Develop Reference

How can I make cluster of near similar images in dictionary based on imageHash without repeating same images in Dictionary

So i have a folder with images I am trying to make cluster of near similar images in a python dictionary with Imagehash as the key and a list of similar images as their value, how can i prevent for a image to generate a new key if it's already present in any of the other dictionary key list here is the code that I have done so far:
from PIL import Image
import imagehash
import cv2
import numpy as np
import dhash
import distance
norm_cache: dict = dict()
def _get_image(image_path: str) -> Image:
try:
img_arr = cv2.imread(image_path)
img_arr = cv2.resize(img_arr, (512, 512), interpolation=cv2.INTER_AREA)
# Convert image into 3 channels if it contains 4
if len(img_arr.shape) > 2 and img_arr.shape[2] == 4:
img_arr = cv2.cvtColor(img_arr, cv2.COLOR_BGRA2BGR)
# using W3C luminance calc to convert into gray-scale
data = np.inner(img_arr, [299, 587, 114]) / 1000.0
return Image.fromarray(np.uint8(data),"L")
except SyntaxError:
pass
def find_similar_images(userpath):
import os
global norm_cache
def is_image(filename):
f = filename.lower()
return f.endswith(".png") or f.endswith(".jpg") or \
f.endswith(".jpeg") or f.endswith(".bmp") or f.endswith(".gif")
image_filenames = [os.path.join(userpath, path) for path in os.listdir(userpath) if is_image(path)]
images = {}
buffer = []
for img in image_filenames:
if (len(buffer) == 0):
print("Original list is empty, Appending first image to buffer.")
buffer.append(img)
continue
gray1 = _get_image(img)
h1r,h1c = dhash.dhash_row_col(gray1)
hash1 = dhash.format_hex(h1r,h1c)
images[hash1] = images.get(hash1, []) + [img]
for each in buffer:
if each in norm_cache:
print(f"cached val found for {each}")
gray2 = norm_cache[each]
h2r,h2c = dhash.dhash_row_col(gray2)
hash2 = dhash.format_hex(h2r,h2c)
else:
print("No cached_val found, Computing and storing in norm_cache")
gray2 = _get_image(each)
h2r,h2c = dhash.dhash_row_col(gray2)
hash2 = dhash.format_hex(h2r,h2c)
norm_cache[each] = gray2 # Update cache...
print(f"Comparing ---> {img}:{hash1} with {each}:{hash2}")
if(distance.hamming(hash1,hash2) <= 22):
//what should i put in here
unique = 0
for k, img_list in images.items():
if(len(img_list) >= 1):
print(''.join(img_list))
unique = unique + 1
print(unique)
if __name__ == '__main__':
import sys, os
userpath = <Image folder/>
find_similar_images(userpath=userpath)

