General: I'm hoping that the use-case I'm about to describe is a simple case of an optical flow problem and since I don't have much knowledge on the subject, I was wondering if anyone has any suggestions on how I can approach solving my problem.
Research I've already done: I have began reading the High Accuracy Optical Flow Estimation Based on a Theory for Warping paper and am planning on looking over the Particle Video paper. I have found a MATLAB High Accuracy Optical Flow implementation of optical flow. However, the papers (and the code) seem to describe concepts that are very involved and may require a lot of time for me to dig in and understand. I am hoping that the solution to my problem may be more simple.
Problem: I have a sequence of images. The images depict a material breakage process, where the material and background are black and the cracks are white. I am interested in traversing the sequence of images in reverse in an attempt to map all of the cracks that have formed in the breakage process to the first black image. You can think of the material as a large puzzle and I am trying to put the pieces back together in the reverse order that they broke.
In each image, there can be some cracks that are just emerging and/or some cracks that have been fully formed (and thus created a fragment). Throughout the breakage process, some fragments may separate and break further. The fragments can also move farther away from one another (the change is slight between subsequent frames).
Desired Output: All of the cracks/lines in the sequence mapped to the first image in the sequence.
Additional Notes: Images are available in grayscale format (i.e. original) as well as in binary format, where the cracks have been outlined in white and the background is completely black. See below for some image examples.
The top row shows the original images and the bottom row shows the binary images. As you can see, the crack that goes down the middle grows wider and wider as the image sequence progresses. Thus, the bottom crack moves together with the lower fragment. When traversing the sequence in reverse, I hope to algorithmically realize that the middle crack comes together as one (and map it correctly to the first image), and also map the bottom crack correctly, keeping its correct correspondence (size and position) with the bottom fragment.
A sequence typically contains about 30~40 images, so I've just shown the beginning subset. Also, although these images don't show it, it is possible that a particular image only contains the beginning of the crack (i.e. its initial appearance) and in subsequent images it gets longer and longer and may join with other cracks.
Language: Although not necessary, I would like to implement the solution using MATLAB (just because most of the other code that relates to the project has been done in MATLAB). However, if OpenCV may be easier, I am flexible in my language/library usage.
Any ideas are greatly appreciated.
Traverse forward rather than reverse, and don't use optical flow. Use the fracture lines to segment the black parts, track the centroid of each black segment over time. Whenever a new fracture line appears that cuts across a black segment, split the segment into two and continue tracking each segment separately.
From this you should be able to construct a tree structure representing the segmentation of the black parts over time. The fracture lines can be added as metadata to this tree, perhaps assigning fracture lines to the segment node in which they first appeared.
I would advise you to follow your initial idea of backtracking the cracks. Yo kind of know how the cracks look like so you can track all the points that belong to the crack. You just track all the white points with an optical flow tracker, start with Lukas-Kanade tracker and see where you get. The high-accuracy optical flow method is a global one and more general, I'll track all the pixels in the image trying to keep some smoothness everywhere. The LK is a local method that will just use a small window around each point to do the tracking. The problem is that appart from the cracks all the pixels are plain black so nothing to track there, you'll just waist time trying to track something that you can't track and you don't need to track.
If lines are very straight you might end up with what's called the aperture problem and you'll get inaccurate results. You can also try some shape fitting/deformation based on snakes.
I agree to damian. Most optical flow methods like the HAOF rely on the first-order taylor approximation of the intensity constancy constrian equation I(x,t)=I(x+v,t+dt). That mean the solution depends on image derivatives where the gradient determine the motion vector magnitude and angle i.e. you need a certain amount of texture. However the very low texture of your non-binarised images could be enough. You could try histogram equalization to increase the contrast of your input data but it is important to apply the same transformation for both input images. e.g. as follows:
cv::Mat equalizeMat(grayInp1.rows, grayInp1.cols * 2 , CV_8UC1);
grayInp1.copyTo(equalizeMat(cv::Rect(0,0,grayInp1.cols,grayInp1.rows)));
grayInp2.copyTo(equalizeMat(cv::Rect(grayInp1.cols,0,grayInp2.cols,grayInp2.rows)));
cv::equalizeHist(equalizeMat,equalizeMat);
equalizeMat(cv::Rect(0,0,grayInp1.cols,grayInp1.rows)).copyTo(grayInp1);
equalizeMat(cv::Rect(grayInp1.cols,0,grayInp2.cols,grayInp2.rows)).copyTo(grayInp2);
// estimate optical flow
Related
I am trying to count the number of hairs transplanted in the following image. So practically, I have to count the number of spots I can find in the center of image.
