3. 灰度级分层
代码:
import cv2
import imutils
import numpy as np
# 在某一范围(A, B)突出灰度,其他灰度值保持不变
image = cv2.imread('E:/city.PNG')
gray_img = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
r_left, r_right = 150, 230
r_min, r_max = 0, 255
level_img = np.zeros((gray_img.shape[0], gray_img.shape[1]), dtype=np.uint8)
for i in range(gray_img.shape[0]):
for j in range(gray_img.shape[1]):
if r_left <= gray_img[i, j] <= r_right:
level_img[i, j] = r_max
else:
level_img[i, j] = gray_img[i, j]
cv2.imshow('origin image', imutils.resize(image, 480))
cv2.imshow('level image', imutils.resize(level_img, 480))
if cv2.waitKey(0) == 27:
cv2.destroyAllWindows()
效果:
4. 幂律变换
代码:
import math
import numpy as np
import cv2
import imutils
# #幂律变换 φ>1
# # image = cv2.imread('E:/1.png')
image = cv2.imread('E:/1.png')
gamma_img1 = np.zeros((image.shape[0], image.shape[1], 3), dtype=np.float32)
for i in range(image.shape[0]):
for j in range(image.shape[1]):
gamma_img1[i, j, 0] = math.pow(image[i, j, 0], 5)
gamma_img1[i, j, 1] = math.pow(image[i, j, 1], 5)
gamma_img1[i, j, 2] = math.pow(image[i, j, 2], 5)
cv2.normalize(gamma_img1, gamma_img1, 0, 255, cv2.NORM_MINMAX)
gamma_img1 = cv2.convertScaleAbs(gamma_img1)
cv2.imshow('image', imutils.resize(image, 400))
cv2.imshow('gamma1 transform', imutils.resize(gamma_img1, 400))
if cv2.waitKey(0) == 27:
cv2.destroyAllWindows()
#幂律变换,φ<1
# image = cv2.imread('E:/1.png')
image = cv2.imread('E:/city.png')
gamma_img2 = np.zeros((image.shape[0], image.shape[1], 3), dtype=np.float32)
for i in range(image.shape[0]):
for j in range(image.shape[1]):
gamma_img2[i, j, 0] = math.pow(image[i, j, 0], 0.4)
gamma_img2[i, j, 1] = math.pow(image[i, j, 1], 0.4)
gamma_img2[i, j, 2] = math.pow(image[i, j, 2], 0.4)
cv2.normalize(gamma_img2, gamma_img2, 0, 255, cv2.NORM_MINMAX)
gamma_img2 = cv2.convertScaleAbs(gamma_img2)
cv2.imshow('image', imutils.resize(image, 400))
cv2.imshow('gamma2 transform', imutils.resize(gamma_img2, 400))
if cv2.waitKey(0) == 27:
cv2.destroyAllWindows()
效果:
5. 阈值处理
代码:
import cv2
import imutils
import numpy as np
image = cv2.imread('E:/1.png')
gray_img = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
#阈值处理函数:当r1=r2, s1=0, s2=L-1时,此时分段线性函数便是阈值处理函数
plist = []
for i in range(gray_img.shape[0]):
for j in range(gray_img.shape[1]):
plist.append(gray_img[i, j])
r_avg = int(sum(plist)/len(plist))
thresh_img = np.zeros((gray_img.shape[0], gray_img.shape[1]), dtype=np.uint8)
for i in range(gray_img.shape[0]):
for j in range(gray_img.shape[1]):
