|
#!/opt/local/bin/python2.7
|
|
import bz2
|
|
from collections import defaultdict
|
|
import cPickle
|
|
import imghdr
|
|
import os
|
|
import sys
|
|
|
|
import pHash
|
|
|
|
from image import Image
|
|
|
|
HAMMING_THRESHOLD = 10
|
|
CORRELATION_THRESHOLD = 70.0
|
|
|
|
# Find duplicates by looking over index
|
|
# write some description
|
|
|
|
def find_similar(total_done, index, image):
|
|
index_length = len(index)
|
|
image_digest = image.make_digest()
|
|
|
|
# Search the index
|
|
ctr = 0
|
|
for index_image in index:
|
|
ctr += 1
|
|
percent_done = int((float(ctr) / index_length) * 100)
|
|
sys.stdout.write('\r\tTotal: {:3d}% --- This image: {:3d}%'.format(total_done, percent_done))
|
|
sys.stdout.flush()
|
|
# Original might be in index, skip it
|
|
if image.hash == index_image.hash and image.path == index_image.path:
|
|
continue
|
|
|
|
# Hamming distance hash compare
|
|
hamming_distance = pHash.hamming_distance(image.hash, index_image.hash)
|
|
|
|
# Cross correlation compare
|
|
correlation = pHash.crosscorr(image_digest, index_image.make_digest())[1]
|
|
|
|
# Determine if comparison criteria are within the thresholds
|
|
if hamming_distance <= HAMMING_THRESHOLD or \
|
|
correlation >= CORRELATION_THRESHOLD:
|
|
sys.stdout.write('\r\t--- SIMILAR IMAGE FOUND --- \n')
|
|
print '\tHamming distance: {:d}'.format(hamming_distance)
|
|
print '\tCross correlation: {:f}'.format(correlation)
|
|
print '\tImage path: {:s}\n'.format(index_image.path)
|
|
print
|
|
|
|
|
|
def main():
|
|
|
|
# Make sure at least one command line argument was provided
|
|
if len(sys.argv) < 3:
|
|
print 'Usage: find_similar.py <image dir root path> <index path>'
|
|
return -1;
|
|
|
|
# Print out the path we're walking
|
|
root_path = sys.argv[1]
|
|
index_path = sys.argv[2]
|
|
|
|
# Load image index
|
|
index_file = bz2.BZ2File(index_path, 'r')
|
|
image_index = cPickle.load(index_file)
|
|
index_file.close()
|
|
|
|
print 'Looking for similar images from from path: {:s}'.format(root_path)
|
|
|
|
# Walk the root path and count all images
|
|
# (is there a better way to do this?)
|
|
image_counter = 0
|
|
for root, dirs, files in os.walk(root_path):
|
|
for file in files:
|
|
image_path = os.path.join(root, file)
|
|
# Check the make sure the file is a JPEG
|
|
if not imghdr.what(image_path) == 'jpeg':
|
|
continue
|
|
image_counter += 1
|
|
print 'Done counting, {:d} images total.'.format(image_counter)
|
|
|
|
# Walk the root path
|
|
ctr = 0
|
|
for root, dirs, files in os.walk(root_path):
|
|
for file in files:
|
|
image_path = os.path.join(root, file)
|
|
# Check the make sure the file is a JPEG
|
|
if not imghdr.what(image_path) == 'jpeg':
|
|
continue
|
|
ctr += 1
|
|
percent_done = int((float(ctr) / image_counter) * 100)
|
|
print '\n\nLooking for similar -- {:s}'.format(image_path)
|
|
image_obj = Image(image_path)
|
|
# Find similar images by searching the index
|
|
find_similar(percent_done, image_index, image_obj)
|
|
|
|
print '\nDone.'
|
|
|
|
if __name__ == '__main__':
|
|
sys.exit(main())
|