计算图片相似度部分
# -*- coding: utf-8 -*-
import Image
def make_regalur_image(img, size=(256, 256)):
return img.resize(size).convert('RGB')
def split_image(img, part_size=(64, 64)):
w, h = img.size
pw, ph = part_size
assert w % pw == h % ph == 0
return [img.crop((i, j, i + pw, j + ph)).copy()
for i in xrange(0, w, pw)
for j in xrange(0, h, ph)]
def hist_similar(lh, rh):
assert len(lh) == len(rh)
return sum(1 - (0 if l == r else float(abs(l - r)) / max(l, r)) for l, r in zip(lh, rh)) / len(lh)
def calc_similar(li, ri):
#   return hist_similar(li.histogram(), ri.histogram())
return sum(hist_similar(l.histogram(), r.histogram()) for l, r in zip(split_image(li), split_image(ri))) / 16.0
def calc_similar_by_path(lf, rf):
li, ri = make_regalur_image(Image.open(lf)), make_regalur_image(Image.open(rf))
return calc_similar(li, ri)
def make_doc_data(lf, rf):
li, ri = make_regalur_image(Image.open(lf)), make_regalur_image(Image.open(rf))
li.save(lf + '_regalur.png')
ri.save(rf + '_regalur.png')
fd = open('stat.csv', 'w')
fd.write(' '.join(l + ',' + r for l, r in zip(map(str, li.histogram()), map(str, ri.histogram()))))
#   print >>fd, ' '
#   fd.write(','.join(map(str, ri.histogram())))
fd.close()
import ImageDraw
li = li.convert('RGB')
draw = ImageDraw.Draw(li)
for i in xrange(0, 256, 64):
draw.line((0, i, 256, i), fill='#ff0000')
draw.line((i, 0, i, 256), fill='#ff0000')
li.save(lf + '_lines.png')