if gray_img[i, j] < r_avg:
thresh_img[i, j] = 0
else:
thresh_img[i, j] = 255
cv2.imshow('origin image', imutils.resize(image, 480))
cv2.imshow('thresh image', imutils.resize(thresh_img, 480))
if cv2.waitKey(0) == 27:
cv2.destroyAllWindows()
效果:
6. 直方图均衡化
代码:
import cv2
import imutils
import numpy as np
import matplotlib.pyplot as plt
wiki_img=cv2.imread('E:/1.PNG')
wiki_gray=cv2.cvtColor(wiki_img,cv2.COLOR_BGR2GRAY)
#对图像进行均衡化处理,增强图像对比度
wiki_equ=cv2.equalizeHist(wiki_gray)
hist=cv2.calcHist([wiki_gray],[0],None,[256],[0,256])
equ_hist=cv2.calcHist([wiki_equ],[0],None,[256],[0,256])
fig=plt.figure()
ax1=fig.add_subplot(1,2,1)
ax1.plot(hist)
ax2=fig.add_subplot(1,2,2)
ax2.plot(equ_hist)
plt.show()
cv2.imshow('wiki_origin',imutils.resize(wiki_img,400))
cv2.imshow('wiki_gray',imutils.resize(wiki_gray,400))
cv2.imshow('wiki_equ',imutils.resize(wiki_equ,400))
if cv2.waitKey(0)==27:
cv2.destroyAllWindows()
效果:
7. 均值滤波器
代码:
import cv2
import copy
import random
import imutils
import numpy as np
img=cv2.imread('E:/1.PNG')
gray_img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#利用OpenCV提供函数实现均值滤波
blur_img=cv2.blur(gray_img,(3,3))
#在灰度图上手动实现均值滤波器
gray_avg_img=copy.deepcopy(gray_img) #在复制图像上修改,首先复制一份
for i in range(1,gray_img.shape[0]-1):
for j in range(1,gray_img.shape[1]-1):
sum_pix=sum([gray_img[l,k] for l in range(i-1,i+2) for k in range(j-1,j+2)]) #range函数写到i+2实际遍历到i+1,j+1同理
gray_avg_img[i,j]=int(sum_pix/9) #9个点求和除均值,均值滤波实现
#在RGB彩色图上手动实现均值滤波
rgb_avg_img=copy.deepcopy(img)
for i in range(1,img.shape[0]-1):
for j in range(1,img.shape[1]-1): #RGB三个通道,实现三次
sum_b_pix=sum([img[l,k,0] for l in range(i-1,i+2) for k in range(j-1,j+2)])
sum_g_pix = sum([img[l, k, 1] for l in range(i - 1, i + 2) for k in range(j - 1, j + 2)])
sum_r_pix = sum([img[l, k, 2] for l in range(i - 1, i + 2) for k in range(j - 1, j + 2)])
rgb_avg_img[i,j]=[int(sum_b_pix/9),int(sum_g_pix/9),int(sum_r_pix/9)]
cv2.imshow('origin image',imutils.resize(img,500))
cv2.imshow('gray image',imutils.resize(gray_img,500))
cv2.imshow('blur image',imutils.resize(blur_img,500))
cv2.imshow('gray average image',imutils.resize(gray_avg_img,500))
cv2.imshow('rgb average image',imutils.resize(rgb_avg_img,500))
if cv2.waitKey(0) == 27:
cv2.destroyAllWindows()
效果:
8. 最大、最小、中值滤波器
代码:
import cv2
import copy
import random
import imutils
import numpy as np
img=cv2.imread('E:/1.PNG')
gray_img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#给灰度图像自动添加椒盐噪声
pepper_img=copy.deepcopy(gray_img)
for i in range(gray_img.shape[0]):
