OpenCV人脸识别项目（训练+测试）-Toy模板网

这篇具有很好参考价值的文章主要介绍了OpenCV人脸识别项目（训练+测试）。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

图片来自网上，如果侵权，告知则删除

>>>>>>>>批量修改文件名（常见文件操作，可以学习一下）

import os

path = './opencv/data/images'

# 获取该目录下所有文件，存入列表中
labelList = os.listdir(path)
n = 0
count = 1
for label in labelList:
    print(label)
    dirPath = os.path.join(path,label)
    for img_name in os.listdir(dirPath):
        old_img_path = os.path.join(dirPath,img_name)
        # 设置新文件名
        name = str(n+1)+'.' + str(label) + '.'+ str(count) +'.jpg'
        # new_img_path = os.path.join(dirPath,name)
        new_img_path = dirPath + '/' + name
        print(old_img_path)
        print(new_img_path)
        os.rename(old_img_path, new_img_path)
        count +=1
    n+=1

>>>>>>>>进入正题

（一）读取图片

#导入cv模块
import  cv2 as cv
#读取图片
img = cv.imread('face1.png')
#显示图片
cv.imshow('read_img',img)
#等待
cv.waitKey(0)
#释放内存
cv.destroyAllWindows()

opencv人脸识别模型训练,opencv,人工智能,计算机视觉

（二）灰度转换

#导入cv模块
import cv2 as cv
#读取图片
img = cv.imread('face1.png')
#灰度转换
gray_img = cv.cvtColor(img,cv.COLOR_BGR2GRAY)
#显示灰度图片
cv.imshow('gray_img',gray_img)
#保存灰度图片
cv.imwrite('gray_face1.png',gray_img)
#显示图片
cv.imshow('read_img',img)
#等待
cv.waitKey(0)
#释放内存
cv.destroyAllWindows()

opencv人脸识别模型训练,opencv,人工智能,计算机视觉

（三）修改尺寸

#导入cv模块
import cv2 as cv
#读取图片
img = cv.imread('face1.png')
#修改尺寸
resize_img = cv.resize(img,dsize=(200,200))
#显示原图
cv.imshow('img',img)
#显示修改后的
cv.imshow('resize_img',resize_img)
#打印原图尺寸大小
print('未修改',img.shape)
#打印修改后的大小
print('修改后',resize_img.shape)
#等待
while True:
    if ord('q') == cv.waitKey(0):
        break
cv.waitKey(0)
#灰度转换
gray_img = cv.cvtColor(img,cv.COLOR_BGR2GRAY)
#显示灰度图片
cv.imshow('gray_img',gray_img)
#保存灰度图片
cv.imwrite('gray_face1.png',gray_img)
#显示图片
cv.imshow('read_img',img)
#等待
cv.waitKey(0)
#释放内存
cv.destroyAllWindows()

opencv人脸识别模型训练,opencv,人工智能,计算机视觉

（四）绘制矩形

#导入cv模块
import cv2 as cv
#读取图片
img = cv.imread('face1.png')
#坐标
x,y,w,h = 50,50,50,50
#绘制矩形
cv.rectangle(img,(x,y,x+w,y+h),color=(0,0,255),thickness=1)
#绘制圆形
cv.circle(img,center=(x+w,y+h),radius=50,color=(255,0,0),thickness=2)
#显示
cv.imshow('re_img',img)
#等待
while True:
    if ord('q') == cv.waitKey(0):
        break
#释放内存
cv.destroyAllWindows()

（五）人脸检测

#导入cv模块
import cv2 as cv
def face_detect_demo(img):
    gray = cv.cvtColor(img,cv.COLOR_BGR2GRAY)
    # 分类器
    face_detect = cv.CascadeClassifier('F:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_alt2.xml')
    face = face_detect.detectMultiScale(gray,1.01,5,0,(100,100),(300,300))
    for x,y,w,h in face:
        cv.rectangle(img,(x,y),(x+w,y+h),color=(0,0,255),thickness=2)
    cv.imshow('res',img)
# 读取图片
img = cv.imread('face1.png')
# 检测函数
face_detect_demo(img)
# 等待
while True:
    if ord('q') == cv.waitKey(0):
        break

