# -*- encoding=utf-8 -*-
from image_similarity_function import *
import os
import shutil
# 融合相似度閾值
threshold1 = 0.70
# 最終相似度較高判斷閾值
threshold2 = 0.95

# 融合函數(shù)計算圖片相似度
def calc_image_similarity(img1_path, img2_path):
 """
 :param img1_path: filepath+filename
 :param img2_path: filepath+filename
 :return: 圖片最終相似度
 """
 similary_ORB = float(ORB_img_similarity(img1_path, img2_path))
 similary_phash = float(phash_img_similarity(img1_path, img2_path))
 similary_hist = float(calc_similar_by_path(img1_path, img2_path))
 # 如果三種算法的相似度最大的那個大于0.7，則相似度取最大，否則，取最小。
 max_three_similarity = max(similary_ORB, similary_phash, similary_hist)
 min_three_similarity = min(similary_ORB, similary_phash, similary_hist)
 if max_three_similarity > threshold1:
  result = max_three_similarity
 else:
  result = min_three_similarity
 return round(result, 3)

if __name__ == '__main__':
 # 搜索文件夾
 filepath = r'D:\Dataset\cityscapes\leftImg8bit\val\frankfurt'
 #待查找文件夾
 searchpath = r'C:\Users\Administrator\Desktop\cityscapes_paper'
 # 相似圖片存放路徑
 newfilepath = r'C:\Users\Administrator\Desktop\result'
 for parent, dirnames, filenames in os.walk(searchpath):
  for srcfilename in filenames:
img1_path = searchpath +"\\"+ srcfilename
for parent, dirnames, filenames in os.walk(filepath):
 for i, filename in enumerate(filenames):
  print("{}/{}: {} , {} ".format(i+1, len(filenames), srcfilename,filename))
  img2_path = filepath + "\\" + filename
  # 比較
  kk = calc_image_similarity(img1_path, img2_path)
  try:if kk >= threshold2:
# 將兩張照片同時拷貝到指定目錄
shutil.copy(img2_path, os.path.join(newfilepath, srcfilename[:-4] + "_" + filename))
  except Exception as e:# print(e)pass

# -*- encoding=utf-8 -*-
# 導(dǎo)入包
import cv2
from functools import reduce
from PIL import Image

# 計算兩個圖片相似度函數(shù)ORB算法
def ORB_img_similarity(img1_path, img2_path):
 """
 :param img1_path: 圖片1路徑
 :param img2_path: 圖片2路徑
 :return: 圖片相似度
 """
 try:
  # 讀取圖片
  img1 = cv2.imread(img1_path, cv2.IMREAD_GRAYSCALE)
  img2 = cv2.imread(img2_path, cv2.IMREAD_GRAYSCALE)
  # 初始化ORB檢測器
  orb = cv2.ORB_create()
  kp1, des1 = orb.detectAndCompute(img1, None)
  kp2, des2 = orb.detectAndCompute(img2, None)
  # 提取并計算特征點
  bf = cv2.BFMatcher(cv2.NORM_HAMMING)
  # knn篩選結(jié)果
  matches = bf.knnMatch(des1, trainDescriptors=des2, k=2)
  # 查看最大匹配點數(shù)目
  good = [m for (m, n) in matches if m.distance < 0.75 * n.distance]
  similary = len(good) / len(matches)
  return similary
 except:
  return '0'

# 計算圖片的局部哈希值--pHash
def phash(img):
 """
 :param img: 圖片
 :return: 返回圖片的局部hash值
 """
 img = img.resize((8, 8), Image.ANTIALIAS).convert('L')
 avg = reduce(lambda x, y: x + y, img.getdata()) / 64.
 hash_value = reduce(lambda x, y: x | (y[1] << y[0]), enumerate(map(lambda i: 0 if i < avg else 1, img.getdata())),0)
 return hash_value

# 計算兩個圖片相似度函數(shù)局部敏感哈希算法
def phash_img_similarity(img1_path, img2_path):
 """
 :param img1_path: 圖片1路徑
 :param img2_path: 圖片2路徑
 :return: 圖片相似度
 """
 # 讀取圖片
 img1 = Image.open(img1_path)
 img2 = Image.open(img2_path)
 # 計算漢明距離
 distance = bin(phash(img1) ^ phash(img2)).count('1')
 similary = 1 - distance / max(len(bin(phash(img1))), len(bin(phash(img1))))
 return similary

# 直方圖計算圖片相似度算法
def make_regalur_image(img, size=(256, 256)):
 """我們有必要把所有的圖片都統(tǒng)一到特別的規(guī)格，在這里我選擇是的256x256的分辨率。"""
 return img.resize(size).convert('RGB')

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 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 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 range(0, w, pw) \
for j in range(0, h, ph)]