whash(): Wavelet based image hash

imagehash/__init__.py

@@ -33,6 +33,7 @@
 from PIL import Image
 import numpy
 import scipy.fftpack
+import pywt
 
 def _binary_array_to_hex(arr):
 	"""
@@ -161,4 +162,47 @@ def dhash(image, hash_size=8):
 	return ImageHash(diff)
 
 
+def whash(image, hash_size = 8, image_scale = None, mode = 'haar', remove_max_haar_ll = True):
+	"""
+	Wavelet Hash computation.
 
+	@image must be a PIL instance.
+	@hash_size must be a power of 2 and less than @image_scale.
+	@image_scale must be power of 2 and less than image size. By default is equal to max
+		power of 2 for an input image.
+	@mode (see modes in pywt library):
+		'haar' - Haar wavelets, by default
+		'db4' - Daubechies wavelets
+	@remove_max_haar_ll - remove the lowest low level (LL) frequency using Haar wavelet.
+	"""
+
+	if image_scale != 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)))
+	ll_max_level = int(numpy.log2(image_scale))
+
+	level = int(numpy.log2(hash_size))
+	assert hash_size == 2**level, "hash_size is not power of 2"
+	assert level <= ll_max_level, "hash_size in a wrong range"
+	dwt_level = ll_max_level - level
+
+	image = image.convert("L").resize((image_scale, image_scale), Image.ANTIALIAS)
+	pixels = numpy.array(image.getdata(), dtype=numpy.float).reshape((image_scale, image_scale))
+	pixels /= 255
+
+	# Remove low level frequency LL(max_ll) if @remove_max_haar_ll using haar filter
+	if remove_max_haar_ll:
+		coeffs = pywt.wavedec2(pixels, 'haar', level = ll_max_level)
+		coeffs = list(coeffs)
+		coeffs[0] *= 0
+		pixels = pywt.waverec2(coeffs, 'haar')
+
+	# Use LL(K) as freq, where K is log2(@hash_size)
+	coeffs = pywt.wavedec2(pixels, mode, level = dwt_level)
+	dwt_low = coeffs[0]
+
+	# Subsitract median and compute hash
+	med = numpy.median(dwt_low)
+	diff = dwt_low > med
+	return ImageHash(diff)