Related
I'm working on a system that does fuzzy image deduplication.
Right now, I have a functional system that can do large-scale phash fuzzy image searching and deduplication via either DCT-based or gradient-based perceptual hashes.
However, while determining if an image has been reduced in size is programatically trivial, how can I determine which image is the parent of which?
Basically, if I have two images with the same resolution, where one is a resaved version of the other (either in a different format (jpg/png), or simply recompressed), how can I determine which one is the original in a reliable manner?
(Note: Assume all metadata has been stripped from the images, I wish it were that simple.)
Bonus points if any solution is fairly easy to implement in python.
This isn't a positive answer, but I spent a while of time evaluating the use of average entropy per-pixel to determine if it could be a useful metric for determining how compressed an image is.
I have a write up here.
Some excerpts:
Variance in entropy across compression levels on SIPI reference image database images.
In retrospect, the x-axis should be labeled "JPEG Quality level". Higher numbers mean better quality
While per-pixel entropy does decline sharply at extremely aggressive compression levels, it does not vary in a way that correlates well with compression level.
This means that any attempt to compare two images by inspecting the entropy will likely have issues unless one knows exactly what compression level the image had been resaved at.
I'm looking to do some javascript powered animation via image clipping. Here's an example of what I'm talking about: http://www.def-logic.com/_dhtml/freejack/hero1.gif
I know png uses a kind of prediction in its compression, what would be the best way to lay out an image like the one above so that I get the most out of the compression? I'm especially interested when the images are very similar, more so than the one above, so there is a lot of potential for compression due to redundancy.
For example, is there specific size of tile that would work well?
For example, is there specific size of tile that would work well?
Not really. PNG prediction is strictly local (it uses the 3 neighbours pixels), and the prediction ("filter") strategy can be chosen on a line basis.
That kind of redundancy is not very detectable in PNG compression (not in JPG or practically any other, actually).
If you have the freedom to select the distribution of tiles (few or many per row), you can try vary that, it can have some small influence (to have an image with many short lines instead of few long lines can give the filter better opportunities to select different filters) but, again, I'd bet that the difference will be very small.
For example, I have an 1024*768 JPEG image. I want to estimate the size of the image which will be scaled down to 800*600 or 640*480. Is there any algorithm to calculate the size without generating the scaled image?
I took a look in the resize dialog in Photoshop. The size they show is basically (width pixels * height pixels * bit/pixel) which shows a huge gap between the actual file size.
I have mobile image browser application which allow user to send image through email with options to scale down the image. We provide check boxes for the user to choose down-scale resolution with the estimate size. For large image (> 10MB), we have 3 down scale size to choose from. If we generate a cached image for each option, it may hurt the memory. We are trying to find the best solution which avoid memory consumption.
I have successfully estimated the scaled size based on the DQT - the quality factor.
I conducted some experiments and find out if we use the same quality factor as in the original JPEG image, the scaled image will have size roughly equal to (scale factor * scale factor) proportion of the original image size. The quality factor can be estimate based on the DQT defined in the every JPEG image. Algorithm has be defined to estimate the quality factor based on the standard quantization table shown in Annex K in JPEG spec.
Although other factors like color subsampling, different compression algorithm and the image itself will contribute to error, the estimation is pretty accurate.
P.S. By examining JPEGSnoop and it source code, it helps me a lot :-)
Cheers!
Like everyone else said, the best algorithm to determine what sort of JPEG compression you'll get is the JPEG compression algorithm.
However, you could also calculate the Shannon entropy of your image, in order to try and understand how much information is actually present. This might give you some clues as to the theoretical limits of your compression, but is probably not the best solution for your problem.
This concept will help you measure the differences in information between an all white image and that of a crowd, which is related to it's compressibility.
-Brian J. Stinar-
Why estimate what you can measure?
In essence, it's impossible to provide any meaningful estimate due to the fact that different types of images (in terms of their content) will compress very differently using the JPEG algorithm. (A 1024x768 pure white image will be vastly smaller than a photograph of a crowd scene for example.)
As such, if you're after an accurate figure it would make sense to simply carry out the re-size.
Alternatively, you could just provide an range such as "40KB to 90KB", based on an "average" set of images.
