1、任务描述

性别分类和年龄分类预测

2、网络结构

2.1 人脸检测

输出最高的 200 个 RoI，每个 RoI 7 个值，（xx，xx，score，x0，y0，x1，y1）

2.2 性别分类

二分类

2.3 年龄分类

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

3、代码实现

先检测人脸，人脸外扩，再性别检测，再年龄检测，最后结果绘制输出

# Import required modules
import cv2 as cv
import math
import time
import argparse


def getFaceBox(net, frame, conf_threshold=0.7):
    frameOpencvDnn = frame.copy()
    frameHeight = frameOpencvDnn.shape[0]  # 333
    frameWidth = frameOpencvDnn.shape[1]  # 500
    blob = cv.dnn.blobFromImage(frameOpencvDnn, 1.0, (300, 300), [104, 117, 123], True, False)

    net.setInput(blob)
    detections = net.forward()  # (1, 1, 200, 7)， (xxx, xxx, confidence, x0, y0, x1, y1)
    bboxes = []
    for i in range(detections.shape[2]):  # 遍历 top 200 RoI
        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.',
                    default="jolie.jpg")
parser.add_argument("--device", default="cpu", help="Device to inference on")

args = parser.parse_args()


args = parser.parse_args()

faceProto = "opencv_face_detector.pbtxt"
faceModel = "opencv_face_detector_uint8.pb"

ageProto = "age_deploy.prototxt"
ageModel = "age_net.caffemodel"

genderProto = "gender_deploy.prototxt"
genderModel = "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)


if args.device == "cpu":
    ageNet.setPreferableBackend(cv.dnn.DNN_TARGET_CPU)
    genderNet.setPreferableBackend(cv.dnn.DNN_TARGET_CPU)
    faceNet.setPreferableBackend(cv.dnn.DNN_TARGET_CPU)
    print("Using CPU device")

elif args.device == "gpu":
    ageNet.setPreferableBackend(cv.dnn.DNN_BACKEND_CUDA)
    ageNet.setPreferableTarget(cv.dnn.DNN_TARGET_CUDA)

    genderNet.setPreferableBackend(cv.dnn.DNN_BACKEND_CUDA)
    genderNet.setPreferableTarget(cv.dnn.DNN_TARGET_CUDA)

    genderNet.setPreferableBackend(cv.dnn.DNN_BACKEND_CUDA)
    genderNet.setPreferableTarget(cv.dnn.DNN_TARGET_CUDA)
    print("Using GPU device")


# 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)  # (333, 500, 3), 4 bbox
    if not bboxes:
        print("No face Detected, Checking next frame")
        continue

    for bbox in bboxes:  # 遍历检测出来的人脸
        # 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)] # 人脸外扩

        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()]
        # array([[9.9999559e-01, 4.4012304e-06]], dtype=float32), 'Male'
        # print("Gender Output : {}".format(genderPreds))
        print("Gender : {}, conf = {:.3f}".format(gender, genderPreds[0].max()))

        ageNet.setInput(blob)
        agePreds = ageNet.forward()
        """
        array([[5.3957672e-05, 5.3967893e-02, 9.4579268e-01, 1.0875276e-04, 5.0436443e-05, 
                1.2142612e-05, 1.0151542e-05, 3.9845672e-06]],dtype=float32)
        """
        age = ageList[agePreds[0].argmax()]  # '(8-12)'
        # print("Age Output : {}".format(agePreds))
        # print("Age : {}, conf = {:.3f}".format(age, agePreds[0].max()))

        label = "{},{}".format(gender, age)  # Out[15]: 'Male,(8-12)'
        cv.putText(frameFace, label, (bbox[0], bbox[1]-5), cv.FONT_HERSHEY_SIMPLEX,
                   0.6, (0, 0, 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))

4、结果展示

输入图片

人脸检测结果

人脸外扩

输出结果

性别还是比较准的

输入图片

输出结果

输入图片

输出结果

输入图片

输出结果

输入图片

输出结果

5、参考

OpenCV进阶（8）性别和年龄识别