Set Author, Title, and Subject for PDF using Reportlab

How can you correctly set the Author, Title and Subject attributes for a PDF File using Reportlab?
I have found the methods in the Reportlab User Guide on page 56, but I am not sure how to implement them correctly.
Below in my PDF cropping and scaling script, I have added the annotations method, but I don't know where to call them from, or if a whole new Canvas object is needed. Please excuse the lengthy code, but only after line 113 is the doc being created, above are mostly auxiliary methods, including the annotations method on line 30.
# All the necessary parameters are accessible after line 92,
# but can of course be changed manually in the Code
# imports for the crop, rename to avoid conflict with reportlab Image import
from PIL import Image as imgPIL
from PIL import ImageChops, ImageOps, ImageFilter
import os.path, sys
# import for the PDF creation
import glob
from reportlab.lib.pagesizes import A4
from reportlab.lib import utils
from reportlab.platypus import Image, SimpleDocTemplate, Spacer
from reportlab.pdfgen import canvas
# get os path for Cropping
path = (os.path.dirname(os.path.abspath("cropPDF.py")))
dirs = os.listdir(path)
def trim(im, border="white"):
bg = imgPIL.new(im.mode, im.size, border)
diff = ImageChops.difference(im, bg)
bbox = diff.getbbox()
if bbox:
return im.crop(bbox)
def annotations(canvas):
canvas.setAuthor("the ReportLab Team")
canvas.setTitle("ReportLab PDF Generation User Guide")
canvas.setSubject("How to Generate PDF files using the ReportLab modules")
def findMaxWidth():
maxWidth = 0
for item in dirs:
try:
fullpath = os.path.join(path, item)
if os.path.isfile(fullpath):
im = imgPIL.open(fullpath)
maxWidth = max(maxWidth, im.size[0])
except:
pass
return maxWidth
def padImages(docHeight):
maxWidth = findMaxWidth()
for item in dirs:
try:
fullpath = os.path.join(path, item)
if os.path.isfile(fullpath):
im = imgPIL.open(fullpath)
f, e = os.path.splitext(fullpath)
width, height = im.size # get the image dimensions, the height is needed for the blank image
if not docHeight <= height: # to prevent oversized images from bein padded, such that they remain centered
image = imgPIL.new('RGB', (maxWidth, height),
(255, 255, 255)) # create a white image with the max width
image.paste(im, (0, 0)) # paste the original image overtop the blank one, flush on the left side
image.save(f + ".png", "PNG", quality=100)
except:
pass
def crop():
for item in dirs:
try:
fullpath = os.path.join(path, item)
if os.path.isfile(fullpath):
im = imgPIL.open(fullpath)
f, e = os.path.splitext(fullpath)
imCrop = trim(im, "white")
imCrop.save(f + ".png", "PNG", quality=100)
except:
pass
def add_page_number(canvas, doc):
canvas.saveState()
canvas.setFont('Times-Roman', numberFontSize)
page_number_text = "%d" % (doc.page)
canvas.drawCentredString(
pageNumberSpacing * mm,
pageNumberSpacing * mm,
page_number_text
)
canvas.restoreState()
#############################
executeCrop = True
executePad = True
outputName = "output.pdf" #The name of the file that will be created
fileAuthor = "Roman Stadler" #these 3 attributes are visible in the file info menu
fileTitle = ""
fileSubject = ""
margin = 0.5
imageWidthDefault = 550
spacerHeight = 7
scalingIfImageTooTall = 0.95 # larger than 95 can result in an empty page after the image
includePagenumbers = True
numberFontSize = 10
pageNumberSpacing = 5
############################
doc = SimpleDocTemplate(
outputName,
topMargin=margin * mm,
leftMargin=margin * mm,
rightMargin=margin * mm,
bottomMargin=margin * mm,
pagesize=A4
)
if executeCrop:
crop()
if executePad:
padImages(doc.height)
filelist = glob.glob("*.png") # Get a list of files in the current directory
filelist.sort()
story = [] # create the list of images for the PDF
for fn in filelist:
img = utils.ImageReader(fn)
img_width, img_height = img.getSize() # necessary for the aspect ratio
aspect = img_height / float(img_width)
documentHeight = doc.height
imageWidth = imageWidthDefault
imageHeight = imageWidth * aspect
if imageHeight > documentHeight:
imageHeight = documentHeight * scalingIfImageTooTall
imageWidth = imageHeight / aspect
img = Image(
fn,
width=imageWidth,
height=imageHeight
)
story.append(img)
space = Spacer(width=0, height=spacerHeight)
story.append(space)
if includePagenumbers and not len(filelist) == 0: # if pagenumbers are desired, or not
doc.build(
story,
onFirstPage=add_page_number,
onLaterPages=add_page_number,
)
elif not len(filelist) == 0:
doc.build(story)
else: # to prevent an empty PDF that can't be opened
print("no files found")

In the meantime, I have found another way, that does not use reportlab, but instead relies on PyPDF2:
The following import is needed:
# PyPDF2 for the metadata modification
from PyPDF2 import PdfFileReader, PdfFileWriter
Then the metadata can be edited like this:
author = "Roman Stadler"
title = "CropPDF"
subject = "Stackoverflow"
#rest of the script
#attemp the metadate edit
try:
file = open('output.pdf', 'rb+')
reader = PdfFileReader(file)
writer = PdfFileWriter()
writer.appendPagesFromReader(reader)
metadata = reader.getDocumentInfo()
writer.addMetadata(metadata)
writer.addMetadata({
'/Author': author,
'/Title': title,
'/Subject' : subject,
'/Producer' : "CropPDF",
'/Creator' : "CropPDF",
})
writer.write(file)
file.close()
except:
print("Error while editing metadata")

