algorithm for finding closest images based on jitter / translation - image

I've got a series of images and in some of them the people are only slightly moved, or the camera was shifted slightly, but mostly all is still the same.
I'm wondering algorithmically how I could detect this and find and score images based on their closeness.
A simple euclidian distance might not work - imagine the case in where zebra stripes were shifted just enough to have the "old" white positions filled with black and vice versa. A pathological example, I know, but you get the idea.
As an optional tag along, perhaps there's a nice OpenCV or scipy (preference for Python) function for this or some of the pipeline for doing this.
Thanks!

You can calculate the difference between your images.
The higher the intensity values of the difference image, the more they are different.
So, if you have two exactly the same images and subtract them, there will be a "black" difference image.
You can simply use the overloaded operator-() of Mat-class.

Related

anyway to remove algorithmically discolorations from aerial imagery

I don't know much about image processing so please bear with me if this is not possible to implement.
I have several sets of aerial images of the same area originating from different sources. The pictures have been taken during different seasons, under different lighting conditions etc. Unfortunately some images look patchy and suffer from discolorations or are partially obstructed by clouds or pix-elated, as par example picture1 and picture2
I would like to take as an input several images of the same area and (by some kind of averaging them) produce 1 picture of improved quality. I know some C/C++ so I could use some image processing library.
Can anybody propose any image processing algorithm to achieve it or knows any research done in this field?
I would try with a "color twist" transform, i.e. a 3x3 matrix applied to the RGB components. To implement it, you need to pick color samples in areas that are split by a border, on both sides. You should fing three significantly different reference colors (hence six samples). This will allow you to write the nine linear equations to determine the matrix coefficients.
Then you will correct the altered areas by means of this color twist. As the geometry of these areas is intertwined with the field patches, I don't see a better way than contouring the regions by hand.
In the case of the second picture, the limits of the regions are blurred so that you will need to blur the region mask as well and perform blending.
In any case, don't expect a perfect repair of those problems as the transform might be nonlinear, and completely erasing the edges will be difficult. I also think that colors are so washed out at places that restoring them might create ugly artifacts.
For the sake of illustration, a quick attempt with PhotoShop using manual HLS adjustment (less powerful than color twist).
The first thing I thought of was a kernel matrix of sorts.
Do a first pass of the photo and use an edge detection algorithm to determine the borders between the photos - this should be fairly trivial, however you will need to eliminate any overlap/fading (looks like there's a bit in picture 2), you'll see why in a minute.
Do a second pass right along each border you've detected, and assume that the pixel on either side of the border should be the same color. Determine the difference between the red, green and blue values and average them along the entire length of the line, then divide it by two. The image with the lower red, green or blue value gets this new value added. The one with the higher red, green or blue value gets this value subtracted.
On either side of this line, every pixel should now be the exact same. You can remove one of these rows if you'd like, but if the lines don't run the length of the image this could cause size issues, and the line will likely not be very noticeable.
This could be made far more complicated by generating a filter by passing along this line - I'll leave that to you.
The issue with this could be where there was development/ fall colors etc, this might mess with your algorithm, but there's only one way to find out!

Detect the vein pattern in leaves?

