In the upcoming version of Photoshop there is a feature called Content-Aware fill.
This feature will fill a selection of an image based on the surrounding image - to the point it can generate bushes and clouds while being seamless with the surrounding image.
See http://www.youtube.com/watch?v=NH0aEp1oDOI for a preview of the Photoshop feature I'm talking about.
My question is:
How does this feature work algorithmically?
I am a co-author of the PatchMatch paper previously mentioned here, and I led the development of the original Content-Aware Fill feature in Photoshop, along with Ivan Cavero Belaunde and Eli Shechtman in the Creative Technologies Lab, and Jeff Chien on the Photoshop team.
Photoshop's Content-Aware Fill uses a highly optimized, multithreaded variation of the algorithm described in the PatchMatch paper, and an older method called "SpaceTime Video Completion." Both papers are cited on the following technology page for this feature:
http://www.adobe.com/technology/projects/content-aware-fill.html
You can find out more about us on the Adobe Research web pages.
I'm guessing that for the smaller holes they are grabbing similarly textured patches surrounding the area to fill it in. This is described in a paper entitled "PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing" by Connelly Barnes and others in SIGGRAPH 2009. For larger holes they can exploit a large database of pictures with similar global statistics or texture, as describe in "Scene Completion Using Millions of Photographs". If they somehow could fused the two together I think it should work like in the video.
There is very similar algorithm for GIMP for a quite long time. It is called resynthesizer and probably you should be able to find a source for it (maybe at the project site)
EDIT
There is also source available at the ubuntu repository
And here you can see processing the same images with GIMP: http://www.youtube.com/watch?v=0AoobQQBeVc&feature=related
Well, they are not going to tell for the obvious reasons. The general name for the technique is "inpainting", you can look this up.
Specifically, if you look at what Criminisi did while in Microsoft http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.9407 and what Todor Georgiev does now at Adobe http://www.tgeorgiev.net/Inpainting.html, you'll be able to make a very good guess. A 90% guess, I'd say, which should be good enough.
I work on a similar problem. From what i read they use "PatchMatch" or "non-parametric patch sampling" in general.
PatchMatch: A Randomized Correspondence Algorithm
for Structural Image Editing
As a guess (and that's all that it would be) I'd expect that it does some frequency analysis (some like a Fourier transform) of the image. By looking only at the image at the edge of the selection and ignoring the middle, it could then extrapolate back into the middle. If the designers choose the correct color plains and what not, they should be able to generate a texture that seamlessly blends into the image at the edges.
edit: looking at the last example in the video; if you look at the top of the original image on either edge you see that the selection line runs right down a "gap" in the clouds and that right in the middle there is a "bump". These are the kind of artifacts I'd expect to see if my guess is correct. (OTOH, I'd also expect to see them is it was using some kind of sudo-mirroring across the selection boundary.)
The general approach is either content-aware fill or seam-carving. Ariel Shamir's group is responsible for the seminal work here, which was presented in SIGGRAPH 2007. See:
http://www.faculty.idc.ac.il/arik/site/subject-seam-carve.asp
Edit: Please see answer from the co-author of Content-Aware fill. I will be deleting this soon.
Related
I'm going to match the sketch face (drawing photo) in to the color photo. so for the research i want to find out what are the challenges that matching sketch drawing in to color faces. for now i have find out that
resolution pixel difference
texture difference
distance difference
and color (not much effect)
I want to know (in technical terms) what are other challenges and what are available OPEN CV and JAVA CV method and algorithms to overcome that challenges?
Here is some example of the sketches and the photos that are known to match them:
This problem is called multi-modal face recognition. There has been a lot of interest in comparing a high quality mugshot (modality 1) to low quality surveillance images (modality 2), another is frontal images to profiles, or pictures to sketches like the OP is interested in. Partial Least Squares (PLS) and Tied Factor Analysis (TFA) have been used for this purpose.