(I've uploaded the inverted image of a bald scalp on which new hairs have been transplanted because the original image is bloody and absolutely disgusting! To see the original non-inverted image click here. To see the larger version of the inverted image just click on it). Is there any known image processing algorithm to detect these spots? I've found out that the Circle Hough Transform algorithm can be used to find circles in an image, I'm not sure if it's the best algorithm that can be applied to find the small spots in the following image though.
P.S. According to one of the answers, I tried to extract the spots using ImageJ, but the outcome was not satisfactory enough:
I opened the original non-inverted image (Warning! it's bloody and disgusting to see!).
Splited the channels (Image > Color > Split Channels). And selected the blue channel to continue with.
Applied Closing filter (Plugins > Fast Morphology > Morphological Filters) with these values: Operation: Closing, Element: Square, Radius: 2px
Applied White Top Hat filter (Plugins > Fast Morphology > Morphological Filters) with these values: Operation: White Top Hat, Element: Square, Radius: 17px
However I don't know what to do exactly after this step to count the transplanted spots as accurately as possible. I tried to use (Process > Find Maxima), but the result does not seem accurate enough to me (with these settings: Noise tolerance: 10, Output: Single Points, Excluding Edge Maxima, Light Background):
As you can see, some white spots have been ignored and some white areas which are not actually hair transplant spots, have been marked.
What set of filters do you advise to accurately find the spots? Using ImageJ seems a good option since it provides most of the filters we need. Feel free however, to advise what to do using other tools, libraries (like OpenCV), etc. Any help would be highly appreciated!
I do think you are trying to solve the problem in a bit wrong way. It might sound groundless, so I'd better show my results first.
Below I have a crop of you image on the left and discovered transplants on the right. Green color is used to highlight areas with more than one transplant.
The overall approach is very basic (will describe it later), but still it provides close to be accurate results. Please note, it was a first try, so there is a lot of room for enhancements.
Anyway, let's get back to the initial statement saying you approach is wrong. There are several major issues:
the quality of your image is awful
you say you want to find spots, but actually you are looking for hair transplant objects
you completely ignores the fact average head is far from being flat
it does look like you think filters will add some important details to your initial image
you expect algorithms to do magic for you
Let's review all these items one by one.
1. Image quality
It might be very obvious statement, but before the actual processing you need to make sure you have best possible initial data. You might spend weeks trying to find a way to process photos you have without any significant achievements. Here are some problematic areas:
I bet it is hard for you to "read" those crops, despite the fact you have the most advanced object recognition algorithms in your brain.
Also, your time is expensive and you still need best possible accuracy and stability. So, for any reasonable price try to get: proper contrast, sharp edges, better colors and color separation.
2. Better understanding of the objects to be identified
Generally speaking, you have a 3D objects to be identified. So you can analyze shadows in order to improve accuracy. BTW, it is almost like a Mars surface analysis :)
3. The form of the head should not be ignored
Because of the form of the head you have distortions. Again, in order to get proper accuracy those distortions should be corrected before the actual analysis. Basically, you need to flatten analyzed area.
3D model source
4. Filters might not help
Filters do not add information, but they can easily remove some important details. You've mentioned Hough transform, so here is interesting question: Find lines in shape
I will use this question as an example. Basically, you need to extract a geometry from a given picture. Lines in shape looks a bit complex, so you might decide to use skeletonization
All of a sadden, you have more complex geometry to deal with and virtually no chances to understand what actually was on the original picture.
5. Sorry, no magic here
Please be aware of the following:
You must try to get better data in order to achieve better accuracy and stability. The model itself is also very important.
Results explained
As I said, my approach is very simple: image was posterized and then I used very basic algorithm to identify areas with a specific color.
Posterization can be done in a more clever way, areas detection can be improved, etc. For this PoC I just have a simple rule to highlight areas with more than one implant. Having areas identified a bit more advanced analysis can be performed.
Anyway, better image quality will let you use even simple method and get proper results.
