123);

cv::Mat inputBlob;

cv::dnn::blobFromImage(frameOpenCVDNN, inputBlob, inScaleFactor, size, meanVal, true, false);

net.setInput(inputBlob, "data");

cv::Mat detection = net.forward("detection_out");

cv::Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());

vector<vector<int>> bboxes;

for(int i = 0; i < detectionMat.rows; i++)

{

float confidence = detectionMat.at<float>(i, 2);

if(confidence > conf_threshold)

{

int x1 = static_cast<int>(detectionMat.at<float>(i, 3) * frameWidth);

int y1 = static_cast<int>(detectionMat.at<float>(i, 4) * frameHeight);

int x2 = static_cast<int>(detectionMat.at<float>(i, 5) * frameWidth);

int y2 = static_cast<int>(detectionMat.at<float>(i, 6) * frameHeight);

vector<int> box = {x1, y1, x2, y2};

bboxes.push_back(box);

cv::rectangle(frameOpenCVDNN, cv::Point(x1, y1), cv::Point(x2, y2), cv::Scalar(0, 255, 0),2, 4);

}

return make_tuple(frameOpenCVDNN, bboxes);

}

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 &gt; 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

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

2.2 预测性别

我们将性别网络加载到内存中，并通过网络传递检测到的面部。前向传递给出了两个类的概率或置信度。我们取两个输出的最大值并将其用作最终的性别预测。

string genderProto = "gender_deploy.prototxt";
string genderModel = "gender_net.caffemodel";
Net genderNet = readNet(genderModel, genderProto);
 
vector&lt;string&gt; genderList = {"Male", "Female"};
 
blob = blobFromImage(face, 1, Size(227, 227), MODEL_MEAN_VALUES, false);
genderNet.setInput(blob);
// string gender_preds;
vector&lt;float&gt; genderPreds = genderNet.forward();
// printing gender here
// find max element index
// distance function does the argmax() work in C++
int max_index_gender = std::distance(genderPreds.begin(), max_element(genderPreds.begin(), genderPreds.end()));
string gender = genderList[max_index_gender];

string genderProto = "gender_deploy.prototxt";

string genderModel = "gender_net.caffemodel";

Net genderNet = readNet(genderModel, genderProto);

vector<string> genderList = {"Male", "Female"};

blob = blobFromImage(face, 1, Size(227, 227), MODEL_MEAN_VALUES, false);

genderNet.setInput(blob);

// string gender_preds;

vector<float> genderPreds = genderNet.forward();

// printing gender here

// find max element index

// distance function does the argmax() work in C++

int max_index_gender = std::distance(genderPreds.begin(), max_element(genderPreds.begin(), genderPreds.end()));

string gender = genderList[max_index_gender];

genderProto = "gender_deploy.prototxt"
genderModel = "gender_net.caffemodel"
ageNet = cv.dnn.readNet(ageModel, ageProto)
 
genderList = ['Male', 'Female']
 
blob = cv.dnn.blobFromImage(face, 1, (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 : {}".format(gender))

genderProto = "gender_deploy.prototxt"

genderModel = "gender_net.caffemodel"

ageNet = cv.dnn.readNet(ageModel, ageProto)

genderList = ['Male', 'Female']

blob = cv.dnn.blobFromImage(face, 1, (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 : {}".format(gender))

2.3 预测年龄

我们加载年龄网络并使用正向传递来获得输出。由于网络架构类似于性别网络，我们可以从所有输出中获取最大值以获得预测年龄组。

string ageProto = "age_deploy.prototxt";
string ageModel = "age_net.caffemodel";
Net ageNet = readNet(ageModel, ageProto);
 
vector&lt;string&gt; ageList = {"(0-2)", "(4-6)", "(8-12)", "(15-20)", "(25-32)", "(38-43)", "(48-53)", "(60-100)"};
 
ageNet.setInput(blob);
vector&lt;float&gt; agePreds = ageNet.forward();
int max_indice_age = distance(agePreds.begin(), max_element(agePreds.begin(), agePreds.end()));
string age = ageList[max_indice_age];

string ageProto = "age_deploy.prototxt";

string ageModel = "age_net.caffemodel";

Net ageNet = readNet(ageModel, ageProto);

vector<string> ageList = {"(0-2)", "(4-6)", "(8-12)", "(15-20)", "(25-32)", "(38-43)", "(48-53)", "(60-100)"};

ageNet.setInput(blob);

vector<float> agePreds = ageNet.forward();

int max_indice_age = distance(agePreds.begin(), max_element(agePreds.begin(), agePreds.end()));

string age = ageList[max_indice_age];

ageProto = "age_deploy.prototxt"
ageModel = "age_net.caffemodel"
ageNet = cv.dnn.readNet(ageModel, ageProto)
 
ageList = ['(0 - 2)', '(4 - 6)', '(8 - 12)', '(15 - 20)', '(25 - 32)', '(38 - 43)', '(48 - 53)', '(60 - 100)']
 
ageNet.setInput(blob)
agePreds = ageNet.forward()
age = ageList[agePreds[0].argmax()]
print("Gender Output : {}".format(agePreds))
print("Gender : {}".format(age))

ageProto = "age_deploy.prototxt"

ageModel = "age_net.caffemodel"

ageNet = cv.dnn.readNet(ageModel, ageProto)

ageList = ['(0 - 2)', '(4 - 6)', '(8 - 12)', '(15 - 20)', '(25 - 32)', '(38 - 43)', '(48 - 53)', '(60 - 100)']

ageNet.setInput(blob)

agePreds = ageNet.forward()

age = ageList[agePreds[0].argmax()]

print("Gender Output : {}".format(agePreds))

print("Gender : {}".format(age))

2.4 显示输出

我们将在输入图像上显示网络输出，并使用imshow功能显示它们。

string label = gender + ", " + age; // label
cv::putText(frameFace, label, Point(it-&gt;at(0), it-&gt;at(1) -20), cv::FONT_HERSHEY_SIMPLEX, 0.9, Scalar(0, 255, 255), 2, cv::LINE_AA);
imshow("Frame", frameFace);

string label = gender + ", " + age; // label

cv::putText(frameFace, label, Point(it->at(0), it->at(1) -20), cv::FONT_HERSHEY_SIMPLEX, 0.9, Scalar(0, 255, 255), 2, cv::LINE_AA);

imshow("Frame", frameFace);

label = "{}, {}".format(gender, age)
cv.putText(frameFace, label, (bbox[0], bbox[1]-20), cv.FONT_HERSHEY_SIMPLEX, 0.8, (255, 0, 0), 3, cv.LINE_AA)
cv.imshow("Age Gender Demo", frameFace)