img_gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
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)
img_gray.shape #二维(414,500)
cv2.imshow("img_gray", img_gray)
cv2.waitKey(0)
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)
hsv=cv2.cvtColor(img,cv2.COLOR_BGR2HSV)
cv2.imshow("hsv", hsv)
cv2.waitKey(0)
cv2.destroyAllWindows()
ret,dst=cv2.threshold(src,thresh,maxval,type)
dst:输出图
src:输入图,只能输入单通道,通常来说是灰度图
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)
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()
需要设置卷积内核kernel = np.ones((3,3),np.uint8)
(1)图像梯度-Sobel算子
dst = cv2.Sobel(src, ddepth, dx, dy, ksize)
img = cv2.imread('pie.png',cv2.IMREAD_GRAYSCALE)
def cv_show(img,name):
cv2.imshow(name,img)
cv2.waitKey()
cv2.destroyAllWindows()
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3)
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
sobelx = cv2.convertScaleAbs(sobelx)
cv_show(sobelx,'sobelx')
sobely = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=3)
sobely = cv2.convertScaleAbs(sobely)
cv_show(sobely,'sobely')
#分别计算x和y,再求和
sobelxy = cv2.addWeighted(sobelx,0.5,sobely,0.5,0)
cv_show(sobelxy,'sobelxy')
#不建议直接计算
sobelxy=cv2.Sobel(img,cv2.CV_64F,1,1,ksize=3)
sobelxy = cv2.convertScaleAbs(sobelxy)
cv_show(sobelxy,'sobelxy')
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)
res = np.hstack((sobelx,sobely,sobelxy))
cv_show(res,'sobel')
(2)图像梯度-Scharr算子
(3)图像梯度-laplacian算子
#不同算子的差异
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')
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)
v2=cv2.Canny(img,50,100)
res = np.hstack((v1,v2))
cv_show(res,'res')
img=cv2.imread("car.png",cv2.IMREAD_GRAYSCALE)
v1=cv2.Canny(img,120,250)
v2=cv2.Canny(img,50,100)
res = np.hstack((v1,v2))
cv_show(res,'res')
down=cv2.pyrDown(img)
up=cv2.pyrUp(img)
down=cv2.pyrDown(img)
down_up=cv2.pyrUp(down)
l_1=img-down_up
cv_show(l_1,'l_1')
cv2.findContours(img,mode,method)
(1) mode:轮廓检索模式
(2) method:轮廓逼近方法
# 为了更高的准确率,使用二值图像
"""
第一步:载入图片
第二步:使用cv2.cvtcolor() 将图片转换为灰度图
第三步: 使用cv2.threshold将图片做二值化转换
第四步:使用cv2.findContours 找出图片的轮廓值
第五步:使用cv2.drawContours在图片上画上轮廓
第六步: 使用cv2.imshow 完成画图操作
"""
def cv_show(img, name):
cv2.imshow(name, img)
cv2.waitKey(0)
cv2.destroyAllWindows()
# 第一步读入图片
img = cv2.imread('contours.png')
# 第二步:对图片做灰度变化
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 第三步:对图片做二值变化
ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
# 第四步:获得图片的轮廓值
contours, h = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
# 第五步:在图片中画出图片的轮廓值
# 参数说明,draw_img 需要作图的原始图像, contours表示轮廓, 0表示轮廓索引, (0, 0, 255)表示颜色, 2表示线条粗细
draw_img = img.copy()
ret = cv2.drawContours(draw_img, contours, -1, (0, 0, 255), 2)
# 第六步:画出带有轮廓的原始图片
cv_show(ret,'ret')
(3)轮廓特征
# 取出单个的轮廓值
cnt = contours[0]
# 第二步:计算轮廓的面积
area = cv2.contourArea(cnt)
# 第三步: 计算轮廓的周长
length= cv2.arcLength(cnt, True)
print(area, length)
(4)轮廓近似(RDP):假设存在一个曲线A, B,在曲线上存在一个C点,离AB线段的距离最远,记为d1, 如果d1 < T(自己设定的阈值), 将AB线段作为AB曲线的替代,否者连接AC和BC, 计算AC线段上的D点离AB距离最远,记为d2,如果d2 < T,则使用AC线段替代AC曲线,否者继续连接划
# 轮廓近似
img = cv2.imread('contours2.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
contours, h = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cnt = contours[0]
# 使用周长的倍数作为阈值,阈值越小,图像的轮廓近似与轮廓越近似
epsilon = 0.1 * cv2.arcLength(cnt, True)
approx = cv2.approxPolyDP(cnt, epsilon, True)
draw_img = img.copy()
ret = cv2.drawContours(draw_img, [approx], -1, (0, 0, 255), 2)