I think what you want is something weird and difficult to do. Based on JPG compression level some images are heavier that others in terms of heavier (size).
My hunch for JPEG images: Given two images at same resolution, compressed at the same quality ratio - the image taking smaller memory will compress more (in general) when its resolution is reduced.
Why? From experience: many times when working with a set of images, I have seen that if a thumbnail is occupying significantly more memory than most others, reducing its resolution has almost no change in the size (memory). On other hand, reducing resolution of one of the average size thumbnails reduces the size significantly. (all parameters like original/final resolution and JPEG quality being the same in the two cases).
Roughly speaking - higher the entropy, less will be the impact on size of image by changing resolution (at the same JPEG quality).
If you can verify this with experiments, maybe you can use this as a quick method to estimate the size. If my language is confusing, I can explain with some mathematical notation/psuedo formula.
An 800*600 image file should be roughly (800*600)/(1024*768) times as large as the 1024*768 image file it was scaled down from. But this is really a rough estimate, because the compressibility of original and scaled versions of the image might be different.
Before I attempt to answer your question, I'd like to join the ranks of people that think it's simpler to measure rather than estimate. But it's still an interesting question, so here's my answer:
Look at the block DCT coefficients of the input JPEG image. Perhaps you can find some sort of relationship between the number of higher frequency components and the file size after shrinking the image.
My hunch: all other things (e.g. quantization tables) being equal, the more higher frequency components you have in your original image, the bigger the difference in file size between the original and shrinked image will be.
I think that by shrinking the image, you will reduce some of the higher frequency components during interpolation, increasing the possibility that they will be quantized to zero during the lossy quantization step.
If you go down this path, you're in luck: I've been playing with JPEG block DCT coefficients and put some code up to extract them.
I need to create fingerprints of many images (about 100.000 existing, 1000 new per day, RGB, JPEG, max size 800x800) to compare every image to every other image very fast. I can't use binary compare methods because also images which are nearly similar should be recognized.
Best would be an existing library, but also some hints to existing algorithms would help me a lot.
Normal hashing or CRC calculation algorithms do not work well with image data. The dimensional nature of the information must be taken into account.
If you need extremely robust fingerprinting, such that affine transformations (scaling, rotation, translation, flipping) are accounted for, you can use a Radon transformation on the image source to produce a normative mapping of the image data - store this with each image and then compare just the fingerprints. This is a complex algorithm and not for the faint of heart.
a few simple solutions are possible:
Create a luminosity histogram for the image as a fingerprint
Create scaled down versions of each image as a fingerprint
Combine technique (1) and (2) into a hybrid approach for improved comparison quality
A luminosity histogram (especially one that is separated into RGB components) is a reasonable fingerprint for an image - and can be implemented quite efficiently. Subtracting one histogram from another will produce a new historgram which you can process to decide how similar two images are. Histograms, because the only evaluate the distribution and occurrence of luminosity/color information handle affine transformations quite well. If you quantize each color component's luminosity information down to an 8-bit value, 768 bytes of storage are sufficient for the fingerprint of an image of almost any reasonable size. Luminosity histograms produce false negatives when the color information in an image is manipulated. If you apply transformations like contrast/brightness, posterize, color shifting, luminosity information changes. False positives are also possible with certain types of images ... such as landscapes and images where a single color dominates others.
Using scaled images is another way to reduce the information density of the image to a level that is easier to compare. Reductions below 10% of the original image size generally lose too much of the information to be of use - so an 800x800 pixel image can be scaled down to 80x80 and still provide enough information to perform decent fingerprinting. Unlike histogram data, you have to perform anisotropic scaling of the image data when the source resolutions have varying aspect ratios. In other words, reducing a 300x800 image into an 80x80 thumbnail causes deformation of the image, such that when compared with a 300x500 image (that's very similar) will cause false negatives. Thumbnail fingerprints also often produce false negatives when affine transformations are involved. If you flip or rotate an image, its thumbnail will be quite different from the original and may result in a false positive.
Combining both techniques is a reasonable way to hedge your bets and reduce the occurence of both false positives and false negatives.
There is a much less ad-hoc approach than the scaled down image variants that have been proposed here that retains their general flavor, but which gives a much more rigorous mathematical basis for what is going on.