# 释放内存
cv.destroyAllWindows()

opencv人脸识别模型训练,opencv,人工智能,计算机视觉

（六）检测多个人脸

#导入cv模块
import cv2 as cv
def face_detect_demo(img):
    gray = cv.cvtColor(img,cv.COLOR_BGR2GRAY)
    # 分类器
    # face_detect = cv.CascadeClassifier('F:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_alt2.xml')
    face_detect = cv.CascadeClassifier('F:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_default.xml')
    # face = face_detect.detectMultiScale(gray,1.1,5,0,(10,10),(100,100))
    face = face_detect.detectMultiScale(gray,1.1)
    for x,y,w,h in face:
        cv.rectangle(img,(x,y),(x+w,y+h),color=(0,0,255),thickness=2)
    cv.imshow('res',img)
# 读取图片
img = cv.imread('multi_face1.png')
# 检测函数
face_detect_demo(img)
# 等待
while True:
    if ord('q') == cv.waitKey(0):
        break

# 释放内存
cv.destroyAllWindows()

opencv人脸识别模型训练,opencv,人工智能,计算机视觉

（七）视频检测

#导入cv模块
import cv2 as cv
def face_detect_demo(img):
    gray = cv.cvtColor(img,cv.COLOR_BGR2GRAY)
    # 分类器
    # face_detect = cv.CascadeClassifier('F:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_alt2.xml')
    face_detect = cv.CascadeClassifier('F:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_default.xml')
    # face = face_detect.detectMultiScale(gray,1.1,5,0,(10,10),(100,100))
    face = face_detect.detectMultiScale(gray,1.1)
    for x,y,w,h in face:
        cv.rectangle(img,(x,y),(x+w,y+h),color=(0,0,255),thickness=2)
    cv.imshow('res',img)
# 读取摄像头
cap = cv.VideoCapture(0)
# cap = cv.VideoCapture("face.mp4")
# 循环
while True:
    flag,frame = cap.read()
    if not flag:
        break
    face_detect_demo(frame)
    if ord('q') == cv.waitKey(0):
        break
# 释放内存
cv.destroyAllWindows()
# 释放摄像头
cap.release()

（八）拍照保存

# 导入模块
import cv2
import os
# 摄像头
cap = cv2.VideoCapture(0)

num = 1

while(cap.isOpened()):#检测是否在开启状态
    flag,frame = cap.read() # 得到每帧图像
    cv2.imshow("Capture_Test",frame) #显示图像
    k = cv2.waitKey(1) & 0xFF #按键判断
    if k == ord('s'):#保存
        path = os.path.join('E:/faceRecognition/save_img/',str(num)+"_name"+".jpg")
        print(path)
        cv2.imwrite(path,frame)
        print("success to save"+str(num)+".jpg")
        print("----------------")
        num+=1
    elif k == ord(' '):
        break
# 释放摄像头
cap.release()
# 释放内存
cv2.destroyAllWindows()

>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>准备数据集>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

训练集train

opencv人脸识别模型训练,opencv,人工智能,计算机视觉

opencv人脸识别模型训练,opencv,人工智能,计算机视觉注意：第一个.前面是id,后面是label

测试集test

opencv人脸识别模型训练,opencv,人工智能,计算机视觉

（九）数据训练

import os
import cv2
from PIL import Image
import numpy as np

def getImageAndLabels(path):
    #存储人脸数据
    facesSamples = []
    # 储存姓名数据
    ids = []
    #储存图片信息
    # imagePaths = [(os.path.join(path,f) for f in os.listdir(path))]
    imagePaths = []
    for f in os.listdir(path):
        img_path = path+'/' + f
        imagePaths.append(img_path)
    #加载分类器
    face_detect = cv2.CascadeClassifier('F:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_alt2.xml')
    # print(imagePaths)
    #遍历列表中的图片
    for imagePath in imagePaths:
        # print(imagePath)
        #打开图片，灰度化PIL有九种不同模式
        PIL_img = Image.open(imagePath).convert('L')
        #将图像转换为数组，以黑白深浅
        img_numpy = np.array(PIL_img,'uint8')
        #保存图片人脸检测
        faces = face_detect.detectMultiScale(img_numpy)
        #获取每张图片的id和姓名
        id = int(os.path.split(imagePath)[1].split('.')[0])
        #预测无面容的图片
        for x,y,w,h in faces:
            ids.append(id)
            facesSamples.append(img_numpy[y:y+h,x:x+w])
        #打开脸部特征和id
    # print('id:',id)
    # print('fs:',facesSamples)
    return facesSamples,ids