My aim is to detect the vein pattern in leaves which characterize various species of plants
I have already done the following:
Original image:
After Adaptive thresholding:
However the veins aren't that clear and get distorted , Is there any way i could get a better output
EDIT:
I tried color thresholding my results are still unsatisfactory i get the following image
Please help
The fact that its a JPEG image is going to give the "block" artifacts, which in the example you posted causes most square areas around the veins to have lots of noise, so ideally work on an image that's not been through lossy compression. If that's not possible then try filtering the image to remove some of the noise.
The veins you are wanting to extract have a different colour from the background, leaf and shadow so some sort of colour based threshold might be a good idea. There was a recent S.O. question with some code that might help here.
After that some sort of adaptive normalisation would help increase the contrast before you threshold it.
[edit]
Maybe thresholding isn't an intermediate step that you want to do. I made the following by filtering to remove jpeg artifacts, doing some CMYK channel math (more cyan and black) then applying adaptive equalisation. I'm pretty sure you could then go on to produce (subpixel maybe) edge points using image gradients and non-maxima supression, and maybe use the brightness at each point and the properties of the vein structure (mostly joining at a tangent) to join the points into lines.
In the past I made good experiences with the Edge detecting algorithm difference of Gaussian. Which basically works like this:
You blur the image twice with the gaussian blurr algorithm but with differenct blur radii.
Then you calculate the difference between both images.
Pixel with same color beneath each other will creating a same blured color.
Pixel with different colors beneath each other wil reate a gradient which is depending on the blur radius. For bigger radius the gradient will stretch more far. For smaller ones it wont.
So basically this is bandpass filter. If the selected radii are to small a vain vill create 2 "parallel" lines. But since the veins of leaves are small compared with the extends of the Image you mostly find radii, where a vein results in 1 line.
Here I added th processed picture.
Steps I did on this picture:
desaturate (grayscaled)
difference of Gaussian. Here I blured the first Image with a radius of 10px and the second image with a radius of 2px. The result you can see below.
This is only a quickly created result. I would guess that by optimizing the parametes, you can even get better ones.
This sounds like something I did back in college with neural networks. The neural network stuff is a bit hard so I won't go there. Anyways, patterns are perfect candidates for the 2D Fourier transform! Here is a possible scheme:
You have training data and input data
Your data is represented as a the 2D Fourier transform
If your database is large you should run PCA on the transform results to convert a 2D spectrogram to a 1D spectrogram
Compare the hamming distance by testing the spectrum (after PCA) of 1 image with all of the images in your dataset.
You should expect ~70% recognition with such primitive methods as long as the images are of approximately the same rotation. If the images are not of the same rotation.you may have to use SIFT. To get better recognition you will need more intelligent training sets such as a Hidden Markov Model or a neural net. The truth is to getting good results for this kind of problem may be quite a lot of work.
Check out: https://theiszm.wordpress.com/2010/07/20/7-properties-of-the-2d-fourier-transform/

Counting object on image algorithm

I got school task again. This time, my teacher gave me task to create algorithm to count how many ducks on picture.
The picture is similar to this one:
I think I should use pattern recognition for searching how many ducks on it. But I don't know which pattern match for each duck.
I think that you can solve this problem by segmenting the ducks' beaks and counting the number of connected components in the binary image.
To segment the ducks' beaks, first convert the image to HSV color space and then perform a binarization using the hue component. Note that the ducks' beaks hue are different from other parts of the image.
Here's one way:
Hough transform for circles:
Initialize an accumulator array indexed by (x,y,radius)
For each pixel:
calculate an edge (e.g. Sobel operator will provide both magnitude and direction), if magnitude exceeds some threshold then:
increment every accumulator for which this edge could possibly lend evidence (only the (x,y) in the direction of the edge, only radii between min_duck_radius and max_duck_radius)
Now smooth and threshold the accumulator array, and the coordinates of highest accumulators show you where the heads are. The threshold may leap out at you if you histogram the values in the accumulators (there may be a clear difference between "lots of evidence" and "noise").
So that's very terse, but it can get you started.
It might be just because I'm working with SIFT right now, but to me it looks like it could be good for your problem.
It is an algorithm that matches the same object on two different pictures, where the objects can have different orientations, scales and be viewed from different perspectives on the two pictures. It can also work when an object is partially hidden (as your ducks are) by another object.
I'd suggest finding a good clear picture of a rubber ducky ( :D ) and then use some SIFT implementation (VLFeat - C library with SIFT but no visualization, SIFT++ - based on VLFeat, but in C++ , Rob Hess in C with OpenCV...).
You should bear in mind that matching with SIFT (and anything else) is not perfect - so you might not get the exact number of rubber duckies in the picture.