Take a Haar wavelet of the image. Basically the Haar wavelet is the succession of differences from the lower resolution images to each higher resolution image, but weighted by how deep you are in the 'tree' of mipmaps. The calculation is straightforward. Then once you have the Haar wavelet appropriately weighted, throw away all but the k largest coefficients (in terms of absolute value), normalize the vector and save it.
If you take the dot product of two of those normalized vectors it gives you a measure of similarity with 1 being nearly identical. I posted more information over here.
You should definitely take a look at phash.
For image comparison there is this php project :
https://github.com/kennethrapp/phasher
And my little javascript clone:
https://redaktor.me/phasher/demo_js/index.html
Unfortunately this is "bitcount"-based but will recognize rotated images.
Another approach in javascript was to build a luminosity histogram from the image by the help of canvas. You can visualize a polygon histogram on the canvas and compare that polygon in your database (e.g. mySQL spatial ...)
A long time ago I worked on a system that had some similar characteristics, and this is an approximation of the algorithm we followed:
Divide the picture into zones. In our case we were dealing with 4:3 resolution video, so we used 12 zones. Doing this takes the resolution of the source images out of the picture.
For each zone, calculate an overall color - the average of all pixels in the zone
For the entire image, calculate an overall color - the average of all zones
So for each image, you're storing n + 1 integer values, where n is the number of zones you're tracking.
For comparisons, you also need to look at each color channel individually.
For the overall image, compare the color channels for the overall colors to see if they are within a certain threshold - say, 10%
If the images are within the threshold, next compare each zone. If all zones also are within the threshold, the images are a strong enough match that you can at least flag them for further comparison.
This lets you quickly discard images that are not matches; you can also use more zones and/or apply the algorithm recursively to get stronger match confidence.
Similar to Ic's answer - you might try comparing the images at multiple resolutions. So each image get saved as 1x1, 2x2, 4x4 .. 800x800. If the lowest resolution doesn't match (subject to a threshold), you can immediately reject it. If it does match, you can compare them at the next higher resolution, and so on..
Also - if the images share any similar structure, such as medical images, you might be able to extract that structure into a description that is easier/faster to compare.
As of 2015 (back to the future... on this 2009 question which is now high-ranked in Google) image similarity can be computed using Deep Learning techniques. The family of algorithms known as Auto Encoders can create a vector representation which is searchable for similarity. There is a demo here.
One way you can do this is to resize the image and drop the resolution significantly (to 200x200 maybe?), storing a smaller (pixel-averaged) version for doing the comparison. Then define a tolerance threshold and compare each pixel. If the RGB of all pixels are within the tolerance, you've got a match.
Your initial run through is O(n^2) but if you catalog all matches, each new image is just an O(n) algorithm to compare (you only have to compare it to each previously inserted image). It will eventually break down however as the list of images to compare becomes larger, but I think you're safe for a while.
After 400 days of running, you'll have 500,000 images, which means (discounting the time to resize the image down) 200(H)*200(W)*500,000(images)*3(RGB) = 60,000,000,000 comparisons. If every image is an exact match, you're going to be falling behind, but that's probably not going to be the case, right? Remember, you can discount an image as a match as soon as a single comparison falls outside your threshold.
Do you literally want to compare every image against the others? What is the application? Maybe you just need some kind of indexing and retrieval of images based on certain descriptors? Then for example you can look at MPEG-7 standard for Multimedia Content Description Interface. Then you could compare the different image descriptors, which will be not that accurate but much faster.
So you want to do "fingerprint matching" that's pretty different than "image matching". Fingerprints' analysis has been deeply studied during the past 20 years, and several interesting algorithms have been developed to ensure the right detection rate (with respect to FAR and FRR measures - False Acceptance Rate and False Rejection Rate).
I suggest you to better look to LFA (Local Feature Analysis) class of detection techniques, mostly built on minutiae inspection. Minutiae are specific characteristics of any fingerprint, and have been classified in several classes. Mapping a raster image to a minutiae map is what actually most of Public Authorities do to file criminals or terrorists.
See here for further references
For iPhone image comparison and image similarity development check out:
http://sites.google.com/site/imagecomparison/
To see it in action, check out eyeBuy Visual Search on the iTunes AppStore.
