图 像 基 本 处 理 图像基本处理 图像基本处理
1：绘制线段
import numpy as np
import cv2
# 创建一张黑色的背景图
img=np.zeros((512,512,3), np.uint8)
cv2.imshow("black", img)
cv2.waitKey(0)
cv2.destroyWindow("black")
# 绘制一条线宽为5的线段
cv2.line(img,(0,0),(200,500),(0,0,255),5)
winname = 'example'
cv2.namedWindow(winname)
cv2.imshow(winname, img)
cv2.waitKey(0)
cv2.destroyWindow(winname)
2：绘制矩形
import numpy as np
import cv2
# 创建一张黑色的背景图
img=np.zeros((512,512,3), np.uint8)
# 画一个绿色边框的矩形，参数2：左上角坐标，参数3：右下角坐标
cv2.rectangle(img,(384,0),(510,128),(0,255,255),1)
winname = 'example'
cv2.namedWindow(winname)
cv2.imshow(winname, img)
cv2.waitKey(0)
cv2.destroyWindow(winname)
3：绘制圆
import numpy as np
import cv2
# 创建一张黑色的背景图
img=np.zeros((512,512,3), np.uint8)
# 画一个填充红色的圆，参数2：圆心坐标，参数3：半径
cv2.circle(img,(447,63), 63, (0,0,255), -1)
winname = 'example'
cv2.namedWindow(winname)
cv2.imshow(winname, img)
cv2.waitKey(0)
cv2.destroyWindow(winname)
4：绘制椭圆
import numpy as np
import cv2
# 创建一张黑色的背景图
img=np.zeros((512,512,3), np.uint8)
# 在图中心画一个填充的半圆
cv2.ellipse(img, (256, 256), (100, 50), 0, 30, 180, (255, 0, 0), -1)
winname = 'example'
cv2.namedWindow(winname)
cv2.imshow(winname, img)
cv2.waitKey(0)
cv2.destroyWindow(winname)
5：绘制多边形
import numpy as np
import cv2
# 创建一张黑色的背景图
img=np.zeros((512,512,3), np.uint8)
# 定义四个顶点坐标
pts = np.array([[10, 5], [50, 10], [70, 20], [20, 30]])
print(pts)
# 顶点个数：4，矩阵变成4*1*2维
pts = pts.reshape((-1, 1, 2))
print(pts)
#绘制椭圆
cv2.polylines(img, [pts], False, (0, 255, 255))
winname = 'example'
cv2.namedWindow(winname)
cv2.imshow(winname, img)
cv2.waitKey(0)
cv2.destroyWindow(winname)
6：添加文字
import numpy as np
import cv2
# 创建一张黑色的背景图
img=np.zeros((512,512,3), np.uint8)
#添加文字
font=cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(img,'OpenCV',(50,200), font, 3,(0,255,255),5)
winname = 'example'
cv2.namedWindow(winname)
cv2.imshow(winname, img)
cv2.waitKey(0)
cv2.destroyWindow(winname)
7：综合图像绘制
import numpy as np
import cv2
# 创建一张黑色的背景图
img=np.zeros((512,512,3), np.uint8)
# 绘制一条线宽为5的线段
cv2.line(img,(0,0),(511,511),(255,0,0),1)
# 画一个绿色边框的矩形，参数2：左上角坐标，参数3：右下角坐标
cv2.rectangle(img,(384,0),(510,128),(0,255,0),3)
# 画一个填充红色的圆，参数2：圆心坐标，参数3：半径
cv2.circle(img,(447,63), 63, (0,0,255), -1)
# 在图中心画一个填充的半圆
cv2.ellipse(img, (256, 256), (100, 50), 0, 0, 180, (255, 0, 0), -1)
#绘制多边形
pts=np.array([[10,5],[20,30],[70,20],[50,10]], np.int32)
pts=pts.reshape((-1,1,2))
cv2.polylines(img,[pts], True, (0,0,255),1)
# 这里 reshape 的第一个参数为-1, 表明这一维的长度是根据后面的维度的计算出来的。
#添加文字
font=cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(img,'OpenCV',(10,500), font, 4,(255,255,255),2)
winname = 'example'
cv2.namedWindow(winname)
cv2.imshow(winname, img)
cv2.waitKey(0)
cv2.destroyWindow(winname)
8：图像平移
import cv2
import numpy as np
img = cv2.imread('img2.png')
# 构造移动矩阵H
# 在x轴方向移动多少距离，在y轴方向移动多少距离
H = np.float32([[1, 0, 50], [0, 1, 25]])
rows, cols = img.shape[:2]
print(img.shape)
print(rows, cols)
# 注意这里rows和cols需要反置，即先列后行
res = cv2.warpAffine(img, H, (2*cols, 2*rows))
cv2.imshow('origin_picture', img)
cv2.imshow('new_picture', res)
cv2.waitKey(0)
cv2.destroyAllWindows()
9：图像缩放
import cv2
import numpy as np
img = cv2.imread('img2.png')
# 方法一：通过设置缩放比例，来对图像进行放大或缩小
res1 = cv2.resize(img, None, fx=2, fy=2,
