correction of spelling mistakes of "classfiy" to "classify"

README.md

@@ -1,3 +1,15 @@
+## 检测一个文件夹中的相似图片
+
+```
+bash test.sh folder
+```
+
+将每张图片和他之后的五张图片比较（ls默认顺序），相似的会输出两张图片名称。
+
+test.py中修改使用的算法。具体算法见下。
+
+
+
 
 [中文](Chinese.md)
 

aHash.py

@@ -1,6 +1,7 @@
 from PIL import Image
 from PIL import ImageFilter
 from PIL import ImageOps
+import sys
 
 #This module can classfy the image by Average Hash Method
 #The Hash Method is too strict,so this moudel suitable for finding image by Thumbnail
@@ -34,16 +35,16 @@ def compCode(code1,code2):
 	for index in range(0,len(code1)):
 		if code1[index] != code2[index]:
 			num+=1
-	return num 
+	return num
 
-def classfiy_aHash(image1,image2,size=(8,8),exact=25):
+def classify_aHash(image1,image2,size=(8,8),exact=25):
 	''' 'image1' and 'image2' is a Image Object.
 	You can build it by 'Image.open(path)'.
 	'Size' is parameter what the image will resize to it and then image will be compared by the algorithm.
-	It's 8 * 8 when it default.  
+	It's 8 * 8 when it default.
 	'exact' is parameter for limiting the Hamming code between 'image1' and 'image2',it's 25 when it default.
-	The result become strict when the exact become less. 
-	This function return the true when the 'image1'  and 'image2' are similar. 
+	The result become strict when the exact become less.
+	This function return the true when the 'image1'  and 'image2' are similar.
 	'''
 	image1 = image1.resize(size).convert('L').filter(ImageFilter.BLUR)
 	image1 = ImageOps.equalize(image1)
@@ -53,10 +54,11 @@ def classfiy_aHash(image1,image2,size=(8,8),exact=25):
 	code2 = getCode(image2, size)
 
 	assert len(code1) == len(code2),"error"
-	
+
 	return compCode(code1, code2)<=exact
 
 
 
-__all__=[classfiy_aHash]
+__all__=[classify_aHash]
+
 

dHash.py

@@ -11,7 +11,7 @@ def getCode(img,size):
 	result = []
 	# print("x==",size[0])
 	# print("y==",size[1]-1)
-	
+
 	x_size = size[0]-1#width
 	y_size = size[1] #high
 	for x in range(0,x_size):
@@ -34,15 +34,15 @@ def compCode(code1,code2):
 	for index in range(0,len(code1)):
 		if code1[index] != code2[index]:
 			num+=1
-	return num 
+	return num
 
-def classfiy_dHash(image1,image2,size=(9,8)):
+def classify_dHash(image1,image2,size=(9,8)):
 	''' 'image1' and 'image2' is a Image Object.
 	You can build it by 'Image.open(path)'.
 	'Size' is parameter what the image will resize to it and then image will be compared to another image by the dHash.
-	It's 9 * 8 when it default.  
+	It's 9 * 8 when it default.
 
-	The function will return the hamming code,less is correct. 
+	The function will return the hamming code,less is correct.
 	'''
 	image1 = image1.resize(size).convert('L')
 	code1 = getCode(image1, size)
@@ -52,10 +52,10 @@ def classfiy_dHash(image1,image2,size=(9,8)):
 	code2 = getCode(image2, size)
 
 	assert len(code1) == len(code2),"error"
-	
+
 	return compCode(code1, code2)
 
 
 
-__all__=[classfiy_dHash]
+__all__=[classify_dHash]
 

histogram.py

@@ -1,15 +1,16 @@
 from PIL import Image
+import sys
 
 #This module can classify the image by histogram.
 #This method is easy for someone who is a beginner in Image classification.
 #
 #author MashiMaroLjc
 #version 2016-2-16
 
-def classfiy_histogram(image1,image2,size = (256,256)):
+def classify_histogram(image1,image2,size = (256,256)):
 	''' 'image1' and 'image2' is a Image Object.
 	You can build it by 'Image.open(path)'.
-	'Size' is parameter what the image will resize to it.It's 256 * 256 when it default.  
+	'Size' is parameter what the image will resize to it.It's 256 * 256 when it default.
 	This function return the similarity rate betweene 'image1' and 'image2'
 	'''
 	image1 = image1.resize(size).convert("RGB")
@@ -27,7 +28,7 @@ def classfiy_histogram(image1,image2,size = (256,256)):
 			data.append(1 - abs(g[index] - s[index])/max(g[index],s[index]) )
 		else:
 			data.append(1)
-
-	return sum(data)/len(g)
 