It seems that specialised image hashing algorithms are an area of active research but perhaps a normal hash calculation of the image bytes would do the trick.
Are you seeking byte-identical images rather than looking for images that are derived from the same source but may be a different format or resolution (which strikes me as a rather hard problem).
Given two different image files (in whatever format I choose), I need to write a program to predict the chance if one being the illegal copy of another. The author of the copy may do stuff like rotating, making negative, or adding trivial details (as well as changing the dimension of the image).
Do you know any algorithm to do this kind of job?
These are simply ideas I've had thinking about the problem, never tried it but I like thinking about problems like this!
Before you begin
Consider normalising the pictures, if one is a higher resolution than the other, consider the option that one of them is a compressed version of the other, therefore scaling the resolution down might provide more accurate results.
Consider scanning various prospective areas of the image that could represent zoomed portions of the image and various positions and rotations. It starts getting tricky if one of the images are a skewed version of another, these are the sort of limitations you should identify and compromise on.
Matlab is an excellent tool for testing and evaluating images.
Testing the algorithms
You should test (at the minimum) a large human analysed set of test data where matches are known beforehand. If for example in your test data you have 1,000 images where 5% of them match, you now have a reasonably reliable benchmark. An algorithm that finds 10% positives is not as good as one that finds 4% of positives in our test data. However, one algorithm may find all the matches, but also have a large 20% false positive rate, so there are several ways to rate your algorithms.
The test data should attempt to be designed to cover as many types of dynamics as possible that you would expect to find in the real world.
It is important to note that each algorithm to be useful must perform better than random guessing, otherwise it is useless to us!
You can then apply your software into the real world in a controlled way and start to analyse the results it produces. This is the sort of software project which can go on for infinitum, there are always tweaks and improvements you can make, it is important to bear that in mind when designing it as it is easy to fall into the trap of the never ending project.
Colour Buckets
With two pictures, scan each pixel and count the colours. For example you might have the 'buckets':
white
red
blue
green
black
(Obviously you would have a higher resolution of counters). Every time you find a 'red' pixel, you increment the red counter. Each bucket can be representative of spectrum of colours, the higher resolution the more accurate but you should experiment with an acceptable difference rate.
Once you have your totals, compare it to the totals for a second image. You might find that each image has a fairly unique footprint, enough to identify matches.
Edge detection
How about using Edge Detection.
(source: wikimedia.org)
With two similar pictures edge detection should provide you with a usable and fairly reliable unique footprint.
Take both pictures, and apply edge detection. Maybe measure the average thickness of the edges and then calculate the probability the image could be scaled, and rescale if necessary. Below is an example of an applied Gabor Filter (a type of edge detection) in various rotations.
Compare the pictures pixel for pixel, count the matches and the non matches. If they are within a certain threshold of error, you have a match. Otherwise, you could try reducing the resolution up to a certain point and see if the probability of a match improves.
Regions of Interest
Some images may have distinctive segments/regions of interest. These regions probably contrast highly with the rest of the image, and are a good item to search for in your other images to find matches. Take this image for example:
(source: meetthegimp.org)
The construction worker in blue is a region of interest and can be used as a search object. There are probably several ways you could extract properties/data from this region of interest and use them to search your data set.
If you have more than 2 regions of interest, you can measure the distances between them. Take this simplified example:
(source: per2000.eu)
We have 3 clear regions of interest. The distance between region 1 and 2 may be 200 pixels, between 1 and 3 400 pixels, and 2 and 3 200 pixels.
Search other images for similar regions of interest, normalise the distance values and see if you have potential matches. This technique could work well for rotated and scaled images. The more regions of interest you have, the probability of a match increases as each distance measurement matches.
It is important to think about the context of your data set. If for example your data set is modern art, then regions of interest would work quite well, as regions of interest were probably designed to be a fundamental part of the final image. If however you are dealing with images of construction sites, regions of interest may be interpreted by the illegal copier as ugly and may be cropped/edited out liberally. Keep in mind common features of your dataset, and attempt to exploit that knowledge.
Morphing
Morphing two images is the process of turning one image into the other through a set of steps:
Note, this is different to fading one image into another!