Recognizing distortions in a regular grid

To give you some background as to what I'm doing: I'm trying to quantitatively record variations in flow of a compressible fluid via image analysis. One way to do this is to exploit the fact that the index of refraction of the fluid is directly related to its density. If you set up some kind of image behind the flow, the distortion in the image due to refractive index changes throughout the fluid field leads you to a density gradient, which helps to characterize the flow pattern.
I have a set of routines that do this successfully with a regular 2D pattern of dots. The dot pattern is slightly distorted, and by comparing the position of the dots in the distorted image with that in the non-distorted image, I get a displacement field, which is exactly what I need. The problem with this method is resolution. The resolution is limited to the number of dots in the field, and I'm exploring methods that give me more data.
One idea I've had is to use a regular grid of horizontal and vertical lines. This image will distort the same way, but instead of getting only the displacement of a dot, I'll have the continuous distortion of a grid. It seems like there must be some standard algorithm or procedure to compare one geometric grid to another and infer some kind of displacement field. Nonetheless, I haven't found anything like this in my research.
Does anyone have some ideas that might point me in the right direction? FYI, I am not a computer scientist -- I'm an engineer. I say that only because there may be some obvious approach I'm neglecting due to coming from a different field. But I can program. I'm using MATLAB, but I can read Python, C/C++, etc.
Here are examples of the type of images I'm working with:
Regular: Distorted:
--------
I think you are looking for the Digital Image Correlation algorithm.
Here you can see a demo.
Here is a Matlab Implementation.
From Wikipedia:
Digital Image Correlation and Tracking (DIC/DDIT) is an optical method that employs tracking & image registration techniques for accurate 2D and 3D measurements of changes in images. This is often used to measure deformation (engineering), displacement, and strain, but it is widely applied in many areas of science and engineering.
Edit
Here I applied the DIC algorithm to your distorted image using Mathematica, showing the relative displacements.
Edit
You may also easily identify the maximum displacement zone:
Edit
After some work (quite a bit, frankly) you can come up to something like this, representing the "displacement field", showing clearly that you are dealing with a vortex:
(Darker and bigger arrows means more displacement (velocity))
Post me a comment if you are interested in the Mathematica code for this one. I think my code is not going to help anybody else, so I omit posting it.
I would also suggest a line tracking algorithm would work well.
Simply start at the first pixel line of the image and start following each of the vertical lines downwards (You just need to start this at the first line to get the starting points. This can be done by a simple pattern that moves orthogonally to the gradient of that line, ergo follows a line. When you reach a crossing of a horizontal line you can measure that point (in x,y coordinates) and compare it to the corresponding crossing point in your distorted image.
Since your grid is regular you know that the n'th measured crossing point on the m'th vertical black line are corresponding in both images. Then you simply compare both points by computing their distance. Do this for each line on your grid and you will get, by how far each crossing point of the grid is distorted.
This following a line algorithm is also used in basic Edge linking algorithms or the Canny Edge detector.
(All this are just theoretic ideas and I cannot provide you with an algorithm to it. But I guess it should work easily on distorted images like you have there... but maybe it is helpful for you)