interpolation=cv2.INTER_CUBIC)
height, width = img.shape[:2]
# 方法二：直接设置图像的大小，不需要缩放因子
#cv2.INTER_NEAREST（最近邻插值） cv2.INTER_AREA （区域插值） cv2.INTER_CUBIC（三次样条插值） cv2.INTER_LANCZOS4（Lanczos插值）
res2 = cv2.resize(img, (int(0.8*width), int(0.8*height)),interpolation=cv2.INTER_LANCZOS4)
cv2.imshow('origin_picture', img)
#|cv2.imshow('res1', res1)
cv2.imshow('res2', res2)
cv2.waitKey(0)
cv2.destroyAllWindows()
10：图像旋转
import cv2
import numpy as np
img=cv2.imread('img2.png',1)
rows,cols=img.shape[:2]
#参数1：旋转中心，参数2：旋转角度，参数3：缩放因子
#参数3正为逆时针，负值为正时针
M=cv2.getRotationMatrix2D((cols/2,rows/2),45,1,)
print(M)
#第三个参数是输出图像的尺寸中心
dst=cv2.warpAffine(img,M,(cols,rows))
#dst=cv2.warpAffine(img,M,(cols,rows),borderValue=(255,255,255))
while(1):
cv2.imshow('img', img)
cv2.imshow('img1',dst)
#0xFF==27 ESC
if cv2.waitKey(1)&0xFF==27:
break
cv2.destroyAllWindows()
11：仿射变换
import cv2
import numpy as np
import matplotlib.pyplot as plt
#读取图片
src = cv2.imread('bird.png')
#获取图像大小
rows, cols = src.shape[:2]
#设置图像仿射变换矩阵
pos1 = np.float32([[50,50], [200,50], [50,200]])
pos2 = np.float32([[10,100], [200,50], [100,250]])
M = cv2.getAffineTransform(pos1, pos2)
print(M)
#图像仿射变换
result = cv2.warpAffine(src, M, (2*cols, 2*rows))
#显示图像
cv2.imshow("original", src)
cv2.imshow("result", result)
#等待显示
cv2.waitKey(0)
cv2.destroyAllWindows()
12：透视变化
import cv2
import numpy as np
import matplotlib.pyplot as plt
#读取图片
src = cv2.imread('bird.png')
#获取图像大小
rows, cols = src.shape[:2]
#设置图像透视变换矩阵
pos1 = np.float32([[114, 82], [287, 156],
[8, 100], [143, 177]])
pos2 = np.float32([[0, 0], [188, 0],
[0, 262], [188, 262]])
M = cv2.getPerspectiveTransform(pos1, pos2)
#图像透视变换
result = cv2.warpPerspective(src, M, (2*cols,2*rows))
#显示图像
cv2.imshow("original", src)
cv2.imshow("result", result)
#等待显示
cv2.waitKey(0)
cv2.destroyAllWindows()
13：文档矫正
#encoding:utf-8
import cv2
import numpy as np
import matplotlib.pyplot as plt
#读取图片
src = cv2.imread('paper.png')
#获取图像大小
rows, cols = src.shape[:2]
#将源图像高斯模糊
img = cv2.GaussianBlur(src, (3,3), 0)
#进行灰度化处理
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#边缘检测（检测出图像的边缘信息）
edges = cv2.Canny(gray,50,250,apertureSize = 3)
cv2.imwrite("canny.jpg", edges)
cv2.imshow("canny", edges)
#通过霍夫变换得到A4纸边缘
lines = cv2.HoughLinesP(edges,1,np.pi/180,50,minLineLength=90,maxLineGap=10)
print(lines)
#下面输出的四个点分别为四个顶点
for x1,y1,x2,y2 in lines[0]:
print(x1,y1)
print(x2,y2)
for x3,y3,x4,y4 in lines[1]:
print(x3,y3)
print(x4,y4)
#绘制边缘
for x1,y1,x2,y2 in lines[0]:
cv2.line(gray, (x1,y1), (x2,y2), (0,0,255), 1)
#根据四个顶点设置图像透视变换矩阵
pos1 = np.float32([[114, 82], [287, 156], [8, 322], [216, 333]])
pos2 = np.float32([[0, 0], [188, 0], [0, 262], [188, 262]])
M = cv2.getPerspectiveTransform(pos1, pos2)
# pos1 = np.float32([[114, 82], [287, 156], [8, 322]])
# pos2 = np.float32([[0, 0], [188, 0], [0, 262]])
# M = cv2.getAffineTransform(pos1,pos2)
print(M)
#图像仿射变换
#result = cv2.warpAffine(src, M, (2*cols, 2*rows))
#图像透视变换
result = cv2.warpPerspective(src, M, (190, 272))
#显示图像
cv2.imshow("original", src)
cv2.imshow("result", result)
cv2.imshow("gray", gray)
#等待显示
cv2.waitKey(0)
cv2.destroyAllWindows()
14：图像几何变化
#encoding:utf-8
import cv2
import numpy as np
