特别提醒:
opencv的版本问题:建议使用cv2的 '3.4.2'的版本
因为在3.4版本之后,因为sift的算法申请专利,如无法使用该函数
sift = cv2.xfeatures2d.SIFT_create()
基础知识部分
1.图像的组成与读取
import cv2 #opencv读取的格式是BGR import numpy as np import matplotlib.pyplot as plt#Matplotlib是RGB %matplotlib inline img=cv2.imread('cat.jpg') img_gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)###转化为灰度图 img_gray.shape (414, 500)
cv2.imshow("img_gray", img_gray)##画图 cv2.waitKey(0) ##窗口等待时间 cv2.destroyAllWindows()
- H - 色调(主波长)。 - S - 饱和度(纯度/颜色的阴影)。 - V值(强度)
hsv=cv2.cvtColor(img,cv2.COLOR_BGR2HSV)##色彩转化 cv2.imshow("hsv", hsv) cv2.waitKey(0) cv2.destroyAllWindows()
##图像阈值
ret, dst = cv2.threshold(src, thresh, maxval, type)
- ret:输入的thresh - src: 输入图,只能输入单通道图像,通常来说为灰度图 - dst: 输出图 - thresh: 阈值 - maxval: 当像素值超过了阈值(或者小于阈值,根据type来决定),所赋予的值 - type:二值化操作的类型,包含以下5种类型: cv2.THRESH_BINARY; cv2.THRESH_BINARY_INV; cv2.THRESH_TRUNC; cv2.THRESH_TOZERO;cv2.THRESH_TOZERO_INV - cv2.THRESH_BINARY 超过阈值部分取maxval(最大值),否则取0 - cv2.THRESH_BINARY_INV THRESH_BINARY的反转 - cv2.THRESH_TRUNC 大于阈值部分设为阈值,否则不变 - cv2.THRESH_TOZERO 大于阈值部分不改变,否则设为0 - cv2.THRESH_TOZERO_INV THRESH_TOZERO的反转
ret, thresh1 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_BINARY) ret, thresh2 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_BINARY_INV) ret, thresh3 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TRUNC) ret, thresh4 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TOZERO) ret, thresh5 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TOZERO_INV) print(ret) titles = ['Original Image', 'BINARY', 'BINARY_INV', 'TRUNC', 'TOZERO', 'TOZERO_INV'] images = [img, thresh1, thresh2, thresh3, thresh4, thresh5] for i in range(6): plt.subplot(2, 3, i + 1), plt.imshow(images[i], 'gray') plt.title(titles[i]) plt.xticks([]), plt.yticks([]) plt.show()
滤波操作,除噪,这一个滤波
img = cv2.imread('lenaNoise.png') cv2.imshow('img', img) cv2.waitKey(0) cv2.destroyAllWindows()
# 均值滤波 # 简单的平均卷积操作 blur = cv2.blur(img, (3, 3)) cv2.imshow('blur', blur) cv2.waitKey(0) cv2.destroyAllWindows()
# 方框滤波 # 基本和均值一样,可以选择归一化 box = cv2.boxFilter(img,-1,(3,3), normalize=True) cv2.imshow('box', box) cv2.waitKey(0) cv2.destroyAllWindows()
# 高斯滤波 # 高斯模糊的卷积核里的数值是满足高斯分布,相当于更重视中间的 aussian = cv2.GaussianBlur(img, (5, 5), 1) cv2.imshow('aussian', aussian) cv2.waitKey(0) cv2.destroyAllWindows()
# 中值滤波 # 相当于用中值代替 median = cv2.medianBlur(img, 5) # 中值滤波 cv2.imshow('median', median) cv2.waitKey(0) cv2.destroyAllWindows()
##滤波操作的原理:
利用卷积核,将像素点在卷积内计算,然后平铺图像,从而将噪点清除。
形态学操作:膨胀和腐蚀
原始图像:
腐蚀操作:
kernel = np.ones((3,3),np.uint8) erosion = cv2.erode(img,kernel,iterations = 1) cv2.imshow('erosion', erosion) cv2.waitKey(0) cv2.destroyAllWindows()
腐蚀主要就是调用cv2.erode(img,kernel,iterations),这个函数的参数是
第一个参数:img指需要腐蚀的图
第二个参数:kernel指腐蚀操作的内核,默认是一个简单的3X3矩阵,我们也可以利用getStructuringElement()函数指明它的形状