You can define attributes like the author when defining the doc as a SimpleDocTemplate
doc = SimpleDocTemplate(
outputName,
topMargin=margin * mm,
leftMargin=margin * mm,
rightMargin=margin * mm,
bottomMargin=margin * mm,
pagesize=A4,
title="This is the title of the document", #exchange with your title
author="John Smith", #exchange with your authors name
subject"Adding metadata to pdf via reportlab" #exchange with your subject
)

Merging and saving images in PIL Python

I have two folders of images and I am trying to build one large image from all the slices in each folder. I need to alternate between folders to build the image. For example the first slice comes from folder 1, the second slice comes from folder 2, the third from folder 1 ect. I have the files ordered by filename in the individual folders so I am trying to iterate through the folders and add a new strip to an image. The code runs BUT it doesn't seem to be saving the composite image. I am new to PIL, so I am sure that it is something simple, but your help is appreciated. Thanks!
def merge_images(file1, file2):
"""Merge two images into one, displayed above and below
:param file1: path to first image file
:param file2: path to second image file
:return: the merged Image object
"""
if file1.startswith('.'):
return None
image1 = Image.open(file1)
image2 = Image.open(file2)
(width1, height1) = image1.size
(width2, height2) = image2.size
result_width = width1 + width2
result_height = max(height1, height2)
result = Image.new('RGB', (result_width, result_height))
result.paste(im=image1, box=(0, 0))
result.paste(im=image2, box=(0, height1))
return result
imageCounter = 0
firstPass = True
compImage = Image.new('RGBA', img.size, (0,0,0,0))
for i in range(len(boundingBoxes)+1):
if firstPass:
compImage = merge_images('./image_processing/'+ os.listdir('./image_processing/')[imageCounter],
'./img_patches/outputs/'+os.listdir('./img_patches/outputs/')[imageCounter])
if compImage is not None:
firstPass = False
compImage.save('./image_processing/compImage.jpg')
else:
compImage = merge_images('./image_processing/compImage.jpg','./image_processing/'+ os.listdir('./image_processing/')[imageCounter])
compImage.save('./image_processing/compImage.jpg')
compImage = merge_images('./image_processing/compImage.jpg','./img_patches/outputs/'+ os.listdir('./img_patches/outputs/')[imageCounter])
compImage.save('./image_processing/compImage.jpg')
imageCounter = imageCounter + 1

You have to tell PIL to save the images:
for i in range(len(boundingBoxes)+1):
if firstPass:
compImage = merge_images('./image_processing/'+ os.listdir('./image_processing/')[imageCounter],
'./img_patches/outputs/'+os.listdir('./img_patches/outputs/')[imageCounter])
compImage.save(open('output/{}.png'.format(imageCounter), 'w'))

