小脑一抽去学了狗都不学的CV,几天热度到现在全是凉水
学习视频链接b站openCV
import cv2 #opencv读取的格式的RGB
import matplotlib.pyplot as plt # matplotlib的格式是RGB
import numpy as np
%matplotlib inline
img = cv2.imread('img/cat.jpg')
print(img.shape) # (414, 500, 3)
img
""
array([[[142, 151, 160],
[146, 155, 164],
[151, 160, 170],
...,
[183, 198, 200],
[128, 143, 145],
[127, 142, 144]]], dtype=uint8)
""
def cv_show(name, img):
cv2.imshow(name, img)
cv2.waitKey(0) # 等待时间,毫秒级,0表示任意键终止
cv2.destroyAllWindows()
# 灰度图
img = cv2.imread('img/cat.jpg', cv2.IMREAD_GRAYSCALE)
print(img.shape, type(img), img.size, img.dtype) # (414, 500) 207000 uint8
cv_show('image', img)
cv2.imwrite('img/mycat.jpg', img)
# 截取部分图像
cat = img[0:50, 0:200]
cv_show('cat', cat)
# 颜色通道提取
img = cv2.imread('img/cat.jpg')
b, g, r = cv2.split(img)
print(r.shape) # (414, 500)
img = cv2.merge((b, g, r))
print(img.shape) # (414, 500, 3)
# 只保留R
cur_img = img.copy()
cur_img[:,:,0] = 0
cur_img[:,:,1] = 0
cv_show('G', cur_img)
top_size, bottom_size, left_size, right_size = (50, 50, 50, 50)
replicate = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, borderType=cv2.BORDER_REPLICATE)
reflect = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, borderType=cv2.BORDER_REFLECT)
reflect101 = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, borderType=cv2.BORDER_REFLECT_101)
wrap = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, borderType=cv2.BORDER_WRAP)
constant = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, borderType=cv2.BORDER_CONSTANT, value=0)
plt.subplot(231), plt.imshow(img, 'gray'), plt.title('ORIGINAL')
plt.subplot(232), plt.imshow(replicate, 'gray'), plt.title('REPLICATE')
plt.subplot(233), plt.imshow(reflect, 'gray'), plt.title('REFLECT')
plt.subplot(234), plt.imshow(reflect101, 'gray'), plt.title('REFLECT_101')
plt.subplot(235), plt.imshow(wrap, 'gray'), plt.title('WRAP')
plt.subplot(236), plt.imshow(constant, 'gray'), plt.title('CONSTANT')
plt.show()
img_cat = cv2.imread('img/cat.jpg')
img_cat2 = img_cat + 10
print(img_cat[:5,:,0])
print(img_cat2[:5,:,0])
""
[[142 146 151 ... 156 155 154]
[108 112 118 ... 155 154 153]
[108 110 118 ... 156 155 154]
[139 141 148 ... 156 155 154]
[153 156 163 ... 160 159 158]]
[[152 156 161 ... 166 165 164]
[118 122 128 ... 165 164 163]
[118 120 128 ... 166 165 164]
[149 151 158 ... 166 165 164]
[163 166 173 ... 170 169 168]]
""
print((img_cat + img_cat2)[:5,:,0]) # 相当于% 256
print(cv2.add(img_cat, img_cat2)[:5, :, 0]) # 超过的赋值为最大值
""
[[ 38 46 56 ... 66 64 62]
[226 234 246 ... 64 62 60]
[226 230 246 ... 66 64 62]
[ 32 36 50 ... 66 64 62]
[ 60 66 80 ... 74 72 70]]
[[255 255 255 ... 255 255 255]
[226 234 246 ... 255 255 255]
[226 230 246 ... 255 255 255]
[255 255 255 ... 255 255 255]
[255 255 255 ... 255 255 255]]
""
img_cat = cv2.imread('img/cat.jpg')
img_dog = cv2.imread('img/dog.jpg')
img_cat + img_dog
""
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-30-e16b258924d3> in <module>
1 img_cat = cv2.imread('img/cat.jpg')
2 img_dog = cv2.imread('img/dog.jpg')
----> 3 img_cat + img_dog
ValueError: operands could not be broadcast together with shapes (414,500,3) (429,499,3)
""
img_dog = cv2.resize(img_dog, (500, 414))
print(img_dog.shape) # (414, 500, 3)
res = cv2.addWeighted(img_cat, 0.4, img_dog, 0.6, 0)
plt.imshow(res)
res = cv2.resize(img_cat, (0, 0), fx=4, fy=4)
plt.imshow(res)
res = cv2.resize(img, (0, 0), fx=1, fy=3)
plt.imshow(res)
# gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) # 灰度图
hsv = cv2.cvtColor(img_cat, cv2.COLOR_BGR2HSV)
plt.imshow(hsv)
ret, dst = cv2.threshold(src, thresh, maxval, type)
img_gray = cv2.cvtColor(img_cat, cv2.COLOR_BGR2GRAY)
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()
