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
千金裘换酒2 小时前
LeetCode 移动零元素 快慢指针
算法·leetcode·职场和发展
北辰alk2 小时前
RAG索引流程详解：如何高效解析文档构建知识库
人工智能
九河云2 小时前
海上风电“AI偏航对风”：把发电量提升2.1%，单台年增30万度
大数据·人工智能·数字化转型
wm10432 小时前
机器学习第二讲 KNN算法
人工智能·算法·机器学习
NAGNIP2 小时前
一文搞懂机器学习线性代数基础知识！
算法
NAGNIP2 小时前
机器学习入门概述一览
算法
沈询-阿里2 小时前
Skills vs MCP：竞合关系还是互补？深入解析Function Calling、MCP和Skills的本质差异
人工智能·ai·agent·ai编程
xiaobai1782 小时前
测试工程师入门AI技术 - 前序：跨越焦虑，从优势出发开启学习之旅
人工智能·学习
北岛寒沫2 小时前
北京大学国家发展研究院 经济学原理课程笔记（第二十一课 金融学基础）
经验分享·笔记·学习
盛世宏博北京3 小时前
云边协同・跨系统联动：智慧档案馆建设与功能落地
大数据·人工智能
热门推荐
01GitHub 镜像站点02安娜的档案(Anna’s Archive) 镜像网站/国内最新可访问入口（持续更新）03Linux下V2Ray安装配置指南04Labelme从安装到标注：零基础完整指南05jdk21下载、安装（Windows、Linux、macOS）06【踩坑笔记】50系显卡适配的 PyTorch 安装07手把手教你通过Gemini3 pro 学生认证，白用一年，手慢无！08Opencode CLI 安装成功,但是启动失败09GitLab 零基础入门指南：从安装到项目管理全流程10Claude Code Plan 模式完全指南：从入门到精通