A key difficulty is computing two linear projections from the image in modality 1 (and modality 2) to a space where two points being close means that the individual is the same. This is the key technical step. Here are some papers on this approach:
Abhishek Sharma, David W Jacobs : Bypassing Synthesis: PLS for
Face Recognition with Pose, Low-Resolution and Sketch. CVPR
2011.
S.J.D. Prince, J.H. Elder, J. Warrell, F.M. Felisberti, Tied Factor
Analysis for Face Recognition across Large Pose Differences, IEEE
Patt. Anal. Mach. Intell, 30(6), 970-984, 2008. Elder is a specialist in this area and has a variety of papers on the topic.
B. Klare, Z. Li and A. K. Jain, Matching forensic sketches to
mugshot photos, IEEE Pattern Analysis and Machine Intelligence, 29
Sept. 2010.
As you can understand this is an active research area/problem. In terms using OpenCV to overcome the difficulties, let me give you an analogy: you need to build build a house (match sketches to photos) and you're asking how will having a Stanley hammer (OpenCV) will help. Sure, it will probably help. But you'll also need a lot of other resources: wood, time/money, pipes, cable, etc.
I think that James Elder's old work on the completeness of the edge map (using reconstruction by solving the Laplace equation) is quite relevant here. See the results at the end of this paper: http://elderlab.yorku.ca/~elder/publications/journals/ElderIJCV99.pdf
You could give Eigenfaces a try, though i never tested them with sketches i think they could a least be a good starting point for your research.
See Wiki: http://en.wikipedia.org/wiki/Eigenface and the Tutorial for OpenCV: http://docs.opencv.org/modules/contrib/doc/facerec/facerec_tutorial.html (including not only Eigenfaces!)
OpenCV can be used for feature extraction and machine learning required for this task. I guess you can start with the papers in the answers above, start with some basic features and prototype a classifier with OpenCV.
I guess you might also want to detect and match feature points on the faces. If you use this approach, you will have to do the feature point detectors on your own (training the Viola-Jones detector in OpenCV with your own data is an option).
I dont know whether should I post this question here or not? But if someone knows it, please answer?
What are the algorithms for determining which region in an image is text and which one is graphic? Means how to separate such regions? (figure or diagram)
Most OCR software, e.g., Ocropus, support layout analysis, which is what you need.
Mao, Rosenfeld & Kanungo (2003) Document structure analysis algorithms: a literature survey provides a fairly recent survey of layout analysis algorithms.
first step would probably be to isolate the sharper contrast between text and image. This can be done by taking the derivative of the image. This will show the change in color and the high values would most likely then be compared to textual shapes
Recently I've been messing about with algorithms on images, partly for fun and partly to keep my programming skills sharp.
I've just implemented a 'nearest-neighbour' algorithm that picks n random pixels in an image, and then converts the colour of each other pixel in the image to the colour of its nearest neighbour in the set of n chosen pixels. The result is a kind of "frosted glass" effect on the image, for a reasonably large value of n (if n is too small then the image gets blocky).
I'm just wondering if anyone has any other good/fun algorithms on images that might be interesting to implement?
Tom
This book, Digital Image Processing, is one of the most commonly used books in image processing classes, and it will teach you a lot of basic techniques that will help you understand other algorithms better, like the ones Ants Aasma suggested.
Try making an Andy Warhol print. It's pretty easy in Java. For more ideas, just look at the filters available in GIMP or a similar program.
Marching Squares is a computer vision algorithm. Try using that to convert black and white raster images to object based scenes.
Turns the image into a pizza
Take N images, relate them via an MC-Escher-style painting
"Explode" an image from the inside out
Convert the image into a single-color blocks (piet-style) based on all the colours within.
How about tie-dye algorithm?
Fun to toy with and easy to code filters are:
kaleidoscope
lens
twirl
There are a lot of other filters, but especially the kaleidoscope gives much bang for the bucks. I have made my own graphics editor with lots of filters and is also looking for inspiration.
Instead of coding image filters, I personally would love to code Diffusion Curves, but unfortunately have little time for fun.