cv_show(ret, 'ret')
(5)外接矩形和外接圆
外接矩形: 使用cv2.boudingrect(cnt)获得轮廓的外接矩形,使用cv2.rectangle(img, (x, y), (x+w, y+h), (0, 0, 255), 2)画出矩阵的轮廓
外接圆: 使用cv2.minEnclosingCircle(cnt)获得轮廓的外接圆,使用cv2.circle(ret, centers, radius, (0, 0, 255), 2)画出圆的轮廓
"""
第一步:载入图片,灰度化,二值化,使用cv2.findCountors找出图像的轮廓,使用轮廓索引获得第一个轮廓cnt
第二步:使用cv2.boundingrect(cnt) ,获得轮廓的x,y,w, h (x, y)表示左上角的坐标,w为宽,h为长
第三步: 使用cv2.rectangle 绘制外接的轮廓
第四步: 使用cv2.minEnclosingCircle(cnt), 获得center和radius,即圆心点的坐标和圆的半径
第五步: 使用cv2.circle(img, center, radius, (0, 0, 255), 2) 绘制圆心的外接轮廓
"""
# 外接矩阵
img = cv2.imread('contours.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
res, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
binary, contours, h = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cnt = contours[0]
x, y, w, h = cv2.boundingRect(cnt)
ret = cv2.rectangle(img, (x, y), (x+w, y+h), (0, 0, 255), 2)
cv_show(ret, 'ret')
print('矩形面积 / 外接矩形面积', cv2.contourArea(cnt) / (w*h))
# 外接圆
(x, y), radius = cv2.minEnclosingCircle(cnt)
center = (int(x), int(y))
radius = int(radius)
ret = cv2.circle(ret, center, radius, (0, 255, 0), 2)
cv_show(ret, 'ret')
(1)傅里叶变换的作用-将图像转化为频谱
高频:变化剧烈的灰度分量,例如边界
低频:变化缓慢的灰度分量,例如一片大海
(2) 滤波
低通滤波器:只保留低频,会使得图像模糊
高通滤波器:只保留高频,会使得图像细节增强
opencv中主要就是cv2.dft()和cv2.idft(),输入图像需要先转换成np.float32 格式。
得到的结果中频率为0的部分会在左上角,通常要转换到中心位置,可以通过shift变换来实现。
cv2.dft()返回的结果是双通道的(实部,虚部),通常还需要转换成图像格式才能展示(0,255)。
import numpy as np
import cv2
from matplotlib import pyplot as plt
img = cv2.imread('lena.jpg',0)
img_float32 = np.float32(img)
dft = cv2.dft(img_float32, flags = cv2.DFT_COMPLEX_OUTPUT)
dft_shift = np.fft.fftshift(dft)
# 得到灰度图能表示的形式
magnitude_spectrum = 20*np.log(cv2.magnitude(dft_shift[:,:,0],dft_shift[:,:,1]))
plt.subplot(121),plt.imshow(img, cmap = 'gray')
plt.title('Input Image'), plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(magnitude_spectrum, cmap = 'gray')
plt.title('Magnitude Spectrum'), plt.xticks([]), plt.yticks([])
plt.show()
import numpy as np
import cv2
from matplotlib import pyplot as plt
img = cv2.imread('lena.jpg',0)
img_float32 = np.float32(img)
dft = cv2.dft(img_float32, flags = cv2.DFT_COMPLEX_OUTPUT)
dft_shift = np.fft.fftshift(dft)
rows, cols = img.shape
crow, ccol = int(rows/2) , int(cols/2) # 中心位置
# 低通滤波
mask = np.zeros((rows, cols, 2), np.uint8)
mask[crow-30:crow+30, ccol-30:ccol+30] = 1
# IDFT
fshift = dft_shift*mask
f_ishift = np.fft.ifftshift(fshift)
img_back = cv2.idft(f_ishift)
img_back = cv2.magnitude(img_back[:,:,0],img_back[:,:,1])
plt.subplot(121),plt.imshow(img, cmap = 'gray')
plt.title('Input Image'), plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(img_back, cmap = 'gray')
plt.title('Result'), plt.xticks([]), plt.yticks([])
plt.show()
img = cv2.imread('lena.jpg',0)
img_float32 = np.float32(img)
dft = cv2.dft(img_float32, flags = cv2.DFT_COMPLEX_OUTPUT)
dft_shift = np.fft.fftshift(dft)
rows, cols = img.shape
crow, ccol = int(rows/2) , int(cols/2) # 中心位置
# 高通滤波
mask = np.ones((rows, cols, 2), np.uint8)
mask[crow-30:crow+30, ccol-30:ccol+30] = 0
# IDFT
fshift = dft_shift*mask
f_ishift = np.fft.ifftshift(fshift)
img_back = cv2.idft(f_ishift)
img_back = cv2.magnitude(img_back[:,:,0],img_back[:,:,1])
plt.subplot(121),plt.imshow(img, cmap = 'gray')
plt.title('Input Image'), plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(img_back, cmap = 'gray')
plt.title('Result'), plt.xticks([]), plt.yticks([])
plt.show()