这个周末解决了一个实际问题。
硬盘里存有大量图片。（大约2万）
当需要找某一图片时，如何找出与之相似的呢。
在查资料的过程中。我知道可以使用
PIL（Python Image Library）或者是openCV。
对于学习来说，使用后者更好，因为opencv具有跨平台的特性，且支持多种语言的接口。而且在python上也不乏很多资料可查。
开发环境我选择了 opencv3.1 + pycharm
在python中图像使用numpy.ndarray表示，所以要提前装好numpy库。
下一步就是匹配算法了。
一开始我想用的是Template Matching
后来发现这种模式匹配的方式还需要涉及缩放问题。
于是，简单点的话还是使用直方图匹配的方式进行。
参考 pil的这个博客。不过我使用的是opencv。
opencv的直方图使用资料可以从readdoc网查到
好的。讲了这么多。还是直接贴代码吧～
import cv2
import numpy as np
import os
import os.path
from matplotlib import pyplot as plt
此处安装后，需要配置cv2的so库地址。报错不要紧，不影响调用。见我的安装笔记即可。
获取直方图算法：简单说一下，就是分别获取rgb三个通道的直方图，然后加在一起，成为一个768*1的数组。
返回的是一个元组。分别是直方图向量和图像的像素点总和。我利用这个比例缩放来进行图片的大小匹配。
def get_histGBR(path):
img = cv2.imread(path)
pixal = img.shape[0] * img.shape[1]
# print(pixal)
# scale = pixal/100000.0
# print(scale)
total = np.array([0])
for i in range(3):
histSingle = cv2.calcHist([img], [i], None, [256], [0, 256])
total = np.vstack((total, histSingle))
# plt.plot(total)
# plt.xlim([0, 768])
# plt.show()
return (total, pixal)
相似度计算：
计算公式
def hist_similar(lhist, rhist, lpixal,rpixal):
rscale = rpixal/lpixal
rhist = rhist/rscale
assert len(lhist) == len(rhist)
likely = sum(1 - (0 if l == r else float(abs(l - r)) / max(l, r)) for l, r in zip(lhist, rhist)) / len(lhist)
if likely == 1.0:
return [1.0]
return likely
该算法反悔一个0到1的［float］相似度。来代表两个向量之间的几何距离。输入的4个参数分别为图像的直方图和图像的尺寸。
最后加上一些文件访问的代码和排序代码。即可给出
对于指定图片，在目标文件夹中的所有图片中相似度排名最高的N个图的路径和相似度。
import cv2
import numpy as np
import os
import os.path
from matplotlib import pyplot as plt
# 文件读取并显示
# img = cv2.imread("kitchen.jpeg")
# print("hello opencv "+ str(type(img)))
# # print(img)
# cv2.namedWindow("Image")
# cv2.imshow("Image",img)
# cv2.waitKey(0)
# cv2.destroyAllWindows()
# img = cv2.imread('kitchen.jpeg', 1)
# temp = cv2.imread('Light.png', 1)
# w,h = temp.shape[::-1]
#
# print(w,h,sep=" ")
# # print(img)
# cv2.namedWindow("Image")
# cv2.imshow("Image", img)
# cv2.waitKey(0)
# cv2.destroyAllWindows()
# img = cv2.imread('kitchen.jpeg', 0)
# img2 = img.copy()
# template = cv2.imread('Light.png', 0)
# w, h = template.shape[::-1]
# print(template.shape)
#
# # All the 6 methods for comparison in a list
# methods = ['cv2.TM_CCOEFF', 'cv2.TM_CCOEFF_NORMED', 'cv2.TM_CCORR',
# 'cv2.TM_CCORR_NORMED', 'cv2.TM_SQDIFF', 'cv2.TM_SQDIFF_NORMED']
#
# for meth in methods:
# img = img2.copy()
# method = eval(meth)
#
# # Apply template Matching
# res = cv2.matchTemplate(img, template, method)
# min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)
#
# # If the method is TM_SQDIFF or TM_SQDIFF_NORMED, take minimum
# if method in [cv2.TM_SQDIFF, cv2.TM_SQDIFF_NORMED]:
# top_left = min_loc
# else:
# top_left = max_loc
# bottom_right = (top_left[0] + w, top_left[1] + h)
#
# cv2.rectangle(img, top_left, bottom_right, 255, 2)
#
# plt.subplot(121), plt.imshow(res, cmap='gray')
# plt.title('Matching Result'), plt.xticks([]), plt.yticks([])
# plt.subplot(122), plt.imshow(img, cmap='gray')
# plt.title('Detected Point'), plt.xticks([]), plt.yticks([])
# plt.suptitle(meth)
#
# plt.show()
# image = cv2.imread("kitchen.jpeg", 0)
# hist = cv2.calcHist([image],
# [0],
# None,
# [256],
# [0, 256])
# plt.plot(hist),plt.xlim([0,256])
# plt.show()
# # hist = cv2.calcHist([image],[0,1,2],None,[256,256,256],[[0,255],[0,255],[0,255]])
# # cv2.imshow("img",image)
# cv2.imshow("hist", hist)
# cv2.waitKey(0)
# cv2.destroyAllWindows()
# image = cv2.imread("kitchen.jpeg", 0)
# hist = plt.hist(image.ravel(), 256, [0, 256])
# plt.show(hist)
def hist_similar(lhist, rhist, lpixal,rpixal):
rscale = rpixal/lpixal
rhist = rhist/rscale
assert len(lhist) == len(rhist)
likely = sum(1 - (0 if l == r else float(abs(l - r)) / max(l, r)) for l, r in zip(lhist, rhist)) / len(lhist)
if likely == 1.0:
return [1.0]
return likely
def get_histGBR(path):
img = cv2.imread(path)
pixal = img.shape[0] * img.shape[1]
# print(pixal)
# scale = pixal/100000.0
# print(scale)
total = np.array([0])
for i in range(3):
histSingle = cv2.calcHist([img], [i], None, [256], [0, 256])
total = np.vstack((total, histSingle))
# plt.plot(total)
# plt.xlim([0, 768])
# plt.show()
return (total, pixal)
if __name__ == '__main__':
targetHist, targetPixal = get_histGBR('test.jpg')
rootdir = "/Users/YM/Desktop/DCIM"
# aHist = get_histGBR('a.png')
# bHist = get_histGBR('Light.png')
#
# print(hist_similar(aHist, bHist))
resultDict = {}
for parent, dirnames, filenames in os.walk(rootdir):
# for dirname in dirnames:
# print("parent is: " + parent)
# print("dirname is: " + dirname)
for filename in filenames:
if (filename[-3:] == 'jpg'):
jpgPath = os.path.join(parent, filename)
testHist, testPixal = get_histGBR(jpgPath)
# print(hist_similar(targetHist,testHist)[0])
resultDict[jpgPath]=hist_similar(targetHist,testHist,targetPixal,testPixal)[0]
# print(resultDict)
# for each in resultDict:
# print(each, resultDict[each],sep="----")
sortedDict = sorted(resultDict.items(), key=lambda asd: asd[1], reverse=True)
for i in range(5):
print(sortedDict[i])
