opencv-python图像增强解读

import numpy as np
import cv2 as cv
img = cv.imread('1.jpg')
res = cv.resize(img,None,fx=2, fy=2, interpolation = cv.INTER_CUBIC)
#或者
height, width = img.shape[:2]
res = cv.resize(img,(2*width, 2*height), interpolation = cv.INTER_CUBIC)

import cv2 as cv
import numpy as np
img = cv.imread(image_path, cv.IMREAD_COLOR)
# 上下翻转
dst1 = cv.flip(img, 0)
res1 = np.vstack((img, dst1))
# 左右翻转
dst2 = cv.flip(img, 1)
res2 = np.vstack((img, dst2))
# 对角线翻转
dst3 = cv.flip(img, -1)
res3 = np.vstack((img, dst3))

img=cv2.imread('yun.jpg',cv2.IMREAD_GRAYSCALE)
cv2.imwrite('yun.jpg',img)
#原图的宽高
h,w=img.shape[:2]
#仿射变换矩阵 缩小2倍
A1=np.array([[0.5,0,0],[0,0.5,0]],np.float32)
A2=cv2.warpAffine(img,A1,(w,h),borderValue=126)
#缩小后平移
B1=np.array([[0.5,0,w/4],[0,0.5,h/4]],np.float32)
B2=cv2.warpAffine(img,B1,(w,h),borderValue=126)
#使图像旋转
C1=cv2.getRotationMatrix2D((w/2.0,h/2.0),30,1)
C2=cv2.warpAffine(img,C1,(w,h),borderValue=126)

import cv2 as cv
# 高斯金字塔
def pyramid_demo(image):
    level = 3  # 金字塔层数
    temp = image.copy()
    pyramid_images = []
    for i in range(level):
        dst = cv.pyrDown(temp)       # 降采样
        pyramid_images.append(dst)   # 降采样的结果添加进列表
        cv.imshow('pyramid_down' + str(i), dst)   # 金字塔第几层  imshow
        temp = dst.copy()            # 采样的图像又赋给temp  接着降采样
    return pyramid_images
# 拉普拉斯金字塔
# 由高斯金字塔可以构建拉普拉斯金字塔
def lapalian_demo(image):
    pyramid_images = pyramid_demo(image)
    level = len(pyramid_images)         # 求层数
    for i in range(level - 1, -1, -1):  # 每次递减
        if (i - 1) < 0:
            expand = cv.pyrUp(pyramid_images[i], dstsize=image.shape[:2])  # 升采样
            lpls = cv.subtract(image, expand)
            cv.imshow("lapalian_down" + str(i), lpls)
        else:
            expand = cv.pyrUp(pyramid_images[i], dstsize=pyramid_images[i - 1].shape[:2])
            lpls = cv.subtract(pyramid_images[i - 1], expand)
            cv.imshow("lapalian_down_" + str(i), lpls)

import cv2
import numpy as np
#读取图像信息
k = 5
img0 = cv2.imread("1.jpg")
img1 = cv2.cvtColor(img0, cv2.COLOR_BGR2GRAY)
h, w = img0.shape[:2]
r5=cv2.blur(img1,(k,k)) #5*5卷积

import cv2
import matplotlib.pyplot as plt
# 读取图片
img = cv2.imread('1.jpg')
# 方框滤波，True表示归一化，则效果与均值滤波相同。
result = cv2.boxFilter(source, -1, (5, 5), normalize=False)
# sqrBoxFilter实现对每个像素值的平方求和
# result1 = cv2.sqrBoxFilter(source, -1, (5, 5), normalize=True)

import cv2
k = 5
img=cv2.imread('1.jpg')
#(5, 5)表示高斯矩阵的长与宽都是5，标准差取0
blur=cv2.GaussianBlur(img,(k,k),0)

import cv2
k = 5
img=cv2.imread('1.jpg')
#常用来去除椒盐噪声
#卷积核使用奇数
blur=cv2.medianBlur(img,k)

#cv2.bilateralFilter(src, d, sigmaColor, sigmaSpace[, dst[, borderType]])
#能在保持边界清晰的情况下有效的去除噪音
#但是这种操作与其他滤波器相比会比较慢
import cv2
img=cv2.imread('1.jpg')
#cv2.bilateralFilter(src, d, sigmaColor, sigmaSpace)
#9 邻域直径，两个75分别是空间高斯函数标准差，灰度值相似性高斯函数标准差
blur = cv2.bilateralFilter(img,9,75,75)