Finally
How did the clinic manage to get Yondu as client? :)
Update (tools and techniques)
Posterization - GIMP (default settings,min colors)
Transplant identification and visualization - Java program, no libraries or other dependencies
Having areas identified it is easy to find average size, then compare to other areas and mark significantly bigger areas as multiple transplants.
Basically, everything is done "by hand". Horizontal and vertical scan, intersections give areas. Vertical lines are sorted and used to restore the actual shape. Solution is homegrown, code is a bit ugly, so do not want to share it, sorry.
The idea is pretty obvious and well explained (at least I think so). Here is an additional example with different scan step used:
Yet another update
A small piece of code, developed to verify a very basic idea, evolved a bit, so now it can handle 4K video segmentation in real-time. The idea is the same: horizontal and vertical scans, areas defined by intersected lines, etc. Still no external libraries, just a lot of fun and a bit more optimized code.
Additional examples can be found on YouTube: RobotsCanSee
or follow the progress in Telegram: RobotsCanSee
I've just tested this solution using ImageJ, and it gave good preliminary result:
On the original image, for each channel
Small (radius 1 or 2) closing in order to get rid of the hairs (black part in the middle of the white one)
White top-hat of radius 5 in order to detect the white part around each black hair.
Small closing/opening in order to clean a little bit the image (you can also use a median filter)
Ultimate erode in order to count the number of white blob remaining. You can also certainly use a LoG (Laplacian of Gaussian) or a distance map.
[EDIT]
You don't detect all the white spots using the maxima function, because after the closing, some zones are flat, so the maxima is not a point, but a zone. At this point, I think that an ultimate opening or an ultimate eroded would give you the center or each white spot. But I am not sure that there is a function/pluggin doing it in ImageJ. You can take a look to Mamba or SMIL.
A H-maxima (after white top-hat) may also clean a little bit more your results and improve the contrast between the white spots.
As Renat mentioned, you should not expect algorithms to do magic for you, however I'm hopeful to come up with a reasonable estimate of the number of spots. Here, I'm going to give you some hints and resources, check them out and call me back if you need more information.
First, I'm kind of hopeful to morphological operations, but I think a perfect pre-processing step may push the accuracy yielded by them dramatically. I want you put my finger on the pre-processing step. Thus I'm going ti work with this image:
That's the idea:
Collect and concentrate the mass around the spot locations. What do I mean my concentrating the masses? Let's open the book from the other side: As you see, the provided image contains some salient spots surrounded by some noisy gray-level dots.
By dots, I mean the pixels that are not part of a spot, but their gray-value are larger than zero (pure black) - which are available around the spots. It is clear that if you clear these noisy dots, you surely will come up with a good estimate of spots using other processing tools such as morphological operations.
Now, how to make the image more sharp? What if we could make the dots to move forward to their nearest spots? This is what I mean by concentrating the masses over the spots. Doing so, only the prominent spots will be present in the image and hence we have made a significant step toward counting the prominent spots.
How to do the concentrating thing? Well, the idea that I just explained is available in this paper, which its code is luckily available. See the section 2.2. The main idea is to use a random walker to walk on the image for ever. The formulations is stated such that the walker will visit the prominent spots far more times and that can lead to identifying the prominent spots. The algorithm is modeled Markov chain and The equilibrium hitting times of the ergodic Markov chain holds the key for identifying the most salient spots.
What I described above is just a hint and you should read that short paper to get the detailed version of the idea. Let me know if you need more info or resources.
That is a pleasure to think on such interesting problems. Hope it helps.
You could do the following:
Threshold the image using cv::threshold
Find connected components using cv::findcontour
Reject the connected components of size larger than a certain size as you seem to be concerned about small circular regions only.
Count all the valid connected components.
Hopefully, you have a descent approximation of the actual number of spots.
To be statistically more accurate, you could repeat 1-4 for a range of thresholds and take the average.
This is what you get after applying unsharpen radius 22, amount 5, threshold 2 to your image.
This increases the contrast between the dots and the surrounding areas. I used the ballpark assumption that the dots are somewhere between 18 and 25 pixels in diameter.
Now you can take the local maxima of white as a "dot" and fill it in with a black circle until the circular neighborhood of the dot (a circle of radius 10-12) erases the dot. This should let you "pick off" the dots joined to each other in clusters more than 2. Then look for local maxima again. Rinse and repeat.