Image comparison - fast algorithm

I'm looking to create a base table of images and then compare any new images against that to determine if the new image is an exact (or close) duplicate of the base.
For example: if you want to reduce storage of the same image 100's of times, you could store one copy of it and provide reference links to it. When a new image is entered you want to compare to an existing image to make sure it's not a duplicate ... ideas?
One idea of mine was to reduce to a small thumbnail and then randomly pick 100 pixel locations and compare.
Below are three approaches to solving this problem (and there are many others).
The first is a standard approach in computer vision, keypoint matching. This may require some background knowledge to implement, and can be slow.
The second method uses only elementary image processing, and is potentially faster than the first approach, and is straightforward to implement. However, what it gains in understandability, it lacks in robustness -- matching fails on scaled, rotated, or discolored images.
The third method is both fast and robust, but is potentially the hardest to implement.
Keypoint Matching
Better than picking 100 random points is picking 100 important points. Certain parts of an image have more information than others (particularly at edges and corners), and these are the ones you'll want to use for smart image matching. Google "keypoint extraction" and "keypoint matching" and you'll find quite a few academic papers on the subject. These days, SIFT keypoints are arguably the most popular, since they can match images under different scales, rotations, and lighting. Some SIFT implementations can be found here.
One downside to keypoint matching is the running time of a naive implementation: O(n^2m), where n is the number of keypoints in each image, and m is the number of images in the database. Some clever algorithms might find the closest match faster, like quadtrees or binary space partitioning.
Alternative solution: Histogram method
Another less robust but potentially faster solution is to build feature histograms for each image, and choose the image with the histogram closest to the input image's histogram. I implemented this as an undergrad, and we used 3 color histograms (red, green, and blue), and two texture histograms, direction and scale. I'll give the details below, but I should note that this only worked well for matching images VERY similar to the database images. Re-scaled, rotated, or discolored images can fail with this method, but small changes like cropping won't break the algorithm
Computing the color histograms is straightforward -- just pick the range for your histogram buckets, and for each range, tally the number of pixels with a color in that range. For example, consider the "green" histogram, and suppose we choose 4 buckets for our histogram: 0-63, 64-127, 128-191, and 192-255. Then for each pixel, we look at the green value, and add a tally to the appropriate bucket. When we're done tallying, we divide each bucket total by the number of pixels in the entire image to get a normalized histogram for the green channel.
For the texture direction histogram, we started by performing edge detection on the image. Each edge point has a normal vector pointing in the direction perpendicular to the edge. We quantized the normal vector's angle into one of 6 buckets between 0 and PI (since edges have 180-degree symmetry, we converted angles between -PI and 0 to be between 0 and PI). After tallying up the number of edge points in each direction, we have an un-normalized histogram representing texture direction, which we normalized by dividing each bucket by the total number of edge points in the image.
To compute the texture scale histogram, for each edge point, we measured the distance to the next-closest edge point with the same direction. For example, if edge point A has a direction of 45 degrees, the algorithm walks in that direction until it finds another edge point with a direction of 45 degrees (or within a reasonable deviation). After computing this distance for each edge point, we dump those values into a histogram and normalize it by dividing by the total number of edge points.
Now you have 5 histograms for each image. To compare two images, you take the absolute value of the difference between each histogram bucket, and then sum these values. For example, to compare images A and B, we would compute
|A.green_histogram.bucket_1 - B.green_histogram.bucket_1|
for each bucket in the green histogram, and repeat for the other histograms, and then sum up all the results. The smaller the result, the better the match. Repeat for all images in the database, and the match with the smallest result wins. You'd probably want to have a threshold, above which the algorithm concludes that no match was found.
Third Choice - Keypoints + Decision Trees
A third approach that is probably much faster than the other two is using semantic texton forests (PDF). This involves extracting simple keypoints and using a collection decision trees to classify the image. This is faster than simple SIFT keypoint matching, because it avoids the costly matching process, and keypoints are much simpler than SIFT, so keypoint extraction is much faster. However, it preserves the SIFT method's invariance to rotation, scale, and lighting, an important feature that the histogram method lacked.
Update:
My mistake -- the Semantic Texton Forests paper isn't specifically about image matching, but rather region labeling. The original paper that does matching is this one: Keypoint Recognition using Randomized Trees. Also, the papers below continue to develop the ideas and represent the state of the art (c. 2010):
Fast Keypoint Recognition using Random Ferns - faster and more scalable than Lepetit 06
BRIEF: Binary Robust Independent Elementary Features - less robust but very fast -- I think the goal here is real-time matching on smart phones and other handhelds
The best method I know of is to use a Perceptual Hash. There appears to be a good open source implementation of such a hash available at:
http://phash.org/
