（一）opencv_py之roi区域

opencv_py之roi区域

参考：

• Basic Operations on Images

1. roi

Sometimes, you will have to play with certain region of images. For eye detection in images, first face detection is done all over the image. When a face is obtained, we select the face region alone and search for eyes inside it instead of searching the whole image. It improves accuracy (because eyes are always on faces 😄 ) and performance (because we search in a small area).

2. 示例

import numpy as np
import cv2 as cv


def showImage(img):
    cv.namedWindow("image")
    cv.imshow("image", img)
    cv.waitKey()
    cv.destroyAllWindows()

def printImageInfo(img):
    width=img.shape[0]
    height=img.shape[1]
    print("width is", width)
    print("height is", height)


# 读取图片
imgLena=cv.imread("../lena.jpg")
#showImage(imgLena)
printImageInfo(imgLena)

# roi, 这里是切片，指向同一底层的数组
imgFace=imgLena[100:200, 100:200]
showImage(imgFace)
printImageInfo(imgFace)

# 修改roi， 原始图片也被修改
# for row in range(0,100):
#     for colomn in range(0,100):
#         for channel in range(0,3):
#             imgFace[row][colomn][channel]=255
#
# showImage(imgLena)

imgPeople=cv.imread("../image/people.jpg")
#showImage(imgPeople)
printImageInfo(imgPeople)

imgFace2=imgPeople[100:200, 100:200]
showImage(imgFace2)

#  g(x)=(1−α)f0(x)+αf1(x)
# By varying α from 0→1, you can perform a cool transition between one image to another.

#  cv.addWeighted() applies following equation on the image.
# dst=α⋅img1+β⋅img2+γ
imgBlend=cv.addWeighted(imgFace, 0.7, imgFace2, 0.3, 0)
showImage(imgBlend)