If you want to try something more challenging look for SIGGRAPH papers on the web. There are some really nifty image algorithms presented at that conference. Seam carving is one cool example that is reasonably straightforward to implement.
If you want something more challenging try to complete the symmetry of broken objects
I'm messing around with image manipulation, mostly using Python. I'm not too worried about performance right now, as I'm just doing this for fun. Thus far, I can load bitmaps, merge them (according to some function), and do some REALLY crude analysis (find the brightest/darkest points, that kind of thing).
I'd like to be able to take an image, generate a set of control points (which I can more or less do now), and then smudge the image, starting at a control point and moving in a particular direction. What I'm not sure of is the process of smudging itself. What's a good algorithm for this?
This question is pretty old but I've recently gotten interested in this very subject so maybe this might be helpful to someone. I implemented a 'smudge' brush using Imagick for PHP which is roughly based on the smudging technique described in this paper. If you want to inspect the code feel free to have a look at the project: Magickpaint
Try PythonMagick (ImageMagick library bindings for Python). If you can't find it on your distribution's repositories, get it here: http://www.imagemagick.org/download/python/
It has more effect functions than you can shake a stick at.
One method would be to apply a Gaussian blur (or some other type of blur) to each point in the region defined by your control points.
One method would be to create a grid that your control points moves and then use texture mapping techniques to map the image back onto the distorted grid.
I can vouch for a Gaussian Blur mentioned above, it is quite simple to implement and provides a fairly decent blur result.
James
I am building a web application using .NET 3.5 (ASP.NET, SQL Server, C#, WCF, WF, etc) and I have run into a major design dilemma. This is a uni project btw, but it is 100% up to me what I develop.
I need to design a system whereby I can take an image and automatically crop a certain object within it, without user input. So for example, cut out the car in a picture of a road. I've given this a lot of thought, and I can't see any feasible method. I guess this thread is to discuss the issues and feasibility of achieving this goal. Eventually, I would get the dimensions of a car (or whatever it may be), and then pass this into a 3d modelling app (custom) as parameters, to render a 3d model. This last step is a lot more feasible. It's the cropping issue which is an issue. I have thought of all sorts of ideas, like getting the colour of the car and then the outline around that colour. So if the car (example) is yellow, when there is a yellow pixel in the image, trace around it. But this would fail if there are two yellow cars in a photo.
Ideally, I would like the system to be completely automated. But I guess I can't have everything my way. Also, my skills are in what I mentioned above (.NET 3.5, SQL Server, AJAX, web design) as opposed to C++ but I would be open to any solution just to see the feasibility.
I also found this patent: US Patent 7034848 - System and method for automatically cropping graphical images
Thanks
This is one of the problems that needed to be solved to finish the DARPA Grand Challenge. Google video has a great presentation by the project lead from the winning team, where he talks about how they went about their solution, and how some of the other teams approached it. The relevant portion starts around 19:30 of the video, but it's a great talk, and the whole thing is worth a watch. Hopefully it gives you a good starting point for solving your problem.
What you are talking about is an open research problem, or even several research problems. One way to tackle this, is by image segmentation. If you can safely assume that there is one object of interest in the image, you can try a figure-ground segmentation algorithm. There are many such algorithms, and none of them are perfect. They usually output a segmentation mask: a binary image where the figure is white and the background is black. You would then find the bounding box of the figure, and use it to crop. The thing to remember is that none of the existing segmentation algorithm will give you what you want 100% of the time.
Alternatively, if you know ahead of time what specific type of object you need to crop (car, person, motorcycle), then you can try an object detection algorithm. Once again, there are many, and none of them are perfect either. On the other hand, some of them may work better than segmentation if your object of interest is on very cluttered background.
To summarize, if you wish to pursue this, you would have to read a fair number of computer vision papers, and try a fair number of different algorithms. You will also increase your chances of success if you constrain your problem domain as much as possible: for example restrict yourself to a small number of object categories, assume there is only one object of interest in an image, or restrict yourself to a certain type of scenes (nature, sea, etc.). Also keep in mind, that even the accuracy of state-of-the-art approaches to solving this type of problems has a lot of room for improvement.