stitch images together in python

I am trying to stitch about 50 images(all in the same 287x287 size) together. Specifically, there should be 25 images on the top row and 25 images on the bottom row, and there also exists a small distance between each two images.
I met two difficulties during my attempts:
First problem is that there are 25 images in a folder with their name 'prefix-70',...,'prefix-94' while other 25 images in another folder with the same name 'prefix-70',...,'prefix-94'. I do not know how to them in Python without conflicts.
Second problem is that I wrote the following code to read one folder images to form a row but it outputs a column.
#!/usr/bin/python3.0
#encoding=utf-8
import numpy as np
from PIL import Image
import glob,os
if __name__=='__main__':
#prefix=input('Input the prefix of images:')
prefix = 'prefix'
files=glob.glob(prefix+'-*')
num=len(files)
filename_lens=[len(x) for x in files] #length of the files
min_len=min(filename_lens) #minimal length of filenames
max_len=max(filename_lens) #maximal length of filenames
if min_len==max_len:#the last number of each filename has the same length
files=sorted(files) #sort the files in ascending order
else:
index=[0 for x in range(num)]
for i in range(num):
filename=files[i]
start=filename.rfind('-')+1
end=filename.rfind('.')
file_no=int(filename[start:end])
index[i]=file_no
index=sorted(index)
files=[prefix+'-'+str(x)+'.png' for x in index]
print(files[0])
baseimg=Image.open(files[0])
sz=baseimg.size
basemat=np.atleast_2d(baseimg)
for i in range(1,num):
file=files[i]
im=Image.open(file)
im=im.resize(sz,Image.ANTIALIAS)
mat=np.atleast_2d(im)
print(file)
basemat=np.append(basemat,mat,axis=0)
final_img=Image.fromarray(basemat)
final_img.save('merged.png')
I guess i have got into a wrong way...
How can i stitch them properly? Any suggestion is appreciated.

Try this (explanation in comments):
from PIL import Image
from os import listdir, path
space_between_row = 10
new_image_path = 'result.jpg'
im_dirs = ['images/1', 'images/2']
# get sorted list of images
im_path_list = [[path.join(p, f) for f in sorted(listdir(p))] for p in im_dirs]
# open images and calculate total widths and heights
im_list = []
total_width = 0
total_height = 0
for path_list in im_path_list:
images = list(map(Image.open, path_list))
widths, heights = zip(*(i.size for i in images))
total_width = max(total_width, sum(widths))
total_height += max(heights)
im_list.append(images)
# concat images
new_im = Image.new('RGB', (total_width, total_height))
y_offset = 0
for images in im_list:
x_offset = 0
max_height = 0
for im in images:
new_im.paste(im, (x_offset, y_offset))
x_offset += im.size[0]
max_height = max(im.size[1], max_height)
y_offset = y_offset + max_height + space_between_row
# show and save
new_im.show()
new_im.save(new_image_path)

Install ImageMagick, then tell it where your two directories are.
#!/usr/bin/python3
##=========================================================
## required ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
##
## imagemagick.org/script/download.php
##
##=========================================================
## libs ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
import subprocess as sp
##=========================================================
## vars ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
offset = 2 ## pixel gap between images
color = '#000000' ## background color to fill gaps
dir1 = '/home/me/Pictures/topRow/'
dir2 = '/home/me/Pictures/bottomRow/'
## note: windows dirs use double backslashes
## 'C:\\Users\\me\\Pictures\\topRow\\'
##=========================================================
## script ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
row1args = ['convert', '+smush', offset, '-background', color, dir1 + '*.png', 'row1.png']
row2args = ['convert', '+smush', offset, '-background', color, dir2 + '*.png', 'row2.png']
merge = ['convert', '-smush', offset, '-background', color, 'row*.png', 'merged.png']
##=========================================================
## main ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
sp .call(row1args)
sp .call(row2args)
sp .call(merge)
##=========================================================
## eof ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