#OpenCV实现
dft = cv2.dft(np.float32(img2), flags = cv2.DFT_COMPLEX_OUTPUT)
dft_shift = np.fft.fftshift(dft)
magnitude_spectrum1 = 20*np.log(cv2.magnitude(dft_shift[:, :, 0], dft_shift[:, :, 1]))
plt.subplot(121), plt.imshow(img2, cmap = 'gray')
plt.title('原图'), plt.xticks([]), plt.yticks([])
plt.subplot(122), plt.imshow(magnitude_spectrum1, cmap = 'gray')
plt.title('频谱图'), plt.xticks([]), plt.yticks([])
plt.show()

import cv2
img0 = cv2.imread("1.jpg")
img1 = cv2.cvtColor(img0, cv2.COLOR_BGR2GRAY)
erosion1 = cv2.erode(img1, kernel1)

import cv2
img0 = cv2.imread("1.jpg")
img1 = cv2.cvtColor(img0, cv2.COLOR_BGR2GRAY)
dilation1 = cv2.dilate(img1, kernel1) 

import cv2
import numpy as np
ori = cv2.imread(r"1.jpg")
k = np.ones((10, 10), np.uint8)
opening = cv2.morphologyEx(ori, cv2.MORPH_OPEN,k)       # 开运算

import cv2
import numpy as np
ori = cv2.imread(r"1.jpg")
k1 = np.ones((8, 8), np.uint8)
k2 = np.ones((15, 15), np.uint8)
closing1 = cv2.morphologyEx(ori, cv2.MORPH_CLOSE, k1)
closing2 = cv2.morphologyEx(ori, cv2.MORPH_CLOSE, k2)

import cv2
import numpy as np
ori = cv2.imread(r"1.jpg")
result=cv2.morphologyEx(ori, cv2.MORPH_GRADIENT, kernel)

import cv2
import numpy as np
ori = cv2.imread(r"1.jpg")
result=cv2.morphologyEx(ori, cv2.MORPH_TOPHAT, kernel)

import cv2
import numpy as np
ori = cv2.imread(r"1.jpg")
result=cv2.morphologyEx(ori, cv2.MORPH_BLACKHAT, kernel)

import cv2
import numpy as np
from matplotlib import pyplot as plt
'''
calcHist-计算图像直方图
函数原型：calcHist(images,channels,mask,histSize,ranges,hist=None,accumulate=None)
images：图像矩阵，例如：[image]
channels：通道数，例如：0
mask：掩膜，一般为：None
histSize：直方图大小，一般等于灰度级数
ranges：横轴范围
'''
# 获取灰度图像
img = cv2.imread("1.jpg", 0)
# 灰度图像的直方图
hist = cv2.calcHist([img],[0],None,[256],[0,256])
plt.figure()#新建一个图像
plt.title("Grayscale Histogram")
plt.xlabel("Bins")#X轴标签
plt.ylabel("# of Pixels")#Y轴标签
plt.plot(hist)
plt.xlim([0,256])#设置x坐标轴范围
plt.show()
'''
equalizeHist—直方图均衡化
函数原型： equalizeHist(src, dst=None)
src：图像矩阵(单通道图像)
dst：默认即可
'''
# 灰度图像直方图均衡化
dst = cv2.equalizeHist(img)
# 直方图
hist = cv2.calcHist([dst],[0],None,[256],[0,256])
plt.figure()
plt.hist(dst.ravel(), 256)
plt.show()
cv2.imshow("Histogram Equalization",np.hstack([img, dst]))
cv2.waitKey(0)

# 彩色图像直方图均衡化
img = cv2.imread("1.jpg", 1)
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_rgb", result)
cv2.waitKey(0)

import cv2
#分道计算每个通道的直方图
img0 = cv2.imread('12.jpg')
hist_b = cv2.calcHist([img0],[0],None,[256],[0,256])
hist_g = cv2.calcHist([img0],[1],None,[256],[0,256])
hist_r = cv2.calcHist([img0],[2],None,[256],[0,256])
def gamma_trans(img,gamma):
	#具体做法先归一化到1，然后gamma作为指数值求出新的像素值再还原
	gamma_table = [np.power(x/255.0,gamma)*255.0 for x in range(256)]
	gamma_table = np.round(np.array(gamma_table)).astype(np.uint8)
	#实现映射用的是Opencv的查表函数
	return cv2.LUT(img0,gamma_table)
img0_corrted = gamma_trans(img0, 0.5)
cv2.imshow('img0',img0)
cv2.imshow('gamma_image',img0_corrted)
cv2.imwrite('gamma_image.png',img0_corrted)
#分通道计算Gamma校正后的直方图
hist_b_c =cv2.calcHist([img0_corrted],[0],None,[256],[0,256])
hist_g_c =cv2.calcHist([img0_corrted],[1],None,[256],[0,256])
hist_r_c =cv2.calcHist([img0_corrted],[2],None,[256],[0,256])
fig = plt.figure('gamma')
pix_hists = [[hist_b, hist_g, hist_r],
    [hist_b_c, hist_g_c, hist_r_c]]
pix_vals = range(256)
for sub_plt, pix_hist in zip([121, 122], pix_hists):
	ax = fig.add_subplot(sub_plt, projection='3d')
	for c, z, channel_hist in zip(['b', 'g', 'r'], [20, 10, 0], pix_hist):
  		cs = [c] * 256
  		ax.bar(pix_vals, channel_hist, zs=z, zdir='y', color=cs, alpha=0.618, edgecolor='none', lw=0)
	ax.set_xlabel('Pixel Values')
	ax.set_xlim([0, 256])
	ax.set_ylabel('Count')
	ax.set_zlabel('Channels')
plt.show()
cv2.waitKey()