import matplotlib.pyplot as plt
#读取图片
img = cv2.imread('test2.png')
image = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
#图像平移矩阵
M = np.float32([[1, 0, 80], [0, 1, 30]])
rows, cols = image.shape[:2]
img1 = cv2.warpAffine(image, M, (cols, rows))
#图像缩小
img2 = cv2.resize(image, (200,100))
#图像放大
img3 = cv2.resize(image, None, fx=1.1, fy=1.1)
#绕图像的中心旋转
#源图像的高、宽 以及通道数
rows, cols, channel = image.shape
#函数参数：旋转中心 旋转度数 scale
M = cv2.getRotationMatrix2D((cols/2, rows/2), 30, 1)
#函数参数：原始图像 旋转参数 元素图像宽高
img4 = cv2.warpAffine(image, M, (cols, rows))
#图像翻转
img5 = cv2.flip(image, 0) #参数=0以X轴为对称轴翻转
img6 = cv2.flip(image, 1) #参数>0以Y轴为对称轴翻转
#图像的仿射
pts1 = np.float32([[50,50],[200,50],[50,200]])
pts2 = np.float32([[10,100],[200,50],[100,250]])
M = cv2.getAffineTransform(pts1,pts2)
img7 = cv2.warpAffine(image, M, (rows,cols))
#图像的透射
pts1 = np.float32([[56,65],[238,52],[28,237],[239,240]])
pts2 = np.float32([[0,0],[200,0],[0,200],[200,200]])
M = cv2.getPerspectiveTransform(pts1,pts2)
img8 = cv2.warpPerspective(image,M,(200,200))
#循环显示图形
titles = [ 'source', 'shift', 'reduction', 'enlarge', 'rotation', 'flipX', 'flipY', 'affine', 'transmission']
images = [image, img1, img2, img3, img4, img5, img6, img7, img8]
for i in range(9):
plt.subplot(3, 3, i+1), plt.imshow(images[i], 'gray')
plt.title(titles[i])
plt.xticks([]),plt.yticks([])
plt.show()
图像基本处理2：图像滤波&形态学操作
1. 方框滤波
import cv2
import numpy as np
img = cv2.imread('girl2.png',cv2.IMREAD_UNCHANGED)
r = cv2.boxFilter(img, -1 , (7,7) , normalize = 1)
d = cv2.boxFilter(img, -1 , (3,3) , normalize = 0)
cv2.namedWindow('img',cv2.WINDOW_AUTOSIZE)
cv2.namedWindow('r',cv2.WINDOW_AUTOSIZE)
cv2.namedWindow('d',cv2.WINDOW_AUTOSIZE)
cv2.imshow('img',img)
cv2.imshow('r',r)
cv2.imshow('d',d)
cv2.waitKey(0)
cv2.destroyAllWindows()
2.均值模糊
import cv2
import numpy as np
from matplotlib import pyplot as plt
img = cv2.imread('image/opencv.png')
cv2.imshow('img',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
blur = cv2.blur(img,(3,3 ))
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.subplot(122),plt.imshow(blur),plt.title('Blurred')
plt.xticks([]), plt.yticks([])
plt.show()
图像卷积，图像滤波
import numpy as np
import cv2 as cv
from matplotlib import pyplot as plt
img = cv.imread('./image/opencv.png')
kernel = np.ones((5,5),np.float32)/25
dst = cv.filter2D(img,-1,kernel)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(dst),plt.title('Averaging')
plt.xticks([]), plt.yticks([])
plt.show()
3.高斯模糊
import cv2 as cv
import numpy as np
from matplotlib import pyplot as plt
img = cv.imread('image/median.png')
img = cv.cvtColor(img,cv.COLOR_BGR2RGB)
blur = cv.GaussianBlur(img,(7,7),7)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(blur),plt.title('Blurred')
plt.xticks([]), plt.yticks([])
plt.show()
4.中值模糊
import cv2 as cv
import numpy as np
from matplotlib import pyplot as plt
img = cv.imread('image/median.png')
median = cv.medianBlur(img,3)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(median),plt.title('median')
plt.xticks([]), plt.yticks([])
plt.show()
5.双边滤波
关于2个sigma参数：
简单起见，可以令2个sigma的值相等； 如果他们很小（小于10），那么滤波器几乎没有什么效果； 如果他们很大（大于150），那么滤波器的效果会很强，使图像显得非常卡通化； 关于参数d：
