这段代码实用pil模块比较两个图片的相似度,根据实际实用,代码虽短但效果不错,还是非常靠谱的,前提是图片要大一些,太小的图片不好比较。附件提供完整测试代码和对比用的图片。
#!/usr/bin/python # Filename: histsimilar.py # -*- 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('\n'.join(l + ',' + r for l, r in zip(map(str, li.histogram()), map(str, ri.histogram())))) # print >>fd, '\n' # 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') if __name__ == '__main__': path = r'testpic/TEST%d/%d.JPG' for i in xrange(1, 7): print 'test_case_%d: %.3f%%'%(i, \ calc_similar_by_path('testpic/TEST%d/%d.JPG'%(i, 1), 'testpic/TEST%d/%d.JPG'%(i, 2))*100) # make_doc_data('test/TEST4/1.JPG', 'test/TEST4/2.JPG')
附件:源代码下载