And by the way, the choice of language or platform for this project is by far the least difficult part.
A method often used for face detection in images is through the use of a Haar classifier cascade. A classifier cascade can be trained to detect any objects, not just faces, but the ability of the classifier is highly dependent on the quality of the training data.
This paper by Viola and Jones explains how it works and how it can be optimised.
Although it is C++ you might want to take a look at the image processing libraries provided by the OpenCV project which include code to both train and use Haar cascades. You will need a set of car and non-car images to train a system!
Some of the best attempts I've see of this is using a large database of images to help understand the image you have. These days you have flickr, which is not only a giant corpus of images, but it's also tagged with meta-information about what the image is.
Some projects that do this are documented here:
http://blogs.zdnet.com/emergingtech/?p=629
Start with analyzing the images yourself. That way you can formulate the criteria on which to match the car. And you get to define what you cannot match.
If all cars have the same background, for example, it need not be that complex. But your example states a car on a street. There may be parked cars. Should they be recognized?
If you have access to MatLab, you could test your pattern recognition filters with specialized software like PRTools.
Wwhen I was studying (a long time ago:) I used Khoros Cantata and found that an edge filter can simplify the image greatly.
But again, first define the conditions on the input. If you don't do that you will not succeed because pattern recognition is really hard (think about how long it took to crack captcha's)
I did say photo, so this could be a black car with a black background. I did think of specifying the colour of the object, and then when that colour is found, trace around it (high level explanation). But, with a black object in a black background (no constrast in other words), it would be a very difficult task.
Better still, I've come across several sites with 3d models of cars. I could always use this, stick it into a 3d model, and render it.
A 3D model would be easier to work with, a real world photo much harder. It does suck :(
If I'm reading this right... This is where AI shines.
I think the "simplest" solution would be to use a neural-network based image recognition algorithm. Unless you know that the car will look the exact same in each picture, then that's pretty much the only way.
If it IS the exact same, then you can just search for the pixel pattern, and get the bounding rectangle, and just set the image border to the inner boundary of the rectangle.
I think that you will never get good results without a real user telling the program what to do. Think of it this way: how should your program decide when there is more than 1 interesting object present (for example: 2 cars)? what if the object you want is actually the mountain in the background? what if nothing of interest is inside the picture, thus nothing to select as the object to crop out? etc, etc...
With that said, if you can make assumptions like: only 1 object will be present, then you can have a go with using image recognition algorithms.
Now that I think of it. I recently got a lecture about artificial intelligence in robots and in robotic research techniques. Their research went on about language interaction, evolution, and language recognition. But in order to do that they also needed some simple image recognition algorithms to process the perceived environment. One of the tricks they used was to make a 3D plot of the image where x and y where the normal x and y axis and the z axis was the brightness of that particular point, then they used the same technique for red-green values, and blue-yellow. And lo and behold they had something (relatively) easy they could use to pick out the objects from the perceived environment.
(I'm terribly sorry, but I can't find a link to the nice charts they had that showed how it all worked).
Anyway, the point is that they were not interested (that much) in image recognition so they created something that worked good enough and used something less advanced and thus less time consuming, so it is possible to create something simple for this complex task.
Also any good image editing program has some kind of magic wand that will select, with the right amount of tweaking, the object of interest you point it on, maybe it's worth your time to look into that as well.
So, it basically will mean that you:
have to make some assumptions, otherwise it will fail terribly
will probably best be served with techniques from AI, and more specifically image recognition
can take a look at paint.NET and their algorithm for their magic wand
try to use the fact that a good photo will have the object of interest somewhere in the middle of the image
.. but i'm not saying that this is the solution for your problem, maybe something simpler can be used.
Oh, and I will continue to look for those links, they hold some really valuable information about this topic, but I can't promise anything.