OpenCV完结篇——计算机视觉（人脸识别 || 车牌识别）

本文介绍: 每个特征都是通过从黑色矩形下的像素总和减去白色矩形下的像素总和获得的单个值。scaleFactor调整哈尔级联器的人脸选框使其能框住人脸。测试一下，识别文字还是很准的！深度学习是计算机视觉最为重要的方法。具体实现还需要进一步优化！配置出现问题的，可以看看这篇。只要不测口，还是比较准确的。安装很简单，这里贴一个。

文章 目录

Haar人脸识别方法
Haar识别眼鼻口
Haar+Tesseract进行车牌识别
深度学习基础知识
dnn实现图像分类

在这里插入图片描述

Haar 人脸识别 方法

在这里插入图片描述

scaleFactor调整哈尔级联器的人脸选框使其能框住人脸

官方教程指路

每个特征都是通过从黑色矩形下的像素总和减去白色矩形下的像素总和获得的单个值

级联器模型文件位置

# -*- coding: utf-8 -*-
import cv2
import numpy as np

cv2.namedWindow('img', cv2.WINDOW_NORMAL)
#第一步，创建Haar级联器
facer = cv2.CascadeClassifier('./haarcascade_frontalface_default.xml')

#第二步，导入人脸识别的图片并将其灰度化
img = cv2.imread('E:/pic/Pic/11.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#第三步，进行人脸识别
#[[x,y,w,h]]
faces = facer.detectMultiScale(gray, 1.1, 5)

for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)

cv2.imshow('img', img)
if cv2.waitKey(0) &amp; 0xff == 27:
    cv2.destroyAllWindows()

在这里插入图片描述

Ha ar 识别眼鼻口

# -*- coding: utf-8 -*-
import cv2
import numpy as np

cv2.namedWindow('img', cv2.WINDOW_NORMAL)
#第一步，创建Haar级联器
facer = cv2.CascadeClassifier('./haarcascade_frontalface_default.xml')
eye = cv2.CascadeClassifier('./haarcascade_eye.xml')
mouse = cv2.CascadeClassifier('./haarcascade_mcs_mouth.xml')

#第二步，导入人脸识别的图片并将其灰度化
img = cv2.imread('E:/pic/Pic/11.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#第三步，进行人脸识别
#[[x,y,w,h]]
faces = facer.detectMultiScale(gray, 1.1, 5)
eyes = eye.detectMultiScale(gray, 1.1, 5)
mouses = mouse.detectMultiScale(gray, 1.1, 5)

for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)

for (x, y, w, h) in eyes:
    cv2.rectangle(img, (x, y), (x + w, y + h), (255, 255, 0), 3)

# for (x, y, w, h) in mouses:
#     cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 255), 3)

cv2.imshow('img', img)
if cv2.waitKey(0) &amp; 0xff == 27:
    cv2.destroyAllWindows()

在这里插入图片描述
识别嘴就会不精确了

# -*- coding: utf-8 -*-
import cv2
import numpy as np

cv2.namedWindow('img', cv2.WINDOW_NORMAL)
#第一步，创建Haar级联器
facer = cv2.CascadeClassifier('./haarcascade_frontalface_default.xml')
eye = cv2.CascadeClassifier('./haarcascade_eye.xml')
mouse = cv2.CascadeClassifier('./haarcascade_mcs_mouth.xml')

#第二步，导入人脸识别的图片并将其灰度化
img = cv2.imread('E:/pic/Pic/11.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#第三步，进行人脸识别
#[[x,y,w,h]]
faces = facer.detectMultiScale(gray, 1.1, 5)
eyes = eye.detectMultiScale(gray, 1.1, 5)
mouses = mouse.detectMultiScale(gray, 1.1, 5)

for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)

for (x, y, w, h) in eyes:
    cv2.rectangle(img, (x, y), (x + w, y + h), (255, 255, 0), 3)

for (x, y, w, h) in mouses:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 255), 3)

cv2.imshow('img', img)
if cv2.waitKey(0) &amp; 0xff == 27:
    cv2.destroyAllWindows()

在这里插入图片描述
识别鼻子

# -*- coding: utf-8 -*-
import cv2
import numpy as np

cv2.namedWindow('img', cv2.WINDOW_NORMAL)
#第一步，创建Haar级联器
facer = cv2.CascadeClassifier('./haarcascade_frontalface_default.xml')
eye = cv2.CascadeClassifier('./haarcascade_eye.xml')
mouse = cv2.CascadeClassifier('./haarcascade_mcs_mouth.xml')
nose = cv2.CascadeClassifier('./haarcascade_mcs_nose.xml')