There are many software packages that can morph images. It's traditionaly used as a transitional effect, two images don't morph into something halfway usually, one extreme morphs into the other extreme as the final result.
Why could this be useful? Dependant on the morphing algorithm you use, there may be a relationship between similarity of images, and some parameters of the morphing algorithm.
In a grossly over simplified example, one algorithm might execute faster when there are less changes to be made. We then know there is a higher probability that these two images share properties with each other.
This technique could work well for rotated, distorted, skewed, zoomed, all types of copied images. Again this is just an idea I have had, it's not based on any researched academia as far as I am aware (I haven't look hard though), so it may be a lot of work for you with limited/no results.
Zipping
Ow's answer in this question is excellent, I remember reading about these sort of techniques studying AI. It is quite effective at comparing corpus lexicons.
One interesting optimisation when comparing corpuses is that you can remove words considered to be too common, for example 'The', 'A', 'And' etc. These words dilute our result, we want to work out how different the two corpus are so these can be removed before processing. Perhaps there are similar common signals in images that could be stripped before compression? It might be worth looking into.
Compression ratio is a very quick and reasonably effective way of determining how similar two sets of data are. Reading up about how compression works will give you a good idea why this could be so effective. For a fast to release algorithm this would probably be a good starting point.
Transparency
Again I am unsure how transparency data is stored for certain image types, gif png etc, but this will be extractable and would serve as an effective simplified cut out to compare with your data sets transparency.
Inverting Signals
An image is just a signal. If you play a noise from a speaker, and you play the opposite noise in another speaker in perfect sync at the exact same volume, they cancel each other out.
(source: themotorreport.com.au)
Invert on of the images, and add it onto your other image. Scale it/loop positions repetitively until you find a resulting image where enough of the pixels are white (or black? I'll refer to it as a neutral canvas) to provide you with a positive match, or partial match.
However, consider two images that are equal, except one of them has a brighten effect applied to it:
(source: mcburrz.com)
Inverting one of them, then adding it to the other will not result in a neutral canvas which is what we are aiming for. However, when comparing the pixels from both original images, we can definatly see a clear relationship between the two.
I haven't studied colour for some years now, and am unsure if the colour spectrum is on a linear scale, but if you determined the average factor of colour difference between both pictures, you can use this value to normalise the data before processing with this technique.
Tree Data structures
At first these don't seem to fit for the problem, but I think they could work.
You could think about extracting certain properties of an image (for example colour bins) and generate a huffman tree or similar data structure. You might be able to compare two trees for similarity. This wouldn't work well for photographic data for example with a large spectrum of colour, but cartoons or other reduced colour set images this might work.
This probably wouldn't work, but it's an idea. The trie datastructure is great at storing lexicons, for example a dictionarty. It's a prefix tree. Perhaps it's possible to build an image equivalent of a lexicon, (again I can only think of colours) to construct a trie. If you reduced say a 300x300 image into 5x5 squares, then decompose each 5x5 square into a sequence of colours you could construct a trie from the resulting data. If a 2x2 square contains:
FFFFFF|000000|FDFD44|FFFFFF
We have a fairly unique trie code that extends 24 levels, increasing/decreasing the levels (IE reducing/increasing the size of our sub square) may yield more accurate results.
Comparing trie trees should be reasonably easy, and could possible provide effective results.
More ideas
I stumbled accross an interesting paper breif about classification of satellite imagery, it outlines:
Texture measures considered are: cooccurrence matrices, gray-level differences, texture-tone analysis, features derived from the Fourier spectrum, and Gabor filters. Some Fourier features and some Gabor filters were found to be good choices, in particular when a single frequency band was used for classification.
It may be worth investigating those measurements in more detail, although some of them may not be relevant to your data set.
Other things to consider
There are probably a lot of papers on this sort of thing, so reading some of them should help although they can be very technical. It is an extremely difficult area in computing, with many fruitless hours of work spent by many people attempting to do similar things. Keeping it simple and building upon those ideas would be the best way to go. It should be a reasonably difficult challenge to create an algorithm with a better than random match rate, and to start improving on that really does start to get quite hard to achieve.
