文章目录
一、彩色图像文件转为灰度文件
1. 使用opencv
代码：
import cv2 as cv
img = cv.imread('./pic/lena.png',1)
img_1 = cv.cvtColor(img,cv.COLOR_BGR2GRAY)
cv.imshow('gray',img_1)
cv.imshow('colour',img)
cv.waitKey(0)
效果：
2. 不使用opencv
代码：
from PIL import Image
I = Image.open('./pic/lena.png')
L = I.convert('L')
L.show()
效果：
二、将彩色图像转为HSV、HSI格式
1. 转HSV
HSV 格式： H 代表色彩，S 代表颜色的深浅，V 代表着颜色的明暗程度。
HSV 颜色空间可以很好地把颜色信息和亮度信息分开，将它们放在不同的通道中，减小了光线对于特定颜色识别的影响。
在阴影检测算法中经常需要将RGB格式的图像转化为HSV格式，对于阴影区域而言，它的色度和饱和度相对于原图像而言变化不大，主要是亮度信息变化较大，，将RGB格式转化为HSV格式，就可以得到H、S、V分量，从而得到色度、饱和度、亮度得值；
代码：
import cv2 as cv
img = cv.imread('./pic/lena.png', 1)
cv.imshow('original image', img)
hsv = cv.cvtColor(img, cv.COLOR_BGR2HSV)
cv.imshow('HSV format image', hsv)
cv.waitKey(0)
效果：
2. 转HSI
HSL (色相hue, 饱和度saturation, 亮度lightness/luminance),
也称HLS 或 HSI (I指intensity)
与 HSV非常相似，仅用亮度（lightness）替代了明度（brightness）。
人的视觉对亮度的敏感程度远强于对颜色浓淡的敏感程度，为了便于颜色处理和识别，人的市局系统经常采用HSI彩色空间，它比RGB空间更符合人的视觉特性。此外，由于HSI空间中亮度和色度具有可分离性，使得图像处理和机器视觉中大量灰度处理算法都可在HSI空间方便进行
HSI颜色空间：
代码：
import cv2
import numpy as np
def rgbtohsi(rgb_lwpImg):
rows = int(rgb_lwpImg.shape[0])
cols = int(rgb_lwpImg.shape[1])
b, g, r = cv2.split(rgb_lwpImg)
# 归一化到[0,1]
b = b / 255.0
g = g / 255.0
r = r / 255.0
hsi_lwpImg = rgb_lwpImg.copy()
H, S, I = cv2.split(hsi_lwpImg)
for i in range(rows):
for j in range(cols):
num = 0.5 * ((r[i, j]-g[i, j])+(r[i, j]-b[i, j]))
den = np.sqrt((r[i, j]-g[i, j])**2+(r[i, j]-b[i, j])*(g[i, j]-b[i, j]))
theta = float(np.arccos(num/den))
if den == 0:
H = 0
elif b[i, j] <= g[i, j]:
H = theta
else:
H = 2*3.14169265 - theta
min_RGB = min(min(b[i, j], g[i, j]), r[i, j])
sum = b[i, j]+g[i, j]+r[i, j]
if sum == 0:
S = 0
else:
S = 1 - 3*min_RGB/sum
H = H/(2*3.14159265)
I = sum/3.0
# 输出HSI图像，扩充到255以方便显示，一般H分量在[0,2pi]之间，S和I在[0,1]之间
hsi_lwpImg[i, j, 0] = H*255
hsi_lwpImg[i, j, 1] = S*255
hsi_lwpImg[i, j, 2] = I*255
return hsi_lwpImg
if __name__ == '__main__':
rgb_lwpImg = cv2.imread("./pic/lena.png")
hsi_lwpImg = rgbtohsi(rgb_lwpImg)
cv2.imshow('lena.jpg', rgb_lwpImg)
cv2.imshow('hsi_lwpImg', hsi_lwpImg)
key = cv2.waitKey(0) & 0xFF
if key == ord('q'):
cv2.destroyAllWindows()
效果：
三、车牌数字分割为单个的字符图片
1.图片准备
2. 代码实现
1. 读取图片
file_path = "./pic/License/"
licenses = os.listdir(file_path)
for license in licenses:
path = file_path+license
output_path = "./pic/"+license # 图片输出路径
# 如果该路径存在则删除
if os.path.isdir(output_path):
shutil.rmtree(output_path)
# 创建文件夹
os.mkdir(output_path)
# 1.读取图片
src = cv2.imread(path)
img = src.copy()
2. 图片预处理
- 去除车牌螺丝点
# 去除车牌上螺丝，将其替换为车牌底色
cv2.circle(img, (145, 20), 10, (255, 0, 0), thickness=-1)
cv2.circle(img, (430, 20), 10, (255, 0, 0), thickness=-1)
cv2.circle(img, (145, 170), 10, (255, 0, 0), thickness=-1)
cv2.circle(img, (430, 170), 10, (255, 0, 0), thickness=-1)
cv2.circle(img, (180, 90), 10, (255, 0, 0), thickness=-1)
- 图片灰度处理
# 3.灰度
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
- 高斯滤波
# 4.高斯滤波
GSblurred = cv2.GaussianBlur(gray, (5, 5), 12) # 参数自行调节
- 二值化
# 5.将灰度图二值化设定阈值
ret, thresh = cv2.threshold(GSblurred , 127, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
print("ret",ret)
- 闭运算
# 6. 闭运算
kernel = np.ones((3, 3), int)
closed = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel,iterations=2)
- 分割字符
# 7.分割字符
white = [] # 记录每一列的白色像素总和
black = [] # ..........黑色.......