compare a single image with 10 or more images and find the matching one

when i run the program I need my code to :
initialize the camera
take a picture
request user to enter paths for the current image to be stored and the image to be compared to
detect edges of currently taken picture and save in database
compare current edge image to 10 or more edge images in database
output as the edge image that has highest match percentage with current edge image
basically its like an object identification program ... can someone please help me out ?
here is the code i have done so far
from itertools import izip
import numpy as np
import cv2
from matplotlib import pyplot as plt
from PIL import Image
def take_and_save_picture(im_save):
'''Take a picture and save it
Args:
im_save: filepath where the image should be stored
'''
camera_port = 0
ramp_frames = 30
cap = cv2.VideoCapture(camera_port)
def get_image():
retval, im = cap.read()
return im
for i in xrange(ramp_frames):
temp = get_image()
print("Taking image...")
# Take the actual image we want to keep
camera_capture = get_image()
#im_save_tmp = im_save + '.jpg'
im_save_tmp = im_save
# A nice feature of the imwrite method is that it will automatically choose the
# correct format based on the file extension you provide. Convenient!
cv2.imwrite(im_save_tmp, camera_capture)
# You'll want to release the camera, otherwise you won't be able to create a new
# capture object until your script exits
# del(cap)
img1 = cv2.imread(im_save_tmp, 0)
edges = cv2.Canny(img1, 100, 200)
cv2.imwrite(im_save, edges)
cv2.waitKey(0)
cv2.destroyAllWindows()
#im1 = "/Users/Me/gop.jpg"
#im2 = "/Users/Me/aarthi.jpg"
im1 = input('enter the path of database file')
im2 = input('enter the path where captured image is to be saved')
#im1="/Users/Me/home1.png"
#im2="/Users/Me/home.png"
def compute_edges_diff(im1, im2):
'''Compute edges diff between to image files.
Args:
im1: filepath to the first image
im2: filepath to the second image
Returns:
float: percentage of difference between images
'''
#for no_file1 in range(0,10):
#template = cv2.imread('numbers1/{no_file}.png'.format(no_file=no_file1),0)
i1 = Image.open(im1)
i2 = Image.open(im2)
assert i1.mode == i2.mode, "Different kinds of images."
assert i1.size == i2.size, "Different sizes."
pairs = izip(i1.getdata(), i2.getdata())
if len(i1.getbands()) == 1:
# for gray-scale jpegs
dif = sum(abs(p1-p2) for p1,p2 in pairs)
else:
dif = sum(abs(c1-c2) for p1,p2 in pairs for c1,c2 in zip(p1,p2))
ncomponents = i1.size[0] * i1.size[1] * 3
diff = (dif / 255.0 * 100) / ncomponents
return diff
def main():
#capture_img = "/Users/Me/home1.png"
capture_img = input('enter path of the file from database')
#img_to_compare = "/Users/Me/Documents/python programs/compare/img2.jpg"
take_and_save_picture(capture_img)
diff = compute_edges_diff(im1, im2)
print "Difference (percentage):", diff
if diff > 0.5:
print im1
else :
print im2
if __name__ == '__main__':
main()
#del(cap)
this code works fine .. but i am able to compare only one image ... i need to compare the current taken images with all images in my database ...

In your main function, create a list to ask for the path for the image files, wrap the compare in a for loop:
def get_images_to_compare():
images_to_compare = []
while True:
comp_img = raw_input("Path of image to compare to: ")
if len(comp_img) <= 1:
# break if someone just hits enter
break
images_to_compare.append(comp_img)
return images_to_compare
def main():
#capture_img = "/Users/Me/home1.png"
capture_img = input('enter path of the file from database')
#img_to_compare = "/Users/Me/Documents/python programs/compare/img2.jpg"
take_and_save_picture(capture_img)
#### you have some odd var names here, basic gist, add a for loop
for comp_image in get_images_to_compare():
diff = compute_edges_diff(im1, im2)
print "Difference (percentage):", diff
if diff > 0.5:
print im1
else:
print im2
as a suggestion, avoid having global scope vars intermingled between functions, it makes code hard to read (referring to you setting im1 and im2 between two fn defs.
Code for doing the multiple compares:
def main(folder_path_to_search, files_to_compare_to, source_image_path):
#capture_img = "/Users/Me/home1.png"
capture_img = input('enter path of the file from database')
#img_to_compare = "/Users/Me/Documents/python programs/compare/img2.jpg"
take_and_save_picture(capture_img)
images_to_compare = [ os.path.join(folder_path_to_search,file_path) for file_path in os.listdir(folder_path_to_search) if file_path.endswith(files_to_compare_to) ]
for comp_image in get_images_to_compare():
diff = compute_edges_diff(source_image_path, comp_image)
print "Difference (percentage):", diff, "(", source_image_path, ":", comp_image, ")"
if __name__ == '__main__':
folder_path_to_search = raw_input("Enter folder path to search")
files_to_compare_to = raw_input("enter file extention to glob ex: '.jpg'")
source_image_path = raw_input("enter full file path of source image")
main(folder_path_to_search, files_to_compare_to, source_image_path)