详解Python计算机视觉 图像扭曲（仿射扭曲）

from PCV.geometry import warp, homography
from PIL import Image
from pylab import *
from scipy import ndimage

# 仿射扭曲im1到im2的例子

im1 = array(Image.open('jida.jpg').convert('L'))
im2 = array(Image.open('beijing.jpg').convert('L'))
# 选定一些目标点
tp = array([[420,830,830,420],[400,350,1060,1000],[1,1,1,1]])
#标记物的坐标tp是用齐次坐标意义下的坐标表示的
#array为 第一张图片贴到第二张图片的四个角点的坐标
#tp = array([[675,826,826,677],[55,52,281,277],[1,1,1,1]])
im3 = warp.image_in_image(im1,im2,tp)
#image_in_image()函数的输入参数为两幅图像和一个坐标
figure()
gray()
subplot(141)
axis('off')
imshow(im1)
subplot(142)
axis('off')
imshow(im2)
subplot(143)
axis('off')
imshow(im3)

# 选定im1角上的一些点
m,n = im1.shape[:2]
fp = array([[0,m,m,0],[0,0,n,n],[1,1,1,1]])
# 第一个三角形
tp2 = tp[:,:3]
fp2 = fp[:,:3]
# 计算H
H = homography.Haffine_from_points(tp2,fp2)
im1_t = ndimage.affine_transform(im1,H[:2,:2],
(H[0,2],H[1,2]),im2.shape[:2])
# 三角形的alpha
alpha = warp.alpha_for_triangle(tp2,im2.shape[0],im2.shape[1])
im3 = (1-alpha)*im2 + alpha*im1_t
# 第二个三角形
tp2 = tp[:,[0,2,3]]
fp2 = fp[:,[0,2,3]]
# 计算H
H = homography.Haffine_from_points(tp2,fp2)
#Haffine_from_points()返回给定对应点对的最优仿射变换
im1_t = ndimage.affine_transform(im1,H[:2,:2],
(H[0,2],H[1,2]),im2.shape[:2])
# 三角形的alpha
alpha = warp.alpha_for_triangle(tp2,im2.shape[0],im2.shape[1])
im4 = (1-alpha)*im3 + alpha*im1_t
subplot(144)
imshow(im4)
axis('off')
show()