The actual "dot" areas are in stark contrast to the surrounding areas, so this should let you pick them off as well as you would by eyeballing it.
I have a web cam that takes a picture every N seconds. This gives me a collection of images of the same scene over time. I want to process that collection of images as they are created to identify events like someone entering into the frame, or something else large happening. I will be comparing images that are adjacent in time and fixed in space - the same scene at different moments of time.
I want a reasonably sophisticated approach. For example, naive approaches fail for outdoor applications. If you count the number of pixels that change, for example, or the percentage of the picture that has a different color or grayscale value, that will give false positive reports every time the sun goes behind a cloud or the wind shakes a tree.
I want to be able to positively detect a truck parking in the scene, for example, while ignoring lighting changes from sun/cloud transitions, etc.
I've done a number of searches, and found a few survey papers (Radke et al, for example) but nothing that actually gives algorithms that I can put into a program I can write.
Use color spectroanalisys, without luminance: when the Sun goes down for a while, you will get similar result, colors does not change (too much).
Don't go for big changes, but quick changes. If the luminance of the image changes -10% during 10 min, it means the usual evening effect. But when the change is -5%, 0, +5% within seconds, its a quick change.
Don't forget to adjust the reference values.
Split the image to smaller regions. Then, when all the regions change same way, you know, it's a global change, like an eclypse or what, but if only one region's parameters are changing, then something happens there.
Use masks to create smart regions. If you're watching a street, filter out the sky, the trees (blown by wind), etc. You may set up different trigger values for different regions. The regions should overlap.
A special case of the region is the line. A line (a narrow region) contains less and more homogeneous pixels than a flat area. Mark, say, a green fence, it's easy to detect wheter someone crosses it, it makes bigger change in the line than in a flat area.
If you can, change the IRL world. Repaint the fence to a strange color to create a color spectrum, which can be identified easier. Paint tags to the floor and wall, which can be OCRed by the program, so you can detect wheter something hides it.
I believe you are looking for Template Matching
Also i would suggest you to look on to Open CV
We had to contend with many of these issues in our interactive installations. It's tough to not get false positives without being able to control some of your environment (sounds like you will have some degree of control). In the end we looked at combining some techniques and we created an open piece of software named OpenTSPS (Open Toolkit for Sensing People in Spaces - http://www.opentsps.com). You can look at the C++ source in github (https://github.com/labatrockwell/openTSPS/).
We use ‘progressive background relearn’ to adjust to the changing background over time. Progressive relearning is particularly useful in variable lighting conditions – e.g. if lighting in a space changes from day to night. This in combination with blob detection works pretty well and the only way we have found to improve is to use 3D cameras like the kinect which cast out IR and measure it.
There are other algorithms that might be relevant, like SURF (http://achuwilson.wordpress.com/2011/08/05/object-detection-using-surf-in-opencv-part-1/ and http://en.wikipedia.org/wiki/SURF) but I don't think it will help in your situation unless you know exactly the type of thing you are looking for in the image.
Sounds like a fun project. Best of luck.
The problem you are trying to solve is very interesting indeed!
I think that you would need to attack it in parts:
As you already pointed out, a sudden change in illumination can be problematic. This is an indicator that you probably need to achieve some sort of illumination-invariant representation of the images you are trying to analyze.
There are plenty of techniques lying around, one I have found very useful for illumination invariance (applied to face recognition) is DoG filtering (Difference of Gaussians)
The idea is that you first convert the image to gray-scale. Then you generate two blurred versions of this image by applying a gaussian filter, one a little bit more blurry than the first one. (you could use a 1.0 sigma and a 2.0 sigma in a gaussian filter respectively) Then you subtract from the less-blury image, the pixel intensities of the more-blurry image. This operation enhances edges and produces a similar image regardless of strong illumination intensity variations. These steps can be very easily performed using OpenCV (as others have stated). This technique has been applied and documented here.
This paper adds an extra step involving contrast equalization, In my experience this is only needed if you want to obtain "visible" images from the DoG operation (pixel values tend to be very low after the DoG filter and are veiwed as black rectangles onscreen), and performing a histogram equalization is an acceptable substitution if you want to be able to see the effect of the DoG filter.