第三个参数:iterations指的是腐蚀次数,省略是默认为1
下面从多个iterations了解腐蚀的作用:
原图
经过腐蚀的效果:
膨胀之前的原图:
img = cv2.imread('dige.png') cv2.imshow('img', img) cv2.waitKey(0) cv2.destroyAllWindows()
先进行腐蚀,去毛边
kernel = np.ones((3,3),np.uint8) dige_erosion = cv2.erode(img,kernel,iterations = 1) cv2.imshow('erosion', erosion) cv2.waitKey(0) cv2.destroyAllWindows()
再进行膨胀 kernel = np.ones((3,3),np.uint8) dige_dilate = cv2.dilate(dige_erosion,kernel,iterations = 1) cv2.imshow('dilate', dige_dilate) cv2.waitKey(0) cv2.destroyAllWindows()
pie = cv2.imread('pie.png') kernel = np.ones((30,30),np.uint8) dilate_1 = cv2.dilate(pie,kernel,iterations = 1) dilate_2 = cv2.dilate(pie,kernel,iterations = 2) dilate_3 = cv2.dilate(pie,kernel,iterations = 3) res = np.hstack((dilate_1,dilate_2,dilate_3)) cv2.imshow('res', res) cv2.waitKey(0) cv2.destroyAllWindows()
##开运算,先腐蚀,再膨胀
# 开:先腐蚀,再膨胀 img = cv2.imread('dige.png') kernel = np.ones((5,5),np.uint8) opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel) cv2.imshow('opening', opening) cv2.waitKey(0) cv2.destroyAllWindows()
##闭:先膨胀,再腐蚀
# 梯度=膨胀-腐蚀 pie = cv2.imread('pie.png') kernel = np.ones((7,7),np.uint8) dilate = cv2.dilate(pie,kernel,iterations = 5) erosion = cv2.erode(pie,kernel,iterations = 5) res = np.hstack((dilate,erosion)) cv2.imshow('res', res) cv2.waitKey(0) cv2.destroyAllWindows()
gradient = cv2.morphologyEx(pie, cv2.MORPH_GRADIENT, kernel) cv2.imshow('gradient', gradient) cv2.waitKey(0) cv2.destroyAllWindows()
礼帽与黑帽:
礼帽:原始输入-开运算结果
黑帽 = 闭运算-原始输入
#礼帽 img = cv2.imread('dige.png') tophat = cv2.morphologyEx(img, cv2.MORPH_TOPHAT, kernel) cv2.imshow('tophat', tophat) cv2.waitKey(0) cv2.destroyAllWindows()
#黑帽 img = cv2.imread('dige.png') blackhat = cv2.morphologyEx(img,cv2.MORPH_BLACKHAT, kernel) cv2.imshow('blackhat ', blackhat ) cv2.waitKey(0) cv2.destroyAllWindows()
图像梯度:
图像梯度-Sobel算子
img = cv2.imread('pie.png',cv2.IMREAD_GRAYSCALE) cv2.imshow("img",img) cv2.waitKey() cv2.destroyAllWindows()
dst = cv2.Sobel(src, ddepth, dx, dy, ksize) - ddepth:图像的深度 - dx和dy分别表示水平和竖直方向 - ksize是Sobel算子的大小
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3)##规则是右减左 cv_show(sobelx,'sobelx')
白到黑是正数,黑到白就是负数了,所有的负数会被截断成0,所以要取绝对值,才能得到完整的x轴的梯度
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3) sobelx = cv2.convertScaleAbs(sobelx) cv_show(sobelx,'sobelx')
同理y轴也相同
分别计算x和y轴,再求和获得的轮廓更加完整
sobelxy = cv2.addWeighted(sobelx,0.5,sobely,0.5,0) cv_show(sobelxy,'sobelxy')
这是直接计算的结果
根据现实的图片,来了解sobel的轮廓效果。
img = cv2.imread('lena.jpg',cv2.IMREAD_GRAYSCALE) cv_show(img,'img')
img = cv2.imread('lena.jpg',cv2.IMREAD_GRAYSCALE) sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3) sobelx = cv2.convertScaleAbs(sobelx) sobely = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=3) sobely = cv2.convertScaleAbs(sobely) sobelxy = cv2.addWeighted(sobelx,0.5,sobely,0.5,0) cv_show(sobelxy,'sobelxy')