过大的滤波器（d>5）执行效率低。 对于实时应用，建议取d=5； 对于需要过滤严重噪声的离线应用，可取d=9； d>0时，由d指定邻域直径； d<=0时，d会自动由sigmaSpace的值确定，且d与sigmaSpace成正比
import cv2
from matplotlib import pyplot as plt
img = cv2.imread('image/bilateral.png')
img = cv2.cvtColor(img,cv.COLOR_BGR2RGB)
blur = cv2.bilateralFilter(img,-1,15,10)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(blur),plt.title('Blurred')
plt.xticks([]), plt.yticks([])
plt.show()
6.图像锐化
import cv2 as cv
import numpy as np
def custom_blur_demo(image):
kernel = np.array([[0, -1, 0], [-1, 5, -1], [0, -1, 0]], np.float32) #锐化
dst = cv.filter2D(image, -1, kernel=kernel)
cv.imshow("custom_blur_demo", dst)
src = cv.imread("./image/sharpen.png")
cv.namedWindow("input image", cv.WINDOW_AUTOSIZE)
cv.imshow("input image", src)
custom_blur_demo(src)
cv.waitKey(0)
cv.destroyAllWindows()
7.直方图均衡化
#导入opencv
import cv2
#直接读为灰度图像
img = cv2.imread('./image/dark.png',0)
cv2.imshow("dark",img)
cv2.waitKey(0)
#调用cv2.equalizeHist函数进行直方图均衡化
img_equal = cv2.equalizeHist(img)
cv2.imshow("img_equal",img_equal)
cv2.waitKey(0)
cv2.destroyAllWindows()
#导入opencv
import cv2
#直接读为灰度图像
img = cv2.imread('./image/dark.png',0)
cv2.imshow("dark",img)
cv2.waitKey(0)
#调用cv2.createCLAHE函数进行局部直方图均衡化
clahe = cv2.createCLAHE(clipLimit=2,tileGridSize=(30,30))
cl1 = clahe.apply(img)
cv2.imshow("img_equal",cl1)
cv2.waitKey(0)
cv2.destroyAllWindows()
import cv2
import numpy as np
img = cv2.imread("./image/dark1.jpg")
cv2.imshow("src", img)
# 彩色图像均衡化,需要分解通道 对每一个通道均衡化
(b, g, r) = cv2.split(img)
bH = cv2.equalizeHist(b)
gH = cv2.equalizeHist(g)
rH = cv2.equalizeHist(r)
# 合并每一个通道
result = cv2.merge((bH, gH, rH))
cv2.imshow("dst", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
8.Gamma变化
import cv2
import numpy as np
img=cv2.imread('./image/dark1.jpg')
def adjust_gamma(image, gamma=1.0):
invGamma = 1.0/gamma
table = []
for i in range(256):
table.append(((i / 255.0) ** invGamma) * 255)
table = np.array(table).astype("uint8")
print(table)
return cv2.LUT(image, table)
img_gamma = adjust_gamma(img, 0.8)
#print(img_gamma)
cv2.imshow("img",img)
cv2.imshow("img_gamma",img_gamma)
cv2.waitKey(0)
cv2.destroyAllWindows()
形态学操作
1.腐蚀
import cv2
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread('./image/morphology.png')
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
kernel = np.ones((3,3),np.uint8)
erosion = cv2.erode(img,kernel,iterations = 1)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(erosion),plt.title('erosion')
plt.xticks([]), plt.yticks([])
plt.show()
#kernel = np.ones((5,5),np.uint8)
#kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (7,7))
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (7,7))
#kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,7))
print(kernel)
#!/usr/bin/env python3
import cv2
image = cv2.imread("./image/morphology.png")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv2.imshow("Gray Image", gray)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (7,7))
eroded = cv2.erode(gray.copy(), kernel, 10)
# eroded = cv2.erode(gray.copy(), None, 10)
cv2.imshow("Eroded Image", eroded)
cv2.waitKey(0)
cv2.destroyAllWindows()
2.膨胀
import cv2
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread('./image/morphology.png')