for j in range(gray_img.shape[1]):
if random.randint(0,20)==0:
pix=random.randint(250,255)
pepper_img[i,j]=pix
#opencv提供CV2.medianBlur()函数实现中值滤波
blur_img=cv2.medianBlur(pepper_img,5)
#自实现中值滤波
temp_arr=np.zeros((9))
median_img=copy.deepcopy(pepper_img)
max_img=copy.deepcopy(pepper_img)
min_img=copy.deepcopy(pepper_img)
for i in range(1,pepper_img.shape[0]-1): #九个数字全部提取出来
for j in range(1,pepper_img.shape[1]-1):
temp_arr[0] = pepper_img[i - 1, j - 1]
temp_arr[1] = pepper_img[i - 1, j]
temp_arr[2] = pepper_img[i - 1, j + 1]
temp_arr[3] = pepper_img[i - 1, j - 1]
temp_arr[4] = pepper_img[i, j - 1]
temp_arr[5] = pepper_img[i, j]
temp_arr[6] = pepper_img[i, j + 1]
temp_arr[7] = pepper_img[i + 1, j - 1]
temp_arr[8] = pepper_img[i + 1, j]
arr = np.sort(temp_arr) #从小到大排序
median_img[i,j]=arr[4]
max_img[i,j]=arr[8]
min_img[i,j]=arr[0]
rgb_avg_img=copy.deepcopy(img)
for i in range(1,img.shape[0]-1):
for j in range(1,img.shape[1]-1):
sum_b_pix = sum([img[l,k,0] for l in range(i-1,i+2) for k in range(j-1,j+2)])
sum_g_pix = sum([img[l, k, 1] for l in range(i - 1, i + 2) for k in range(j - 1, j + 2)])
sum_r_pix = sum([img[l, k, 2] for l in range(i - 1, i + 2) for k in range(j - 1, j + 2)])
rgb_avg_img[i,j]=[int(sum_b_pix/9),int(sum_g_pix/9),int(sum_r_pix/9)]
cv2.imshow('pepper image',imutils.resize(pepper_img,600))
cv2.imshow('blur image',imutils.resize(blur_img,600))
cv2.imshow('median image',imutils.resize(pepper_img,600))
cv2.imshow('mean image',imutils.resize(rgb_avg_img,600))
cv2.imshow('max image',imutils.resize(max_img,600))
cv2.imshow('min image',imutils.resize(min_img,600))
if cv2.waitKey(0)==27:
cv2.destroyAllWindows()
效果:
9. 锐化滤波器
代码:
如果你也是看准了Python,想自学Python,在这里为大家准备了丰厚的免费学习大礼包,带大家一起学习,给大家剖析Python兼职、就业行情前景的这些事儿。
一、Python所有方向的学习路线
Python所有方向路线就是把Python常用的技术点做整理,形成各个领域的知识点汇总,它的用处就在于,你可以按照上面的知识点去找对应的学习资源,保证自己学得较为全面。
二、学习软件
工欲善其必先利其器。学习Python常用的开发软件都在这里了,给大家节省了很多时间。
三、全套PDF电子书
书籍的好处就在于权威和体系健全,刚开始学习的时候你可以只看视频或者听某个人讲课,但等你学完之后,你觉得你掌握了,这时候建议还是得去看一下书籍,看权威技术书籍也是每个程序员必经之路。
四、入门学习视频
我们在看视频学习的时候,不能光动眼动脑不动手,比较科学的学习方法是在理解之后运用它们,这时候练手项目就很适合了。
四、实战案例
光学理论是没用的,要学会跟着一起敲,要动手实操,才能将自己的所学运用到实际当中去,这时候可以搞点实战案例来学习。
五、面试资料
我们学习Python必然是为了找到高薪的工作,下面这些面试题是来自阿里、腾讯、字节等一线互联网大厂最新的面试资料,并且有阿里大佬给出了权威的解答,刷完这一套面试资料相信大家都能找到满意的工作。
成为一个Python程序员专家或许需要花费数年时间,但是打下坚实的基础只要几周就可以,如果你按照我提供的学习路线以及资料有意识地去实践,你就有很大可能成功!
最后祝你好运!!!
网上学习资料一大堆,但如果学到的知识不成体系,遇到问题时只是浅尝辄止,不再深入研究,那么很难做到真正的技术提升。
一个人可以走的很快,但一群人才能走的更远!不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人,都欢迎加入我们的的圈子(技术交流、学习资源、职场吐槽、大厂内推、面试辅导),让我们一起学习成长!