#第二步，导入人脸识别的图片并将其灰度化
img = cv2.imread('E:/pic/Pic/11.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#第三步，进行人脸识别
#[[x,y,w,h]]
faces = facer.detectMultiScale(gray, 1.1, 5)
eyes = eye.detectMultiScale(gray, 1.1, 5)
mouses = mouse.detectMultiScale(gray, 1.1, 5)
noses = nose.detectMultiScale(gray, 1.1, 5)

for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)

for (x, y, w, h) in eyes:
    cv2.rectangle(img, (x, y), (x + w, y + h), (255, 255, 0), 3)

for (x, y, w, h) in mouses:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 255), 3)

for (x, y, w, h) in noses:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 3)

cv2.imshow('img', img)
if cv2.waitKey(0) &amp; 0xff == 27:
    cv2.destroyAllWindows()

在这里插入图片描述
只要不测口，还是比较准确的

# -*- coding: utf-8 -*-
import cv2
import numpy as np

cv2.namedWindow('img', cv2.WINDOW_NORMAL)
#第一步，创建Haar级联器
facer = cv2.CascadeClassifier('./haarcascade_frontalface_default.xml')
eye = cv2.CascadeClassifier('./haarcascade_eye.xml')
mouse = cv2.CascadeClassifier('./haarcascade_mcs_mouth.xml')
nose = cv2.CascadeClassifier('./haarcascade_mcs_nose.xml')

#第二步，导入人脸识别的图片并将其灰度化
img = cv2.imread('E:/pic/Pic/11.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#第三步，进行人脸识别
#[[x,y,w,h]]
faces = facer.detectMultiScale(gray, 1.1, 5)
# eyes = eye.detectMultiScale(gray, 1.1, 5)
# mouses = mouse.detectMultiScale(gray, 1.1, 5)
# noses = nose.detectMultiScale(gray, 1.1, 5)

i = 0

for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)
    roi_img = img[y: y+h, x:x+w]
    eyes = eye.detectMultiScale(roi_img, 1.1, 5)
    for (x, y, w, h) in eyes:
        cv2.rectangle(roi_img, (x, y), (x + w, y + h), (255, 255, 0), 3)
    noses = nose.detectMultiScale(roi_img, 1.1, 5)
    for (x, y, w, h) in noses:
        cv2.rectangle(roi_img, (x, y), (x + w, y + h), (0, 0, 255), 3)
    # mouses = mouse.detectMultiScale(roi_img, 1.1, 5)
    # for (x, y, w, h) in mouses:
    #     cv2.rectangle(roi_img, (x, y), (x + w, y + h), (0, 255, 255), 3)
    
    # i += 1
    # winname = 'face' + str(i)
    # cv2.imshow(winname, roi_img)

# for (x, y, w, h) in mouses:
#     cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 255), 3)

# for (x, y, w, h) in noses:
#     cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 3)

cv2.imshow('img', img)
if cv2.waitKey(0) &amp; 0xff == 27:
    cv2.destroyAllWindows()

在这里插入图片描述
测口准确度太低！！！

# -*- coding: utf-8 -*-
import cv2
import numpy as np

cv2.namedWindow('img', cv2.WINDOW_NORMAL)
#第一步，创建Haar级联器
facer = cv2.CascadeClassifier('./haarcascade_frontalface_default.xml')
eye = cv2.CascadeClassifier('./haarcascade_eye.xml')
mouse = cv2.CascadeClassifier('./haarcascade_mcs_mouth.xml')
nose = cv2.CascadeClassifier('./haarcascade_mcs_nose.xml')

#第二步，导入人脸识别的图片并将其灰度化
img = cv2.imread('E:/pic/Pic/11.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#第三步，进行人脸识别
#[[x,y,w,h]]
faces = facer.detectMultiScale(gray, 1.1, 5)
# eyes = eye.detectMultiScale(gray, 1.1, 5)
# mouses = mouse.detectMultiScale(gray, 1.1, 5)
# noses = nose.detectMultiScale(gray, 1.1, 5)

i = 0

for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)
    roi_img = img[y: y+h, x:x+w]
    eyes = eye.detectMultiScale(roi_img, 1.1, 5)
    for (x, y, w, h) in eyes:
        cv2.rectangle(roi_img, (x, y), (x + w, y + h), (255, 255, 0), 3)
    noses = nose.detectMultiScale(roi_img, 1.1, 5)
    for (x, y, w, h) in noses:
        cv2.rectangle(roi_img, (x, y), (x + w, y + h), (0, 0, 255), 3)
    mouses = mouse.detectMultiScale(roi_img, 1.1, 5)
    for (x, y, w, h) in mouses:
        cv2.rectangle(roi_img, (x, y), (x + w, y + h), (0, 255, 255), 3)
    
