1.年龄检测
论文地址:《Age and Gender Classification using Convolutional Neural Networks》
论文作者提出了一个简单的类似AlexNet的网络结构,该网络总共学习了8个年龄段:
- 0-2
- 4-6
- 8-12
- 15-20
- 25-32
- 38-43
- 48-53
- 60-100
注意:这些年龄段不是连续的
首先,要搞懂检测年龄适合用回归还是用分类来做
举个栗子:
1. 回归
2. 分类
年龄预测是基于面部外观,有的人保养的好,显得年轻,实际年龄与测得会有差别。在不结合其它有关信息作推断情况下,网络模型很难预测到实际的真实年龄。若看作是回归问题,模型很难预测到图像中年龄的一个准确值,而看作是分类问题,预测一个年龄段相对来说模型更容易训练,比回归产生更高的准确性。
2.思路方法
自动识别年龄步骤:
1. 检测出输入图像或视频中的人脸
2. 提取面部感兴趣区域(ROI)
3. 用年龄检测器预测人物的年龄
4. 返回结果
对于检测人脸的分类器:
分类器 | 优缺点 |
---|---|
Haar级联 | 速度快,嵌入式设备上运行,但准确性低 |
HOG +线性SVM | 相比Haar级联精确,但速度慢,对遮挡,面部角度变化时检测效果不好 |
深度学习检测器 | 相比以上两者效果最佳,但需消耗更多计算资源 |
3.代码实现
环境:
- win10
- pycharm
- anaconda3
- python3.7
- opencv4.2.0
对于OpenCV尽量用最新版本,可参考这篇仅一个命令行简单快速安装:https://blog.csdn.net/y459541195/article/details/104851892
文件结构:
3.1 单张图像检测代码
import numpy as np
import cv2
"""
#图片年龄预测
执行:
python test_age.py
"""
# 检测年龄段
AGE_LIST = ["(0-2)","(4-6)","(8-12)","(15-20)","(25-32)","(38-43)","(48-53)","(60-100)"]
# 人脸检测模型路径
prototxtPathF ="./models/face_detector/face_deploy.prototxt"
weightsPathF = "./models/face_detector/res10_300x300_ssd_iter_140000.caffemodel"
# 加载人脸模型
faceNet = cv2.dnn.readNet(prototxtPathF,weightsPathF)
# 年龄检测模型
prototxtPathA ="./models/age_detector/age_deploy.prototxt"
weightsPathA = "./models/age_detector/age_net.caffemodel"
#加载模型
ageNet = cv2.dnn.readNet(prototxtPathA,weightsPathA)
#获取图像
image = cv2.imread("./input/test01.jpg")
src = image.copy()
(h,w)= image.shape[:2]
# 构造blob
blob = cv2.dnn.blobFromImage(image,1.0,(300,300),
(104,177,123))
# 送入网络计算
faceNet.setInput(blob)
detect = faceNet.forward()
# 检测
for i in range(0,detect.shape[2]):
confidence = detect[0,0,i,2]
# 过滤掉小的置信度,计算坐标,提取面部roi,构造面部blob特征
if confidence > 0.5:
box = detect[0,0,i,3:7]*np.array([w,h,w,h])
(startX,startY,endX,endY) = box.astype("int")
face = image[startY:endY,startX:endX]
faceBlob = cv2.dnn.blobFromImage(face, 1.0, (227, 227),
(78.4263377603, 87.7689143744, 114.895847746),
swapRB=False)
# 预测年龄
ageNet.setInput(faceBlob)
predictions = ageNet.forward()
i = predictions[0].argmax()
age = AGE_LIST[i]
ageConfidence = predictions[0][i]
#显示打印
text = "age{}:{:.2f}%".format(age,ageConfidence*100)
print(text)
#绘制显示框
y = startY - 10 if startY - 10 > 10 else startY + 10
cv2.rectangle(image, (startX, startY), (endX, endY),
(0, 0, 255), 2)
cv2.putText(image, text, (startX, y),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 255), 2)
cv2.imshow("Result",image)
cv2.waitKey(0)
3.2 视频流检测代码
import numpy as np
import cv2
import imutils
"""
#视频流年龄预测
执行:
python test_video_age.py