Each method would probably need to be tested and tweaked thoroughly, if you have any information about the type of picture you will be checking as well, this would be useful. For example advertisements, many of them would have text in them, so doing text recognition would be an easy and probably very reliable way of finding matches especially when combined with other solutions. As mentioned earlier, attempt to exploit common properties of your data set.
Combining alternative measurements and techniques each that can have a weighted vote (dependant on their effectiveness) would be one way you could create a system that generates more accurate results.
If employing multiple algorithms, as mentioned at the begining of this answer, one may find all the positives but have a false positive rate of 20%, it would be of interest to study the properties/strengths/weaknesses of other algorithms as another algorithm may be effective in eliminating false positives returned from another.
Be careful to not fall into attempting to complete the never ending project, good luck!
Read the paper: Porikli, Fatih, Oncel Tuzel, and Peter Meer. “Covariance Tracking Using Model Update Based
on Means on Riemannian Manifolds”. (2006) IEEE Computer Vision and Pattern Recognition.
I was successfully able to detect overlapping regions in images captured from adjacent webcams using the technique presented in this paper. My covariance matrix was composed of Sobel, canny and SUSAN aspect/edge detection outputs, as well as the original greyscale pixels.
An idea:
use keypoint detectors to find scale- and transform- invariant descriptors of some points in the image (e.g. SIFT, SURF, GLOH, or LESH).
try to align keypoints with similar descriptors from both images (like in panorama stitching), allow for some image transforms if necessary (e.g. scale & rotate, or elastic stretching).
if many keypoints align well (exists such a transform, that keypoint alignment error is low; or transformation "energy" is low, etc.), you likely have similar images.
Step 2 is not trivial. In particular, you may need to use a smart algorithm to find the most similar keypoint on the other image. Point descriptors are usually very high-dimensional (like a hundred parameters), and there are many points to look through. kd-trees may be useful here, hash lookups don't work well.
Variants:
Detect edges or other features instead of points.
It is indeed much less simple than it seems :-) Nick's suggestion is a good one.
To get started, keep in mind that any worthwhile comparison method will essentially work by converting the images into a different form -- a form which makes it easier to pick similar features out. Usually, this stuff doesn't make for very light reading ...
One of the simplest examples I can think of is simply using the color space of each image. If two images have highly similar color distributions, then you can be reasonably sure that they show the same thing. At least, you can have enough certainty to flag it, or do more testing. Comparing images in color space will also resist things such as rotation, scaling, and some cropping. It won't, of course, resist heavy modification of the image or heavy recoloring (and even a simple hue shift will be somewhat tricky).
http://en.wikipedia.org/wiki/RGB_color_space
http://upvector.com/index.php?section=tutorials&subsection=tutorials/colorspace
Another example involves something called the Hough Transform. This transform essentially decomposes an image into a set of lines. You can then take some of the 'strongest' lines in each image and see if they line up. You can do some extra work to try and compensate for rotation and scaling too -- and in this case, since comparing a few lines is MUCH less computational work than doing the same to entire images -- it won't be so bad.
http://homepages.inf.ed.ac.uk/amos/hough.html
http://rkb.home.cern.ch/rkb/AN16pp/node122.html
http://en.wikipedia.org/wiki/Hough_transform
In the form described by you, the problem is tough. Do you consider copy, paste of part of the image into another larger image as a copy ? etc.
What we loosely refer to as duplicates can be difficult for algorithms to discern.
Your duplicates can be either:
Exact Duplicates
Near-exact Duplicates. (minor edits of image etc)
perceptual Duplicates (same content, but different view, camera etc)
No1 & 2 are easier to solve. No 3. is very subjective and still a research topic.
I can offer a solution for No1 & 2.
Both solutions use the excellent image hash- hashing library: https://github.com/JohannesBuchner/imagehash
Exact duplicates
Exact duplicates can be found using a perceptual hashing measure.
The phash library is quite good at this. I routinely use it to clean
training data.