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
#kernel = np.ones((3,),np.uint8)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,7))
dilation = cv2.dilate(img,kernel,iterations = 1)
kernel1 = np.ones((7,7),np.uint8)
opening = cv2.morphologyEx(dilation,cv2.MORPH_OPEN,kernel1)
plt.subplot(121),plt.imshow(opening),plt.title('opening')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(dilation),plt.title('dilation')
plt.xticks([]), plt.yticks([])
plt.show()
3.开运算:侵蚀然后扩张的另一个名称,它对于消除噪音很有用
import cv2
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread('./image/open.png')
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
#kernel = np.ones((5,5),np.uint8)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9,9))
opening = cv2.morphologyEx(img,cv2.MORPH_OPEN,kernel)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(opening),plt.title('opening')
plt.xticks([]), plt.yticks([])
plt.show()
4.闭运算 闭运算与开运算相反，先扩张然后再侵蚀。在关闭前景对象内部的小孔或对象上的小黑点时很有用。
import cv2 as cv
import numpy as np
img = cv.imread('./image/close.png')
img = cv.cvtColor(img,cv.COLOR_BGR2RGB)
#kernel = np.ones((5,5),np.uint8)
kernel = np.ones((7,7),np.uint8)
closing = cv.morphologyEx(img,cv.MORPH_CLOSE,kernel)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(closing),plt.title('closing')
plt.xticks([]), plt.yticks([])
plt.show()
5 .形态学梯度:这是图像膨胀和腐蚀之间的区别。 结果将看起来像对象的轮廓
import cv2 as cv
import numpy as np
import matplotlib.pyplot as plt
img = cv.imread('./image/morphology.png')
img = cv.cvtColor(img,cv.COLOR_BGR2RGB)
kernel = np.ones((3,3),np.uint8)
gradient = cv.morphologyEx(img,cv.MORPH_GRADIENT,kernel)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(gradient),plt.title('gradient')
plt.xticks([]), plt.yticks([])
plt.show()
6 .顶帽: 它是输入图像和图像开运算之差。下面的示例针对9x9内核完成。
import cv2 as cv
import numpy as np
import matplotlib.pyplot as plt
img = cv.imread('./image/morphology.png')
img = cv.cvtColor(img,cv.COLOR_BGR2RGB)
kernel = np.ones((9,9),np.uint8)
tophat = cv.morphologyEx(img,cv.MORPH_TOPHAT,kernel)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(tophat),plt.title('tophat')
plt.xticks([]), plt.yticks([])
plt.show()
7.黑帽: 这是输入图像和图像闭运算之差。
import cv2 as cv
import numpy as np
import matplotlib.pyplot as plt
img = cv.imread('./image/morphology.png')
img = cv.cvtColor(img,cv.COLOR_BGR2RGB)
kernel = np.ones((9,9),np.uint8)
tophat = cv.morphologyEx(img,cv.MORPH_BLACKHAT,kernel)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(tophat),plt.title('tophat')
plt.xticks([]), plt.yticks([])
plt.show()
8.结构元素
# 矩形内核
cv.getStructuringElement(cv.MORPH_RECT,(5,5))
a = [[1, 1, 1, 1, 1],
[1, 1, 1, 1, 1],
[1, 1, 1, 1, 1],
[1, 1, 1, 1, 1],
[1, 1, 1, 1, 1]]
print(a)
# 椭圆内核
cv.getStructuringElement(cv.MORPH_ELLIPSE,(5,5))
采用按像素的方式改变图像对比度和亮度，公式如下
α调节对比度， β调节亮度
def Contrast_and_Brightness(alpha, beta, img):
blank = np.zeros(img.shape, img.dtype)
# dst = alpha * img + beta * blank
dst = cv2.addWeighted(img, alpha, blank, 1-alpha, beta)
return dst
9.调节亮度
img = cv2.imread('rgb_show.jpg')
res = img*(β)
cv2.imwrite("light_img.jpg", res)
10.调节对比度
img = cv2.imread('rgb_show.jpg')
res = img+(α)
cv2.imwrite("light_img.jpg", res)
473
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