The main idea is that each image is reduced down to a small hash code or 'fingerprint' by identifying salient features in the original image file and hashing a compact representation of those features (rather than hashing the image data directly). This means that the false positives rate is much reduced over a simplistic approach such as reducing images down to a tiny thumbprint sized image and comparing thumbprints.
phash offers several types of hash and can be used for images, audio or video.
This post was the starting point of my solution, lots of good ideas here so I though I would share my results. The main insight is that I've found a way to get around the slowness of keypoint-based image matching by exploiting the speed of phash.
For the general solution, it's best to employ several strategies. Each algorithm is best suited for certain types of image transformations and you can take advantage of that.
At the top, the fastest algorithms; at the bottom the slowest (though more accurate). You might skip the slow ones if a good match is found at the faster level.
file-hash based (md5,sha1,etc) for exact duplicates
perceptual hashing (phash) for rescaled images
feature-based (SIFT) for modified images
I am having very good results with phash. The accuracy is good for rescaled images. It is not good for (perceptually) modified images (cropped, rotated, mirrored, etc). To deal with the hashing speed we must employ a disk cache/database to maintain the hashes for the haystack.
The really nice thing about phash is that once you build your hash database (which for me is about 1000 images/sec), the searches can be very, very fast, in particular when you can hold the entire hash database in memory. This is fairly practical since a hash is only 8 bytes.
For example, if you have 1 million images it would require an array of 1 million 64-bit hash values (8 MB). On some CPUs this fits in the L2/L3 cache! In practical usage I have seen a corei7 compare at over 1 Giga-hamm/sec, it is only a question of memory bandwidth to the CPU. A 1 Billion-image database is practical on a 64-bit CPU (8GB RAM needed) and searches will not exceed 1 second!
For modified/cropped images it would seem a transform-invariant feature/keypoint detector like SIFT is the way to go. SIFT will produce good keypoints that will detect crop/rotate/mirror etc. However the descriptor compare is very slow compared to hamming distance used by phash. This is a major limitation. There are a lot of compares to do, since there are maximum IxJxK descriptor compares to lookup one image (I=num haystack images, J=target keypoints per haystack image, K=target keypoints per needle image).
To get around the speed issue, I tried using phash around each found keypoint, using the feature size/radius to determine the sub-rectangle. The trick to making this work well, is to grow/shrink the radius to generate different sub-rect levels (on the needle image). Typically the first level (unscaled) will match however often it takes a few more. I'm not 100% sure why this works, but I can imagine it enables features that are too small for phash to work (phash scales images down to 32x32).
Another issue is that SIFT will not distribute the keypoints optimally. If there is a section of the image with a lot of edges the keypoints will cluster there and you won't get any in another area. I am using the GridAdaptedFeatureDetector in OpenCV to improve the distribution. Not sure what grid size is best, I am using a small grid (1x3 or 3x1 depending on image orientation).
You probably want to scale all the haystack images (and needle) to a smaller size prior to feature detection (I use 210px along maximum dimension). This will reduce noise in the image (always a problem for computer vision algorithms), also will focus detector on more prominent features.
For images of people, you might try face detection and use it to determine the image size to scale to and the grid size (for example largest face scaled to be 100px). The feature detector accounts for multiple scale levels (using pyramids) but there is a limitation to how many levels it will use (this is tunable of course).
The keypoint detector is probably working best when it returns less than the number of features you wanted. For example, if you ask for 400 and get 300 back, that's good. If you get 400 back every time, probably some good features had to be left out.
The needle image can have less keypoints than the haystack images and still get good results. Adding more doesn't necessarily get you huge gains, for example with J=400 and K=40 my hit rate is about 92%. With J=400 and K=400 the hit rate only goes up to 96%.
We can take advantage of the extreme speed of the hamming function to solve scaling, rotation, mirroring etc. A multiple-pass technique can be used. On each iteration, transform the sub-rectangles, re-hash, and run the search function again.
My company has about 24million images come in from manufacturers every month. I was looking for a fast solution to ensure that the images we upload to our catalog are new images.
I want to say that I have searched the internet far and wide to attempt to find an ideal solution. I even developed my own edge detection algorithm.
I have evaluated speed and accuracy of multiple models.
My images, which have white backgrounds, work extremely well with phashing. Like redcalx said, I recommend phash or ahash. DO NOT use MD5 Hashing or anyother cryptographic hashes. Unless, you want only EXACT image matches. Any resizing or manipulation that occurs between images will yield a different hash.
For phash/ahash, Check this out: imagehash
I wanted to extend *redcalx'*s post by posting my code and my accuracy.
What I do:
from PIL import Image
from PIL import ImageFilter
import imagehash
img1=Image.open(r"C:\yourlocation")
img2=Image.open(r"C:\yourlocation")
if img1.width<img2.width:
img2=img2.resize((img1.width,img1.height))
else:
img1=img1.resize((img2.width,img2.height))
img1=img1.filter(ImageFilter.BoxBlur(radius=3))
img2=img2.filter(ImageFilter.BoxBlur(radius=3))
phashvalue=imagehash.phash(img1)-imagehash.phash(img2)
ahashvalue=imagehash.average_hash(img1)-imagehash.average_hash(img2)
totalaccuracy=phashvalue+ahashvalue
Here are some of my results:
item1 item2 totalsimilarity
desk1 desk1 3
desk1 phone1 22
chair1 desk1 17