Once you have illumination-invariant images you could focus on the detection part. If your problem can afford having a static camera that can be trained for a certain amount of time, then you could use a strategy similar to alarm motion detectors. Most of them work with an average thermal image - basically they record the average temperature of the "pixels" of a room view, and trigger an alarm when the heat signature varies greatly from one "frame" to the next. Here you wouldn't be working with temperatures, but with average, light-normalized pixel values. This would allow you to build up with time which areas of the image tend to have movement (e.g. the leaves of a tree in a windy environment), and which areas are fairly stable in the image. Then you could trigger an alarm when a large number of pixles already flagged as stable have a strong variation from one frame to the next one.
If you can't afford training your camera view, then I would suggest you take a look at the TLD tracker of Zdenek Kalal. His research is focused on object tracking with a single frame as training. You could probably use the semistatic view of the camera (with no foreign objects present) as a starting point for the tracker and flag a detection when the TLD tracker (a grid of points where local motion flow is estimated using the Lucas-Kanade algorithm) fails to track a large amount of gridpoints from one frame to the next. This scenario would probably allow even a panning camera to work as the algorithm is very resilient to motion disturbances.
Hope this pointers are of some help. Good Luck and enjoy the journey! =D
Use one of the standard measures like Mean Squared Error, for eg. to find out the difference between two consecutive images. If the MSE is beyond a certain threshold, you know that there is some motion.
Also read about Motion Estimation.
if you know that the image will remain reletivly static I would reccomend:
1) look into neural networks. you can use them to learn what defines someone within the image or what is a non-something in the image.
2) look into motion detection algorithms, they are used all over the place.
3) is you camera capable of thermal imaging? if so it may be worthwile to look for hotspots in the images. There may be existing algorithms to turn your webcam into a thermal imager.
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)
I'm trying to write a simple tracking routine to track some points on a movie.
Essentially I have a series of 100-frames-long movies, showing some bright spots on dark background.
I have ~100-150 spots per frame, and they move over the course of the movie. I would like to track them, so I'm looking for some efficient (but possibly not overkilling to implement) routine to do that.
A few more infos:
the spots are a few (es. 5x5) pixels in size
the movement are not big. A spot generally does not move more than 5-10 pixels from its original position. The movements are generally smooth.
the "shape" of these spots is generally fixed, they don't grow or shrink BUT they become less bright as the movie progresses.
the spots don't move in a particular direction. They can move right and then left and then right again
the user will select a region around each spot and then this region will be tracked, so I do not need to automatically find the points.
As the videos are b/w, I though I should rely on brigthness. For instance I thought I could move around the region and calculate the correlation of the region's area in the previous frame with that in the various positions in the next frame. I understand that this is a quite naïve solution, but do you think it may work? Does anyone know specific algorithms that do this? It doesn't need to be superfast, as long as it is accurate I'm happy.
Thank you
nico
Sounds like a job for Blob detection to me.
I would suggest the Pearson's product. Having a model (which could be any template image), you can measure the correlation of the template with any section of the frame.
The result is a probability factor which determine the correlation of the samples with the template one. It is especially applicable to 2D cases.
It has the advantage to be independent from the sample absolute value, since the result is dependent on the covariance related with the mean of the samples.
Once you detect an high probability, you can track the successive frames in the neightboor of the original position, and select the best correlation factor.
However, the size and the rotation of the template matter, but this is not the case as I can understand. You can customize the detection with any shape since the template image could represent any configuration.
Here is a single pass algorithm implementation , that I've used and works correctly.
This has got to be a well reasearched topic and I suspect there won't be any 100% accurate solution.
Some links which might be of use:
Learning patterns of activity using real-time tracking. A paper by two guys from MIT.
Kalman Filter. Especially the Computer Vision part.
Motion Tracker. A student project, which also has code and sample videos I believe.
Of course, this might be overkill for you, but hope it helps giving you other leads.
Simple is good. I'd start doing something like:
1) over a small rectangle, that surrounds a spot:
2) apply a weighted average of all the pixel coordinates in the area
3) call the averaged X and Y values the objects position
4) while scanning these pixels, do something to approximate the bounding box size
5) repeat next frame with a slightly enlarged bounding box so you don't clip spot that moves
The weight for the average should go to zero for pixels below some threshold. Number 4 can be as simple as tracking the min/max position of anything brighter than the same threshold.