三种算子不同的区别
img = cv2.imread('lena.jpg',cv2.IMREAD_GRAYSCALE) sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3) sobely = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=3) sobelx = cv2.convertScaleAbs(sobelx) sobely = cv2.convertScaleAbs(sobely) sobelxy = cv2.addWeighted(sobelx,0.5,sobely,0.5,0) scharrx = cv2.Scharr(img,cv2.CV_64F,1,0) scharry = cv2.Scharr(img,cv2.CV_64F,0,1) scharrx = cv2.convertScaleAbs(scharrx) scharry = cv2.convertScaleAbs(scharry) scharrxy = cv2.addWeighted(scharrx,0.5,scharry,0.5,0) laplacian = cv2.Laplacian(img,cv2.CV_64F) laplacian = cv2.convertScaleAbs(laplacian) res = np.hstack((sobelxy,scharrxy,laplacian)) cv_show(res,'res')
边缘检测:
### Canny边缘检测 - 1) 使用高斯滤波器,以平滑图像,滤除噪声。 - 2) 计算图像中每个像素点的梯度强度和方向。 - 3) 应用非极大值(Non-Maximum Suppression)抑制,以消除边缘检测带来的杂散响应。 - 4) 应用双阈值(Double-Threshold)检测来确定真实的和潜在的边缘。 - 5) 通过抑制孤立的弱边缘最终完成边缘检测。
img=cv2.imread("lena.jpg",cv2.IMREAD_GRAYSCALE) v1=cv2.Canny(img,80,150)#过滤多
参数中指定就好最大值和最小值,根据最大值和最小值之间的差决定过滤量的多少 v2=cv2.Canny(img,50,100)#过滤少 res = np.hstack((v1,v2)) cv_show(res,'res')
##轮廓检测
mode:轮廓检索模式 - RETR_EXTERNAL :只检索最外面的轮廓; - RETR_LIST:检索所有的轮廓,并将其保存到一条链表当中; - RETR_CCOMP:检索所有的轮廓,并将他们组织为两层:顶层是各部分的外部边界,第二层是空洞的边界; - RETR_TREE:检索所有的轮廓,并重构嵌套轮廓的整个层次; method:轮廓逼近方法 - CHAIN_APPROX_NONE:以Freeman链码的方式输出轮廓,所有其他方法输出多边形(顶点的序列)。 - CHAIN_APPROX_SIMPLE:压缩水平的、垂直的和斜的部分,也就是,函数只保留他们的终点部分。
轮廓检测预处理三部,读图像,灰度图,二值化,且通常使用mode的RETR_TREE
img = cv2.imread('contours.png') gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY) cv_show(thresh,'thresh')
binary, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE) #%% md 绘制轮廓 #%% cv_show(img,'img') #%% #传入绘制图像,轮廓,轮廓索引,颜色模式,线条厚度 # 注意需要copy,要不原图会变。。。 draw_img = img.copy() res = cv2.drawContours(draw_img, contours, -1, (0, 0, 255), 2)###-1表示检测所有轮廓,2 cv_show(res,'res')
img = cv2.imread('contours2.png') gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY) binary, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE) cnt = contours[0] draw_img = img.copy() res = cv2.drawContours(draw_img, [cnt], -1, (0, 0, 255), 2) cv_show(res,'res')
轮廓近似:
epsilon = 0.15*cv2.arcLength(cnt,True) approx = cv2.approxPolyDP(cnt,epsilon,True)##轮廓近似 draw_img = img.copy() res = cv2.drawContours(draw_img, [approx], -1, (0, 0, 255), 2) cv_show(res,'res')
边界矩形:
img = cv2.imread('contours.png') gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY) binary, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE) cnt = contours[0] x,y,w,h = cv2.boundingRect(cnt) img = cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2) cv_show(img,'img')
(x,y),radius = cv2.minEnclosingCircle(cnt) center = (int(x),int(y)) radius = int(radius) img = cv2.circle(img,center,radius,(0,255,0),2) cv_show(img,'img')