OpenCV完结篇——计算机视觉（人脸识别 || 车牌识别）

源代码•宸2023-12-01 21:56

文章目录


Haar人脸识别方法



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

python 复制代码 
# -*- 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) & 0xff == 27:
    cv2.destroyAllWindows()

Haar识别眼鼻口

python 复制代码 
# -*- 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) & 0xff == 27:
    cv2.destroyAllWindows()

识别嘴就会不精确了

python 复制代码 
# -*- 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) & 0xff == 27:
    cv2.destroyAllWindows()

识别鼻子

python 复制代码 
# -*- 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) & 0xff == 27:
    cv2.destroyAllWindows()

只要不测口，还是比较准确的

python 复制代码 
# -*- 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) & 0xff == 27:
    cv2.destroyAllWindows()

测口准确度太低！！！

python 复制代码 
# -*- 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) & 0xff == 27:
    cv2.destroyAllWindows()

Haar+Tesseract进行车牌识别




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！！！

python 复制代码 
# -*- 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) & 0xff == 27:
    cv2.destroyAllWindows()
python 复制代码 
# -*- 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) & 0xff == 27:
    cv2.destroyAllWindows()



python 复制代码 
# -*- 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 Files\Tesseract_OCR\tesseract.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) & 0xff == 27:
    cv2.destroyAllWindows()

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














dnn实现图像分类





python 复制代码 
# -*- 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])


之后我会持续更新，如果喜欢我的文章，请记得一键三连哦，点赞关注收藏，你的每一个赞每一份关注每一次收藏都将是我前进路上的无限动力 ！！！↖(▔▽▔)↗感谢支持！

相关推荐
陈苏同学6 分钟前
4. 将pycharm本地项目同步到(Linux)服务器上——深度学习·科研实践·从0到1
linux·服务器·ide·人工智能·python·深度学习·pycharm
吾名招财24 分钟前
yolov5-7.0模型DNN加载函数及参数详解(重要)
c++·人工智能·yolo·dnn
我是哈哈hh44 分钟前
专题十_穷举vs暴搜vs深搜vs回溯vs剪枝_二叉树的深度优先搜索_算法专题详细总结
服务器·数据结构·c++·算法·机器学习·深度优先·剪枝
鼠鼠龙年发大财1 小时前
【鼠鼠学AI代码合集#7】概率
人工智能
Tisfy1 小时前
LeetCode 2187.完成旅途的最少时间：二分查找
算法·leetcode·二分查找·题解·二分
龙的爹23331 小时前
论文 | Model-tuning Via Prompts Makes NLP Models Adversarially Robust
人工智能·gpt·深度学习·语言模型·自然语言处理·prompt
挥剑决浮云 -1 小时前
Linux 之 安装软件、GCC编译器、Linux 操作系统基础
linux·服务器·c语言·c++·经验分享·笔记
工业机器视觉设计和实现1 小时前
cnn突破四（生成卷积核与固定核对比）
人工智能·深度学习·cnn
Mephisto.java1 小时前
【力扣 | SQL题 | 每日四题】力扣2082， 2084， 2072， 2112， 180
sql·算法·leetcode
robin_suli1 小时前
滑动窗口-＞dd爱框框
算法
热门推荐
01分享几个惊艳的 Three.js 个人站点02【经验分享】Ubuntu22.04安装微信(linux官方版)032024年高教社杯数学建模国赛C题超详细解题思路分析04组基轨迹建模 GBTM的介绍与实现（Stata 或 R）05安卓系列机型永久去除data分区加密 详细步骤解析06【2024数模国赛赛题思路公开】国赛B题思路丨附可运行代码丨无偿自提07CTF网络安全大赛简单的web抓包题目：HEADache08Ubuntu24.04安装中文输入法09【2024高教社杯全国大学生数学建模竞赛】B题 生产过程中的决策问题——解题思路 代码 论文10springer 在线投稿编译踩坑