This will of course have issues with spots that overlap or cross paths. But for some reason I keep thinking you're tracking stars with some unknown camera motion, in which case this should be fine.
I'm afraid that blob tracking is not simple, not if you want to do it well.
Start with blob detection as genpfault says.
Now you have spots on every frame and you need to link them up. If the blobs are moving independently, you can use some sort of correspondence algorithm to link them up. See for instance http://server.cs.ucf.edu/~vision/papers/01359751.pdf.
Now you may have collisions. You can use mixture of gaussians to try to separate them, give up and let the tracks cross, use any other before-and-after information to resolve the collisions (e.g. if A and B collide and A is brighter before and will be brighter after, you can keep track of A; if A and B move along predictable trajectories, you can use that also).
Or you can collaborate with a lab that does this sort of stuff all the time.
I have nothing useful to do and was playing with jigsaw puzzle like this:
alt text http://manual.gimp.org/nl/images/filters/examples/render-taj-jigsaw.jpg
and I was wondering if it'd be possible to make a program that assists me in putting it together.
Imagine that I have a small puzzle, like 4x3 pieces, but the little tabs and blanks are non-uniform - different pieces have these tabs in different height, of different shape, of different size. What I'd do is to take pictures of all of these pieces, let a program analyze them and store their attributes somewhere. Then, when I pick up a piece, I could ask the program to tell me which pieces should be its 'neighbours' - or if I have to fill in a blank, it'd tell me how does the wanted puzzle piece(s) look.
Unfortunately I've never did anything with image processing and pattern recognition, so I'd like to ask you for some pointers - how do I recognize a jigsaw piece (basically a square with tabs and holes) in a picture?
Then I'd probably need to rotate it so it's in the right position, scale to some proportion and then measure tab/blank on each side, and also each side's slope, if present.
I know that it would be too time consuming to scan/photograph 1000 pieces of puzzle and use it, this would be just a pet project where I'd learn something new.
Data acquisition
(This is known as Chroma Key, Blue Screen or Background Color method)
Find a well-lit room, with the least lighting variation across the room.
Find a color (hue) that is rarely used in the entire puzzle / picture.
Get a color paper that has that exactly same color.
Place as many puzzle pieces on the color paper as it'll fit.
You can categorize the puzzles into batches and use it as a computer hint later on.
Make sure the pieces do not overlap or touch each other.
Do not worry about orientation yet.
Take picture and download to computer.
Color calibration may be needed because the Chroma Key background may have upset the built-in color balance of the digital camera.
Acquisition data processing
Get some computer vision software
OpenCV, MATLAB, C++, Java, Python Imaging Library, etc.
Perform connected-component on the chroma key color on the image.
Ask for the contours of the holes of the connected component, which are the puzzle pieces.
Fix errors in the detected list.
Choose the indexing vocabulary (cf. Ira Baxter's post) and measure the pieces.
If the pieces are rectangular, find the corners first.
If the pieces are silghtly-off quadrilateral, the side lengths (measured corner to corner) is also a valuable signature.
Search for "Shape Context" on SO or Google or here.
Finally, get the color histogram of the piece, so that you can query pieces by color later.
To make them searchable, put them in a database, so that you can query pieces with any combinations of indexing vocabulary.
A step back to the problem itself. The problem of building a puzzle can be easy (P) or hard (NP), depending of whether the pieces fit only one neighbour, or many. If there is only one fit for each edge, then you just find, for each piece/side its neighbour and you're done (O(#pieces*#sides)). If some pieces allow multiple fits into different neighbours, then, in order to complete the whole puzzle, you may need backtracking (because you made a wrong choice and you get stuck).
However, the first problem to solve is how to represent pieces. If you want to represent arbitrary shapes, then you can probably use transparency or masks to represent which areas of a tile are actually part of the piece. If you use square shapes then the problem may be easier. In the latter case, you can consider the last row of pixels on each side of the square and match it with the most similar row of pixels that you find across all other pieces.
You can use the second approach to actually help you solve a real puzzle, despite the fact that you use square tiles. Real puzzles are normally built upon a NxM grid of pieces. When scanning the image from the box, you split it into the same NxM grid of square tiles, and get the system to solve that. The problem is then to visually map the actual squiggly piece that you hold in your hand with a tile inside the system (when they are small and uniformly coloured). But you get the same problem if you represent arbitrary shapes internally.