    # i += 1
    # winname = 'face' + str(i)
    # cv2.imshow(winname, roi_img)

# for (x, y, w, h) in mouses:
#     cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 255), 3)

# for (x, y, w, h) in noses:
#     cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 3)

cv2.imshow('img', img)
if cv2.waitKey(0) &amp; 0xff == 27:
    cv2.destroyAllWindows()

在这里插入图片描述

Haar+Tesse ract进行车牌识别

在这里插入图片描述

安装很简单，这里贴一个安装教程

配置出现问题的，可以看看这篇博客

测试一下，识别文字还是很准的！！！
在这里插入图片描述

# -*- coding: utf-8 -*-
import cv2
import numpy as np

# cv2.namedWindow('img', cv2.WINDOW_NORMAL)
#第一步，创建Haar级联器
carplate = cv2.CascadeClassifier('./haarcascade_russian_plate_number.xml')

#第二步，导入带车牌的图片并将其灰度化
img = cv2.imread('./chinacar.jpeg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#第三步，进行车牌定位
#[[x,y,w,h]]
carplates = carplate.detectMultiScale(gray, 1.1, 5)

for (x, y, w, h) in carplates:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)

cv2.imshow('img', img)
if cv2.waitKey(0) &amp; 0xff == 27:
    cv2.destroyAllWindows()

在这里插入图片描述

# -*- coding: utf-8 -*-
import cv2
import numpy as np

# cv2.namedWindow('img', cv2.WINDOW_NORMAL)
#第一步，创建Haar级联器
carplate = cv2.CascadeClassifier('./haarcascade_russian_plate_number.xml')

#第二步，导入带车牌的图片并将其灰度化
img = cv2.imread('./chinacar.jpeg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#第三步，进行车牌定位
#[[x,y,w,h]]
carplates = carplate.detectMultiScale(gray, 1.1, 5)

for (x, y, w, h) in carplates:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)

# 对获取到的车牌进行预处理
# 1.提取ROI
roi = gray[y: y+h, x:x+w]
# 2.进行二值化
ret, roi_bin = cv2.threshold(roi, 10, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)

cv2.imshow('img', img)
cv2.imshow('roi_bin', roi_bin)
if cv2.waitKey(0) &amp; 0xff == 27:
    cv2.destroyAllWindows()

在这里插入图片描述

# -*- coding: utf-8 -*-
import cv2
import numpy as np

# 引入tesseract库
import pytesseract

# cv2.namedWindow('img', cv2.WINDOW_NORMAL)
#第一步，创建Haar级联器
carplate = cv2.CascadeClassifier('./haarcascade_russian_plate_number.xml')

#第二步，导入带车牌的图片并将其灰度化
img = cv2.imread('./chinacar.jpeg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#第三步，进行车牌定位
#[[x,y,w,h]]
carplates = carplate.detectMultiScale(gray, 1.1, 5)

for (x, y, w, h) in carplates:
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)

# 对获取到的车牌进行预处理
# 1.提取ROI
roi = gray[y: y+h, x:x+w]
# 2.进行二值化
ret, roi_bin = cv2.threshold(roi, 10, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)

pytesseract.pytesseract.tesseract_cmd = r'D:Program FilesTesseract_OCRtesseract.exe'
print(pytesseract.image_to_string(roi, lang='chi_sim+eng', config='--psm 8 --oem 3'))

cv2.imshow('img', img)
cv2.imshow('roi_bin', roi_bin)
if cv2.waitKey(0) &amp; 0xff == 27:
    cv2.destroyAllWindows()

在这里插入图片描述
具体实现还需要进一步优化！！！

深度 学习 基础知识

深度学习是计算机视觉最为重要的方法
在这里插入图片描述

dnn实现图像 分类

在这里插入图片描述

# -*- coding: utf-8 -*-
import cv2
from cv2 import dnn
import numpy as np

# 1.导入模型，创建神经网络
# 2.读取图片，转成张量
# 3.将张量输入到网络中，并进行预测
# 4.得到结果，显示

# 导入模型，创建神经网络
config = "./bvlc_googlenet.prototxt"
model = "./bvlc_googlenet.caffemodel"
net = dnn.readNetFromCaffe(config, model)

# 读取图片，转成张量
img = cv2.imread('./smallcat.jpeg')
blob = dnn.blobFromImage(img, 1.0, (224, 224), (104, 117, 123))

# 将张量输入到网络中，并进行预测
net.setInput(blob)
r = net.forward()

# 读取类目
classes = []
path = './synset_words.txt'
with open(path, 'rt') as f:
    classes = [x [x.find(" ") + 1:] for x in f]

order = sorted(r[0], reverse=True)
z = list(range(3))

for i in list(range(0, 3)):
    z[i] = np.where(r[0] == order[i])[0][0]
    print('No.', i + 1, ' matches:', classes[z[i]], end='')
    print('category row is at:', z[i] + 1, ' ', 'posibility:', order[i])