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
白光白光3 分钟前
量子神经网络
人工智能·深度学习·神经网络
yigan_Eins6 分钟前
【数论】莫比乌斯函数及其反演
c++·经验分享·算法
全域观察8 分钟前
如何复制只读模式下的腾讯文档
人工智能·新媒体运营·媒体·内容运营·程序员创富
阿史大杯茶14 分钟前
AtCoder Beginner Contest 381（ABCDEF 题）视频讲解
数据结构·c++·算法
panpantt32115 分钟前
【参会邀请】第二届大数据与数据挖掘国际会议（BDDM 2024）邀您相聚江城！
大数据·人工智能·数据挖掘
lindsayshuo24 分钟前
jetson orin系列开发版安装cuda的gpu版本的opencv
人工智能·opencv
向阳逐梦24 分钟前
ROS机器视觉入门：从基础到人脸识别与目标检测
人工智能·目标检测·计算机视觉
Mr.Q32 分钟前
OpenCV和Qt坐标系不一致问题
qt·opencv
დ旧言~44 分钟前
【高阶数据结构】图论
算法·深度优先·广度优先·宽度优先·推荐算法
张彦峰ZYF1 小时前
投资策略规划最优决策分析
分布式·算法·金融
热门推荐
01(欧拉)openEuler系统添加网卡文件配置流程、(欧拉)openEuler系统手动配置ipv6地址流程、(欧拉)openEuler系统网络管理说明02PyTorch机器学习实现液态神经网络03【HarmonyOS】HUAWEI DevEco Studio 下载地址汇总04玄机平台应急响应—webshell查杀05Coze扣子平台完整体验和实践（附国内和国际版对比）06Ubuntu 20.04使用Livox mid 360 测试 FAST_LIO07【目标跟踪】相机运动补偿08Unity中PICO实现 隔空取物 和 接触抓取物体09RAG 实践- Ollama+RagFlow 部署本地知识库10怎样让音频速度变慢？请跟随以下方法进行操作