phone1 chair1 34
Hope this helps!
As cartman pointed out, you can use any kind of hash value for finding exact duplicates.
One starting point for finding close images could be here. This is a tool used by CG companies to check if revamped images are still showing essentially the same scene.
I have an idea, which can work and it most likely to be very fast.
You can sub-sample an image to say 80x60 resolution or comparable,
and convert it to grey scale (after subsampling it will be faster).
Process both images you want to compare.
Then run normalised sum of squared differences between two images (the query image and each from the db),
or even better Normalised Cross Correlation, which gives response closer to 1, if
both images are similar.
Then if images are similar you can proceed to more sophisticated techniques
to verify that it is the same images.
Obviously this algorithm is linear in terms of number of images in your database
so even though it is going to be very fast up to 10000 images per second on the modern hardware.
If you need invariance to rotation, then a dominant gradient can be computed
for this small image, and then the whole coordinate system can be rotated to canonical
orientation, this though, will be slower. And no, there is no invariance to scale here.
If you want something more general or using big databases (million of images), then
you need to look into image retrieval theory (loads of papers appeared in the last 5 years).
There are some pointers in other answers. But It might be overkill, and the suggest histogram approach will do the job. Though I would think combination of many different
fast approaches will be even better.
I believe that dropping the size of the image down to an almost icon size, say 48x48, then converting to greyscale, then taking the difference between pixels, or Delta, should work well. Because we're comparing the change in pixel color, rather than the actual pixel color, it won't matter if the image is slightly lighter or darker. Large changes will matter since pixels getting too light/dark will be lost. You can apply this across one row, or as many as you like to increase the accuracy. At most you'd have 47x47=2,209 subtractions to make in order to form a comparable Key.
Picking 100 random points could mean that similar (or occasionally even dissimilar) images would be marked as the same, which I assume is not what you want. MD5 hashes wouldn't work if the images were different formats (png, jpeg, etc), had different sizes, or had different metadata. Reducing all images to a smaller size is a good bet, doing a pixel-for- pixel comparison shouldn't take too long as long as you're using a good image library / fast language, and the size is small enough.
You could try making them tiny, then if they are the same perform another comparison on a larger size - could be a good combination of speed and accuracy...
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 have a large number of images, look into a Bloom filter, which uses multiple hashes for a probablistic but efficient result. If the number of images is not huge, then a cryptographic hash like md5 should be sufficient.
I think it's worth adding to this a phash solution I built that we've been using for a while now: Image::PHash. It is a Perl module, but the main parts are in C. It is several times faster than phash.org and has a few extra features for DCT-based phashes.
We had dozens of millions of images already indexed on a MySQL database, so I wanted something fast and also a way to use MySQL indices (which don't work with hamming distance), which led me to use "reduced" hashes for direct matches, the module doc discusses this.
It's quite simple to use:
use Image::PHash;
my $iph1 = Image::PHash->new('file1.jpg');
my $p1 = $iph1->pHash();
my $iph2 = Image::PHash->new('file2.jpg');
my $p2 = $iph2->pHash();
my $diff = Image::PHash::diff($p1, $p2);
I made a very simple solution in PHP for comparing images several years ago. It calculates a simple hash for each image, and then finds the difference. It works very nice for cropped or cropped with translation versions of the same image.
First I resize the image to a small size, like 24x24 or 36x36. Then I take each column of pixels and find average R,G,B values for this column.
After each column has its own three numbers, I do two passes: first on odd columns and second on even ones. The first pass sums all the processed cols and then divides by their number ( [1] + [2] + [5] + [N-1] / (N/2) ). The second pass works in another manner: ( [3] - [4] + [6] - [8] ... / (N/2) ).
So now I have two numbers. As I found out experimenting, the first one is a major one: if it's far from the values of another image, they are not similar from the human point of view at all.
So, the first one represents the average brightness of the image (again, you can pay most attention to green channel, then the red one, etc, but the default R->G->B order works just fine). The second number can be compared if the first two are very close, and it in fact represents the overall contrast of the image: if we have some black/white pattern or any contrast scene (lighted buildings in the city at night, for example) and if we are lucky, we will get huge numbers here if out positive members of sum are mostly bright, and negative ones are mostly dark, or vice versa. As I want my values to be always positive, I divide by 2 and shift by 127 here.
I wrote the code in PHP in 2017, and seems I lost the code. But I still have the screenshots:
The same image:
Black & White version:
Cropped version:
Another image, ranslated version:
Same color gamut as 4th, but another scene:
I tuned the difference thresholds so that the results are really nice. But as you can see, this simple algorithm cannot do anything good with simple scene translations.
On a side note I can notice that a modification can be written to make cropped copies from each of two images at 75-80 percent, 4 at the corners or 8 at the corners and middles of the edges, and then by comparing the cropped variants with another whole image just the same way; and if one of them gets a significantly better similarity score, then use its value instead of the default one).

Resources