img = cv2.imread('img/lenaNoise.png')
cv_show('img', img)
# 均值滤波:简单的卷积操作
blur = cv2.blur(img, (3, 3))
cv_show('blur', blur)
# 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)
cv_show('box', box)
# 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)
cv_show('aussian', aussian)
# 中值滤波:相当于用中值代替
median = cv2.medianBlur(img, 5)
cv_show('median', median)
# 展示所有的
res = np.hstack((blur, aussian, median))
cv_show('res', res)
img = cv2.imread('img/dige.png')
cv_show('img', img)
kernal = np.ones((3, 3), np.uint8)
erosion = cv2.erode(img, kernal, iterations=1)
cv_show('erosion', erosion)
pie = cv2.imread('img/pie.png')
cv_show('pie', pie)
kernel = np.ones((30, 30),np.uint8)
erosion_1 = cv2.erode(pie, kernel, iterations = 1)
erosion_2 = cv2.erode(pie, kernel, iterations = 2)
erosion_3 = cv2.erode(pie, kernel, iterations = 3)
res = np.hstack((erosion_1 erosion_2, erosion_3))
cv_show('res', res)
img = cv2.imread('img/dige.png')
cv_show('img', img)
kernel = np.ones((3, 3), np.uint8)
dige_erosion = cv2.erode(img, kernel, iterations = 1)
dige_dilate = cv2.dilate(dige_erosion, kernel, iterations = 1) # 腐蚀膨胀后不变
cv_show('dige_dilate', dige_dilate)
pie = cv2.imread('img/pie.png')
cv_show('pie', pie)
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))
cv_show('res', res)
img = cv2.imread('img/dige.png')
kernel = np.ones((5, 5), np.uint8)
# 开:先腐蚀,再膨胀
opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)
# 闭:先膨胀,再腐蚀
closing = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel)
res = np.hstack((img, opening, closing))
cv_show('res', res)
# 梯度 = 膨胀 - 腐蚀
pie = cv2.imread('img/pie.png')
kernel = np.ones((7, 7), np.uint8)
dilate = cv2.dilate(pie, kernel, iterations = 5)
erosion = cv2.erode(pie, kernel, iterations = 5)
gradient = cv2.morphologyEx(pie, cv2.MORPH_GRADIENT, kernel)
res = np.hstack((pie, dilate, erosion, gradient))
cv_show('res', res)
img = cv2.imread('img/dige.png')
tophat = cv2.morphologyEx(img, cv2.MORPH_TOPHAT, kernel)
blackhat = cv2.morphologyEx(img, cv2.MORPH_BLACKHAT, kernel)
res = np.hstack((img, tophat, blackhat))
cv_show('res', res)
dst = cv2.Sobel(src, ddepth, dx, dy, ksize)
img = cv2.imread('img/pie.png',cv2.IMREAD_GRAYSCALE)
sobelx = cv2.Sobel(img, cv2.CV_64F, 1, 0, ksize=3)
res = np.hstack((img, sobelx))
cv_show('res', res)
# 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('img/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)
sobelxy1 = cv2.Sobel(img, cv2.CV_64F, 1, 1, ksize=3)
sobelxy1 = cv2.convertScaleAbs(sobelxy1)
res = np.hstack((sobelx, sobely, sobelxy, sobelxy1))
cv_show('res', res)
#不同算子的差异
img = cv2.imread('img/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)
img = cv2.imread("img/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("img/AM.png")
up = cv2.pyrUp(img)
down = cv2.pyrDown(img)
print(img.shape, up.shape, down.shape) # (442, 340, 3) (884, 680, 3) (221, 170, 3)
cv_show('img', img)
cv_show('up', up)
cv_show('down', down)
cv2.findContours(img, mode, method)
mode:轮廓检索模式
method:轮廓逼近方法
为了更高的准确率,使用二值图像。
img = cv2.imread('img/contours.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
cv_show('thresh',thresh)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
#传入绘制图像,轮廓,轮廓索引,颜色模式,线条厚度
draw_img = img.copy()
v1 = cv2.drawContours(draw_img, contours, -1, (0, 0, 255), 2)
v2 = cv2.drawContours(draw_img, contours, 0, (0, 0, 255), 2)
res = np.hstack((v1, v2))
cv_show('res', res)
# 轮廓特征
cnt = contours[0]
# 面积
print(cv2.contourArea(cnt)) # 8500.5
#周长,True表示闭合的
print(cv2.arcLength(cnt, True)) # 437.9482651948929
# 轮廓近似
res = cv2.drawContours(draw_img, [cnt], -1, (0, 0, 255), 2)
cv_show('res', res)
epsilon = 0.15 * cv2.arcLength(cnt, True)