if __name__ == '__main__':
    # 图片路径
    path = './opencv/data/images'
    # 获取该目录下所有文件，存入列表中
    labelList = os.listdir(path)
    facesList = []
    idsList = []
    for label in labelList:
        dirPath = path + '/' + str(label)
        # print('dirPath',dirPath)
        # 获取图像数组和id标签数组和姓名
        faces,ids = getImageAndLabels(dirPath)
        # print(faces)
        # print(ids)
        for face in faces:
            facesList.append(face)
        for id in ids:
            idsList.append(id)
        # # 加载识别器
        # recognizer = cv2.face.LBPHFaceRecognizer_create()
        # #训练
        # recognizer.train(faces,np.array(ids))
        # #保存文件
        # recognizer.write("trainer/trainer.yml")

    # print(facesList)
    # print(idsList)
    # 加载识别器
    recognizer = cv2.face.LBPHFaceRecognizer_create()
    #训练
    recognizer.train(facesList,np.array(idsList))
    #保存文件
    recognizer.write("trainer/trainer.yml")

（十）人脸识别

import cv2
import numpy as np
import os
# coding=utf-8
import urllib
import urllib.request
import hashlib

#加载训练数据集文件
recogizer=cv2.face.LBPHFaceRecognizer_create()
recogizer.read('trainer/trainer.yml')
names=[]

#准备识别的图片
def face_detect_demo(img):
    gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)#转换为灰度
    face_detector = cv2.CascadeClassifier('F:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_alt2.xml')
    # face=face_detector.detectMultiScale(gray,1.1,5,cv2.CASCADE_SCALE_IMAGE,(100,100),(300,300))
    face=face_detector.detectMultiScale(gray,1.1)
    for x,y,w,h in face:
        cv2.rectangle(img,(x,y),(x+w,y+h),color=(0,0,255),thickness=2)
        cv2.circle(img,center=(x+w//2,y+h//2),radius=w//2,color=(0,255,0),thickness=1)
        # 人脸识别
        ids, confidence = recogizer.predict(gray[y:y + h, x:x + w])
        print('标签id:',ids,'置信评分：', confidence)
        if confidence > 80:
            cv2.putText(img, str(names[ids - 1]), (x + 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.35, (0, 255, 0), 1)
            # cv2.putText(img, 'unkonw', (x + 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (0, 255, 0), 1)
        else:
            # cv2.putText(img, str(names[ids - 1]), (x + 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (0, 255, 0), 1)
            cv2.putText(img, 'unkonw', (x + 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (0, 255, 0), 1)
    cv2.namedWindow("result", cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)
    cv2.resizeWindow("result", 400, 400)
    cv2.moveWindow("result", 500, 250)  # 显示框位置，左上角为原点（0， 0）坐标，第一个是x坐标，第二个是y坐标
    cv2.imshow('result',img)
    #print('bug:',ids)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

def name():
    # path = './data/jm/'
    path = './opencv/data/images'
    names = []

    # 获取该目录下所有文件，存入列表中
    labelList = os.listdir(path)
    for label in labelList:
        names.append(label)
    print(names)
    return names


names = name()
path = './test'
for img_name in os.listdir(path):
    img_path = path + '/' + img_name
    img = cv2.imread(img_path)
    face_detect_demo(img)


# cap=cv2.VideoCapture('1.mp4')
# while True:
#     flag,frame=cap.read()
#     if not flag:
#         break
#     face_detect_demo(frame)
#     if ord(' ') == cv2.waitKey(10):
#         break

# cap.release()

>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>实验效果>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

opencv人脸识别模型训练,opencv,人工智能,计算机视觉