height = thresh.shape[0]
width = thresh.shape[1]
white_max = 0
black_max = 0
# 计算每一列的黑白色像素总和
for i in range(width):
s = 0 # 这一列白色总数
t = 0 # 这一列黑色总数
for j in range(height):
if thresh[j][i] == 255:
s += 1
if thresh[j][i] == 0:
t += 1
white_max = max(white_max, s)
black_max = max(black_max, t)
white.append(s)
black.append(t)
- 分割图像
arg = False # False表示白底黑字；True表示黑底白字
if black_max > white_max:
arg = True
# 分割图像
def find_end(start_):
end_ = start_ + 1
for m in range(start_ + 1, width - 1):
if (black[m] if arg else white[m]) > (0.95 * black_max if arg else 0.95 * white_max): # 0.95这个参数请多调整，对应下面的0.05
end_ = m
break
return end_
n = 1
start = 1
end = 2
i=0;
cj=[]
while n < width - 2:
n += 1
if (white[n] if arg else black[n]) > (0.05 * white_max if arg else 0.05 * black_max):
# 上面这些判断用来辨别是白底黑字还是黑底白字
# 0.05这个参数请多调整，对应上面的0.95
start = n
end = find_end(start)
n = end
if end - start > 5:
cj.append(thresh[1:height, start:end])
cv2.imwrite(output_path + '/' + str(i) + '.jpg', cj[i])
i = i + 1;
3. 输出结果
部分展示
4. 源码
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
项目主题：车牌检测将车牌数字分割为单个的字符图片
"""
import os
import shutil
import cv2
import numpy as np
file_path = "./pic/License/"
licenses = os.listdir(file_path)
for license in licenses:
path = file_path+license
output_path = "./pic/"+license
# 如果该路径存在则删除
if os.path.isdir(output_path):
shutil.rmtree(output_path)
# 创建文件夹
os.mkdir(output_path)
# 1.读取图片
src = cv2.imread(path)
img = src.copy()
# 2.去除车牌上螺丝，将其替换为车牌底色
cv2.circle(img, (145, 20), 10, (255, 0, 0), thickness=-1)
cv2.circle(img, (430, 20), 10, (255, 0, 0), thickness=-1)
cv2.circle(img, (145, 170), 10, (255, 0, 0), thickness=-1)
cv2.circle(img, (430, 170), 10, (255, 0, 0), thickness=-1)
cv2.circle(img, (180, 90), 10, (255, 0, 0), thickness=-1)
# 3.灰度
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# 4.高斯滤波
GSblurred = cv2.GaussianBlur(gray, (5, 5), 12)
# 5.将灰度图二值化设定阈值
ret, thresh = cv2.threshold(GSblurred , 127, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
print("ret",ret)
# 6. 闭运算
kernel = np.ones((3, 3), int)
closed = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel,iterations=2)
二值化
ret, thresh = cv2.threshold(closed, 127, 255, cv2.THRESH_BINARY+ cv2.THRESH_OTSU)
# 7.分割字符
white = [] # 记录每一列的白色像素总和
black = [] # ..........黑色.......
height = thresh.shape[0]
width = thresh.shape[1]
white_max = 0
black_max = 0
# 计算每一列的黑白色像素总和
for i in range(width):
s = 0 # 这一列白色总数
t = 0 # 这一列黑色总数
for j in range(height):
if thresh[j][i] == 255:
s += 1
if thresh[j][i] == 0:
t += 1
white_max = max(white_max, s)
black_max = max(black_max, t)
white.append(s)
black.append(t)
# print(s)
# print(t)
arg = False # False表示白底黑字；True表示黑底白字
if black_max > white_max:
arg = True
# 分割图像
def find_end(start_):
end_ = start_ + 1
for m in range(start_ + 1, width - 1):
if (black[m] if arg else white[m]) > (0.95 * black_max if arg else 0.95 * white_max): # 0.95这个参数请多调整，对应下面的0.05
end_ = m
break
return end_
n = 1
start = 1
end = 2
i=0;
cj=[]
while n < width - 2:
n += 1
if (white[n] if arg else black[n]) > (0.05 * white_max if arg else 0.05 * black_max):
# 上面这些判断用来辨别是白底黑字还是黑底白字
# 0.05这个参数请多调整，对应上面的0.95
start = n
end = find_end(start)
n = end
if end - start > 5:
cj.append(thresh[1:height, start:end])
cv2.imwrite(output_path + '/' + str(i) + '.jpg', cj[i])
i += 1;
四、参考
https://www.cnblogs.com/datou-swag/articles/10672207.html
https://blog.csdn.net/qq_47281915/article/details/121705585
1253
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
