version 2

.gitignore

@@ -1 +1,6 @@
 *.pyc
+env
+*.jpg
+build
+dist
+ImageHash.egg-info/

README.rst

@@ -6,6 +6,7 @@ A image hashing library written in Python. ImageHash supports:
 * average hashing (`aHash`_)
 * perception hashing (`pHash`_)
 * difference hashing (`dHash`_)
+* wavelet hashing (`wHash`_)
 
 Requirements
 -------------
@@ -36,6 +37,7 @@ Source hosted at github: https://github.com/JohannesBuchner/imagehash
 .. _aHash: http://www.hackerfactor.com/blog/index.php?/archives/432-Looks-Like-It.html
 .. _pHash: http://www.hackerfactor.com/blog/index.php?/archives/432-Looks-Like-It.html
 .. _dHash: http://www.hackerfactor.com/blog/index.php?/archives/529-Kind-of-Like-That.html
+.. _wHash: https://www.kaggle.com/c/avito-duplicate-ads-detection/
 .. _pypi: https://pypi.python.org/pypi/ImageHash
 
 

find_similar_images.py

@@ -26,14 +26,16 @@ def is_image(filename):
 if __name__ == '__main__':
     import sys, os
     def usage():
-    	sys.stderr.write("""SYNOPSIS: %s [ahash|phash|dhash] [<directory>]
+    	sys.stderr.write("""SYNOPSIS: %s [ahash|phash|dhash|...] [<directory>]
 
 Identifies similar images in the directory.
 
 Method: 
-  ahash: Average hash
-  phash: Perceptual hash
-  dhash: Difference hash
+  ahash:      Average hash
+  phash:      Perceptual hash
+  dhash:      Difference hash
+  whash-haar: Haar wavelet hash
+  whash-db4:  Daubechies wavelet hash
 
 (C) Johannes Buchner, 2013
 """ % sys.argv[0])
@@ -46,6 +48,10 @@ def usage():
     	hashfunc = imagehash.phash
     elif hashmethod == 'dhash':
     	hashfunc = imagehash.dhash
+    elif hashmethod == 'whash-haar':
+    	hashfunc = imagehash.whash
+    elif hashmethod == 'whash-db4':
+    	hashfunc = lambda img: imagehash.whash(img, mode='db4')
     else:
     	usage()
     userpath = sys.argv[2] if len(sys.argv) > 2 else "."

imagehash/__init__.py

@@ -165,6 +165,8 @@ def dhash(image, hash_size=8):
 def whash(image, hash_size = 8, image_scale = None, mode = 'haar', remove_max_haar_ll = True):
 	"""
 	Wavelet Hash computation.
+	
+	based on https://www.kaggle.com/c/avito-duplicate-ads-detection/
 
 	@image must be a PIL instance.
 	@hash_size must be a power of 2 and less than @image_scale.
@@ -176,7 +178,7 @@ def whash(image, hash_size = 8, image_scale = None, mode = 'haar', remove_max_ha
 	@remove_max_haar_ll - remove the lowest low level (LL) frequency using Haar wavelet.
 	"""
 
-	if image_scale != None:
+	if image_scale is not None:
 		assert image_scale == int(2**image_scale), "image_scale is not power of 2"
 	else:
 		image_scale = 2**int(numpy.log2(min(image.size)))
@@ -206,3 +208,4 @@ def whash(image, hash_size = 8, image_scale = None, mode = 'haar', remove_max_ha
 	med = numpy.median(dwt_low)
 	diff = dwt_low > med
 	return ImageHash(diff)
+

setup.py

@@ -9,7 +9,7 @@
 
 setup(
     name='ImageHash',
-    version='1.0',
+    version='2.0',
     author='Johannes Buchner',
     author_email='[email protected]',
     packages=['imagehash'],
@@ -19,9 +19,10 @@
     description='Image Hashing library',
     long_description=long_description,
     install_requires=[
-        "scipy",
         "numpy",
-        "pillow", # or PIL
+        "scipy",       # for phash
+        "pillow",      # or PIL
+        "PyWavelets",  # for whash
     ],
 )