approx = cv2.approxPolyDP(cnt, epsilon ,True)
res = cv2.drawContours(draw_img, [approx], -1, (0, 0, 255), 2)
cv_show('res', res)
# 边界矩形
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)
area = cv2.contourArea(cnt)
x, y, w, h = cv2.boundingRect(cnt)
rect_area = w * h
extent = float(area) / rect_area
print ('轮廓面积与边界矩形比', extent) # 轮廓面积与边界矩形比 0.5154317244724715
# 外接圆
(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)
滤波
注意:
img = cv2.imread('img/lena.jpg', 0)
img_float32 = np.float32(img)
print(img_float32.shape) # (263, 263)
dft = cv2.dft(img_float32, flags = cv2.DFT_COMPLEX_OUTPUT)
# print(dft)
dft_shift = np.fft.fftshift(dft)
# print(dft_shift)
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)
print(mask.shape) # (263, 263, 2)
mask[crow-30:crow+30, ccol-30:ccol+30] = 1
# print(mask)
# 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()
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()
vc = cv2.VideoCapture('img/test.mp4')
if vc.isOpened(): # 检查是否正确打开
open, frame = vc.read()
else:
open = False
while open:
ret, frame = vc.read()
if frame is None:
break
if ret == True:
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
cv2.imshow('res', gray)
if cv2.waitKey(10) & 0xFF == 27:
break
vc.release()
cv2.destroyAllWindows()
import cv2 # opencv读取的格式是BGR
import numpy as np
import matplotlib.pyplot as plt # Matplotlib是RGB
%matplotlib inline
def cv_show(img, name):
cv2.imshow(name,img)
cv2.waitKey()
cv2.destroyAllWindows()
cv2.calcHist(images, channels, mask, histSize, ranges)
img = cv2.imread('img/cat.jpg', 0) # 0表示灰度图
hist = cv2.calcHist([img], [0], None, [256], [0, 256])
print(hist.shape) # (256, 1)
plt.hist(img.ravel(), 256);
plt.show()
img = cv2.imread('img/cat.jpg')
color = ('b','g','r')
for i, col in enumerate(color):
histr = cv2.calcHist([img], [i], None, [256], [0, 256])
plt.plot(histr, color = col)
plt.xlim([0, 256])
# mask操作
mask = np.zeros(img.shape[:2], np.uint8)
print (mask.shape) # (414, 500)
mask[100:300, 100:400] = 255
cv_show(mask, 'mask')
img = cv2.imread('img/cat.jpg', 0)
masked_img = cv2.bitwise_and(img, img, mask=mask) #与操作
cv_show(masked_img, 'masked_img')
hist_full = cv2.calcHist([img], [0], None, [256], [0, 256])
hist_mask = cv2.calcHist([img], [0], mask, [256], [0, 256])
plt.subplot(221), plt.imshow(img, 'gray')
plt.subplot(222), plt.imshow(mask, 'gray')
plt.subplot(223), plt.imshow(masked_img, 'gray')
plt.subplot(224), plt.plot(hist_full), plt.plot(hist_mask)
plt.xlim([0, 256])
plt.show()
img = cv2.imread('img/clahe.jpg', 0)
plt.hist(img.ravel(), 256)
plt.show()
equ = cv2.equalizeHist(img)
plt.hist(equ.ravel(), 256)
plt.show()
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
res_clahe = clahe.apply(img)
res = np.hstack((img, equ, res_clahe))
cv_show(res,'res')
import numpy as np
import cv2
import argparse
# 设置参数
ap = argparse.ArgumentParser()
ap.add_argument('-i', '--image', required=True, default='img/credit_card_01.png', help='path to input image')
ap.add_argument('-t', '--template', required=True, default='img/ocr_a_reference.png', help='path to template OCR-A image')
args = vars(ap.parse_args())
# 绘图展示
def cv_show(name, img):
cv2.imshow(name, img)
cv2.waitKey(0)
cv2.destroyAllWindows()
img = cv2.imread('img/credit_card_01.png')
cv_show('img', img)
# 灰度图
ref = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
cv_show('ref', ref)
# 二值图像
ref = cv2.threshold(ref, 10, 255, cv2.THRESH_BINARY_INV)[1]
cv_show('ref', ref)
返回的list中每个元素都是图像中的一个轮廓
refCnts, hierarchy = cv2.findContours(ref.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(img, refCnts, -1, (0, 0, 255), 3)
cv_show('img', img)
print(np.array(refCnts).shape)
refCnts