+	return sum(data)/len(g)
 
+__all__=[classify_histogram]

histogram2.py

@@ -18,7 +18,7 @@ def calculate(image1,image2):
 			data.append(1 - abs(g[index] - s[index])/max(g[index],s[index]) )
 		else:
 			data.append(1)
-	
+
 	return sum(data)/len(g)
 
 
@@ -38,10 +38,10 @@ def split_imgae(image,part_size):
 
 	return sub_image_list
 
-def classfiy_histogram_with_split(image1,image2,size = (256,256),part_size=(64,64)):
+def classify_histogram_with_split(image1,image2,size = (256,256),part_size=(64,64)):
 	''' 'image1' and 'image2' is a Image Object.
 	You can build it by 'Image.open(path)'.
-	'Size' is parameter what the image will resize to it.It's 256 * 256 when it default.  
+	'Size' is parameter what the image will resize to it.It's 256 * 256 when it default.
 	'part_size' is size of piece what the image will be divided.It's 64*64 when it default.
 	This function return the similarity rate betweene 'image1' and 'image2'
 	'''
@@ -59,7 +59,7 @@ def classfiy_histogram_with_split(image1,image2,size = (256,256),part_size=(64,6
 	y = size[1]/part_size[1]
 
 	pre = round((sub_data/(x*y) ),3 )
-	return  pre	
+	return  pre
 
-__all__ = [classfiy_histogram_with_split]
+__all__ = [classify_histogram_with_split]
 

result

@@ -0,0 +1,6 @@
+similar/0.jpg similar/1.jpg
+similar/0.jpg similar/2.jpg
+similar/1.jpg similar/2.jpg
+similar/3.jpg similar/4.jpg
+similar/5.jpg similar/6.jpg
+similar/7.jpg similar/8.jpg

test.py

@@ -0,0 +1,52 @@
+#!/usr/bin/python3
+
+#================================================================
+#   Copyright (C) 2018 Sangfor Ltd. All rights reserved.
+#
+#   filename：test.py
+#   author：ljx (jiaxinustc#gmail.com)
+#   date：2018.12.11
+#   description：传入两张图片，检测其相似与否
+#
+#================================================================
+from PIL import Image
+from aHash import classify_aHash
+from dHash import classify_dHash
+from pHash import classify_DCT
+from histogram import classify_histogram
+from histogram2 import classify_histogram_with_split
+import sys
+
+
+if __name__=="__main__":
+
+    #phash dhash ahash
+    #method="ahash"
+    #method="dhash"
+    #method="phash"
+    #method="histogram"
+    method="histogram2"
+
+    image1=Image.open(sys.argv[1])
+    image2=Image.open(sys.argv[2])
+    if method=="ahash":
+        re=classify_aHash(image1,image2)
+        if(re):
+            print(sys.argv[1],sys.argv[2])
+    elif method=="dhash":
+        re=classify_dHash(image1,image2)
+        if(re<30):
+            print(sys.argv[1],sys.argv[2])
+    elif method=="phash":
+        re=classify_DCT(image1,image2)
+        if(re<=10):
+            print(sys.argv[1],sys.argv[2])
+    elif method=="histogram":
+        re=classify_histogram(image1,image2)
+        if(re>0.8):
+            print(sys.argv[1],sys.argv[2])
+    elif method=="histogram2":
+        re=classify_histogram_with_split(image1,image2)
+        if(re>0.55):
+            print(sys.argv[1],sys.argv[2])
+            #print(re)

test.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+
+#================================================================
+#   Copyright (C) 2018 Sangfor Ltd. All rights reserved.
+#
+#   filename：test.sh
+#   author：ljx (jiaxinustc#gmail.com)
+#   date：2018.12.11
+#   description：比较$1目录下所有图片，找出相似图片
+#
+#================================================================
+
+#export PYTHONPATH=`pwd`
+#图片数目
+s=0
+
+for file in $1/*
+do
+    filelist[$s]=$file
+    #echo ${filelist[$i]}
+    ((s++))
+done
+
+for((i=0;i<s;i++))
+do
+    for((j=i+1;j<s;j++))
+    do
+        #echo ${filelist[$i]} ${filelist[$j]}
+        python3 test.py ${filelist[$i]} ${filelist[$j]}
+    done
+done
+
+#运行结果定向到result，然后将第二列移走即可，第二列都是相似图片。
+#cat result| awk '{printf("mv %s s/\n",[)}''])}'