数字图像与机器视觉基础补充(补)
作者:互联网
数字图像与机器视觉基础补充
彩色图像文件转换为灰度文件
使用opencv
代码:
import cv2 as cv
img = cv.imread('189.png', 1)
img_1 = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
cv.imshow('gray', img_1)
cv.imshow('colour', img)
cv.waitKey(0)
不使用opencv
from PIL import Image
I = Image.open('189.png')
L = I.convert('L')
L.show()
彩色图像(RGB)转为HSV、HSI 格式
HSV
import cv2 as cv
img = cv.imread('189.png', 1)
cv.imshow('original image', img)
hsv = cv.cvtColor(img, cv.COLOR_BGR2HSV)
cv.imshow('HSV format image', hsv)
cv.waitKey(0)
HSI
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("1.jpg")
hsi_lwpImg = rgbtohsi(rgb_lwpImg)
cv2.imshow('1.jpg', rgb_lwpImg)
cv2.imshow('hsi_lwpImg', hsi_lwpImg)
key = cv2.waitKey(0) & 0xFF
if key == ord('q'):
cv2.destroyAllWindows()
参考
标签:机器,img,数字图像,cv2,lwpImg,rgb,HSV,视觉,cv 来源: https://blog.csdn.net/xyf_fate/article/details/122246088