python如何提取图片的特定区域

1、crop 方法函数原型为：

Image.crop(box=None)Returns a rectangular region from this image. The box is a 4-tuple defining the left, upper, right, and lower pixel coordinate. 

This is a lazy operation. Changes to the source image may or may not be reflected in the cropped image. To break the connection, call the load() method on the cropped copy. 

Parameters:    box – The crop rectangle, as a (left, upper, right, lower)-tuple. 

Return type:    Image 

Returns:    An Image object.

2、通过矩形的左上角的坐标和右下角的坐标，即可构造box，例如下面的代码：

box = (100, 100, 400, 400) 

region = im.crop(box)

3、通过提取除ROI时，上面例子为 region，保存ROI到图像则使用类 Image 的 save 方法：

region.save(filename)

4、写一个Demo例子，使用人脸数据库GENKI部分的图像做实验，该数据的数字子集GENKI-SZSL提供人脸区域的坐标和大小。提取代码如下：

from PIL import Image

import os

 src = '.'

imlist = open(src + '/GENKI-SZSL_Images.txt', 'r').readlines()

 rs = [float(line.split()[1]) for line in open(src + '/GENKI-SZSL_labels.txt', 'r').readlines()]

 cs = [float(line.split()[0]) for line in open(src + '/GENKI-SZSL_labels.txt', 'r').readlines()] 

ss = [float(line.split()[2]) for line in open(src + '/GENKI-SZSL_labels.txt', 'r').readlines()]

for i in range(0, len(rs)):    

path = src + '/images/' + imlist[i].strip()   

 filename = src + '/output/' + imlist[i].strip()   

 try:       

 im = Image.open(path)    

except:        

continue       

 r = rs[i]    

c = cs[i]    

s = ss[i]    

xLeft   = int(c - s/2)   

 yUpper  = int(r - s/2)    

xRight  = int(c + s/2)    

yLower  = int(r + s/2)    

region = im.crop((xLeft, yUpper, xRight, yLower))   

 region.save(filename)