"""
def detect_age(frame,faceNet,ageNet,minConfidence=0.5):
# 检测年龄段
AGE_LIST = ["(0-2)","(4-6)","(8-12)","(15-20)","(25-32)","(38-43)","(48-53)","(60-100)"]
#定义空列表存放结果
results = []
(h,w)= frame.shape[:2]
# 构造blob
blob = cv2.dnn.blobFromImage(frame,1.0,(300,300),
(104,177,123))
# 送入网络计算
faceNet.setInput(blob)
detect = faceNet.forward()
# 检测
for i in range(0,detect.shape[2]):
confidence = detect[0,0,i,2]
# 过滤掉小的置信度,计算坐标,提取面部roi,
if confidence > minConfidence:
box = detect[0,0,i,3:7]*np.array([w,h,w,h])
(startX,startY,endX,endY) = box.astype("int")
face = frame[startY:endY,startX:endX]
# 过滤干扰
if face.shape[0]<20 or face.shape[1]<20:
continue
# 构造面部blob特
faceBlob = cv2.dnn.blobFromImage(face, 1.0, (227, 227),
(78.4263377603, 87.7689143744, 114.895847746),
swapRB=False)
# 预测年龄
ageNet.setInput(faceBlob)
predictions = ageNet.forward()
i = predictions[0].argmax()
age = AGE_LIST[i]
ageConfidence = predictions[0][i]
# 构造字典存放结果
dicts = {
"location":(startX,startY,endX,endY),
"age":(age,ageConfidence)
}
results.append(dicts)
return results
# 人脸检测模型路径
prototxtPathF ="./models/face_detector/face_deploy.prototxt"
weightsPathF = "./models/face_detector/res10_300x300_ssd_iter_140000.caffemodel"
# 加载人脸模型
faceNet = cv2.dnn.readNet(prototxtPathF,weightsPathF)
# 年龄检测模型
prototxtPathA ="./models/age_detector/age_deploy.prototxt"
weightsPathA = "./models/age_detector/age_net.caffemodel"
#加载模型
ageNet = cv2.dnn.readNet(prototxtPathA,weightsPathA)
#获取视频图像
videoPath = "./input/test1.mp4"
vs = cv2.VideoCapture(videoPath)
#处理视频流
while True:
(grabbed,frame) = vs.read()
# 判断是否结束
if not grabbed:
print("无视频读取...")
break
frame = imutils.resize(frame,width=720)
#调用上面函数计算
results = detect_age(frame,faceNet,ageNet,minConfidence=0.5)
for i in results:
#显示信息
text = "age{}:{:.2f}%".format(i["age"][0], i["age"][1] * 100)
(startX,startY,endX,endY) = i["location"]
# 绘制显示框
y = startY - 10 if startY - 10 > 10 else startY + 10
cv2.rectangle(frame, (startX, startY), (endX, endY),
(0, 0, 255), 2)
cv2.putText(frame, text, (startX, y),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 255), 2)
# 显示
cv2.imshow("Result", frame)
key = cv2.waitKey(1) & 0xFF
# 按q键退出循环
if key == ord("q"):
break
cv2.destroyAllWindows()
vs.release()
4.测试结果
4.1 单张图像测试
虚拟环境下命令行输入:
python test_age.py
效果一:
效果二:
效果三:
4.2 视频流检测
深度学习之年龄检测
视频地址: https://www.bilibili.com/video/BV16g4y187iQ/
Reference:
1.https://talhassner.github.io/home/publication/2015_CVPR
2.https://github.com/dpressel/rude-carnie
3.https://github.com/GilLevi/AgeGenderDeepLearning