Usage (from github site) is as simple as:
from PIL import Image
import imagehash
# image_fns : List of training image files
img_hashes = {}
for img_fn in sorted(image_fns):
hash = imagehash.average_hash(Image.open(image_fn))
if hash in img_hashes:
print( '{} duplicate of {}'.format(image_fn, img_hashes[hash]) )
else:
img_hashes[hash] = image_fn
Near-Exact Duplicates
In this case you will have to set a threshold and compare the hash values for their distance from each
other. This has to be done by trial-and-error for your image content.
from PIL import Image
import imagehash
# image_fns : List of training image files
img_hashes = {}
epsilon = 50
for img_fn1, img_fn2 in zip(image_fns, image_fns[::-1]):
if image_fn1 == image_fn2:
continue
hash1 = imagehash.average_hash(Image.open(image_fn1))
hash2 = imagehash.average_hash(Image.open(image_fn2))
if hash1 - hash2 < epsilon:
print( '{} is near duplicate of {}'.format(image_fn1, image_fn2) )
If you take a step-back, this is easier to solve if you watermark the master images.
You will need to use a watermarking scheme to embed a code into the image. To take a step back, as opposed to some of the low-level approaches (edge detection etc) suggested by some folks, a watermarking method is superior because:
It is resistant to Signal processing attacks
► Signal enhancement – sharpening, contrast, etc.
► Filtering – median, low pass, high pass, etc.
► Additive noise – Gaussian, uniform, etc.
► Lossy compression – JPEG, MPEG, etc.
It is resistant to Geometric attacks
► Affine transforms
► Data reduction – cropping, clipping, etc.
► Random local distortions
► Warping
Do some research on watermarking algorithms and you will be on the right path to solving your problem. (
Note: You can benchmark you method using the STIRMARK dataset. It is an accepted standard for this type of application.
This is just a suggestion, it might not work and I'm prepared to be called on this.
This will generate false positives, but hopefully not false negatives.
Resize both of the images so that they are the same size (I assume that the ratios of widths to lengths are the same in both images).
Compress a bitmap of both images with a lossless compression algorithm (e.g. gzip).
Find pairs of files that have similar file sizes. For instance, you could just sort every pair of files you have by how similar the file sizes are and retrieve the top X.
As I said, this will definitely generate false positives, but hopefully not false negatives. You can implement this in five minutes, whereas the Porikil et. al. would probably require extensive work.
I believe if you're willing to apply the approach to every possible orientation and to negative versions, a good start to image recognition (with good reliability) is to use eigenfaces: http://en.wikipedia.org/wiki/Eigenface
Another idea would be to transform both images into vectors of their components. A good way to do this is to create a vector that operates in x*y dimensions (x being the width of your image and y being the height), with the value for each dimension applying to the (x,y) pixel value. Then run a variant of K-Nearest Neighbours with two categories: match and no match. If it's sufficiently close to the original image it will fit in the match category, if not then it won't.
K Nearest Neighbours(KNN) can be found here, there are other good explanations of it on the web too: http://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm
The benefits of KNN is that the more variants you're comparing to the original image, the more accurate the algorithm becomes. The downside is you need a catalogue of images to train the system first.
If you're willing to consider a different approach altogether to detecting illegal copies of your images, you could consider watermarking. (from 1.4)
...inserts copyright information into the digital object without the loss of quality. Whenever the copyright of a digital object is in question, this information is extracted to identify the rightful owner. It is also possible to encode the identity of the original buyer along with the identity of the copyright holder, which allows tracing of any unauthorized copies.
While it's also a complex field, there are techniques that allow the watermark information to persist through gross image alteration: (from 1.9)
... any signal transform of reasonable strength cannot remove the watermark. Hence a pirate willing to remove the watermark will not succeed unless they debase the document too much to be of commercial interest.
of course, the faq calls implementing this approach: "...very challenging" but if you succeed with it, you get a high confidence of whether the image is a copy or not, rather than a percentage likelihood.
If you're running Linux I would suggest two tools:
align_image_stack from package hugin-tools - is a commandline program that can automatically correct rotation, scaling, and other distortions (it's mostly intended for compositing HDR photography, but works for video frames and other documents too). More information: http://hugin.sourceforge.net/docs/manual/Align_image_stack.html
compare from package imagemagick - a program that can find and count the amount of different pixels in two images. Here's a neat tutorial: http://www.imagemagick.org/Usage/compare/ uising the -fuzz N% you can increase the error tolerance. The higher the N the higher the error tolerance to still count two pixels as the same.
align_image_stack should correct any offset so the compare command will actually have a chance of detecting same pixels.