Particle Swarm Optimization for Picture Analysis

Roland Piquepaille writes "Particle swarm optimization (PSO) is a computer algorithm based on a mathematical model of the social interactions of swarms which was first described in 1995. Now, researchers in the UK and Jordan have carried this swarm approach to photography to 'intelligently boost contrast and detail in an image without distorting the underlying features.' This looks like a clever concept even if I haven't seen any results. The researchers have developed an iterative process where a swarm of images are created by a computer. These images are 'graded relative to each other, the fittest end up at the front of the swarm until a single individual that is the most effectively enhanced.'"

The only problem...

[arrrrg]

with PSO, ant colony optimization, genetic algorithms, etc. is that they take tons of computational effort, and typically work no better than (or significantly worse than) much more efficient direct optimization methods. Wake me up if they show good results (esp. that didn't take a year of computer time to construct).

P.S. IAAAIR (I am an AI researcher, albeit not in computer vision)

Re:The only problem...

[TapeCutter]

"the fittest end up at the front of the swarm until a single individual that is the most effectively enhanced"

Actually I think the biggest problem with any of these techniques is finding an algorithmic definition of 'fittest' and 'effectively', the rest can be solved by throwing money at the computation.

Not exactly comprehensive

[vikstar]

For more detail, including the citation of the paper, see this http://www.primidi.com/2008/02/03.html [primidi.com]

Re:The only problem...

[NickBoje]

You are hundred and one percent right. PSO works mainly with the help of two arbitrary coefficients which are highly oscillatory. Main effort is involved in selecting those coefficient values, accurately. Very good technique but very few good applications solved ...,

Nothing new to see here

[kegon]

They've reinvented genetic algorithms ?

Without seeing the details (read TFA but it's a summary and quite a bad one at that), I can't see why this would be better than a Bayesian optimisation with a photometric constraint. "The objective of the algorithm is to maximize the total number of pixels in the edges" sounds very, very simplified.

There are efficient ways of solving these things. Interesting that they invent an image processing algorithm but publish it in a non image processing journal - I wonder why that is ?

Re:The only problem...

[rucs_hack]

with PSO, ant colony optimization, genetic algorithms, etc. is that they take tons of computational effort, and typically work no better than (or significantly worse than) much more efficient direct optimization methods. Wake me up if they show good results (esp. that didn't take a year of computer time to construct).

Oh god, not another 'Bayesian methods for everything' guy..

Genetic algorithms have major advantages over other approaches. When designed well they are easy to code, and they can get tasks done as well as, if not better then the alternative techniques. I have a GA that can outperform a neural network on a particular task (not all tasks, just one very hard pattern recognition task, not going into it though, that would result in too long a post). It outperforms NN, and is so much simpler you wouldn't believe it. I was shocked to discover how much better it was, and I wrote it.

As for computational effort, well duh..

If it wasn't a task that needed a lot of computational effort, it would hardly be interesting, probably it would be in P or something.

ACO does tend to take a while, but in my experience, most really interesting GAs can take weeks to complete a single run. As a rule what your after is the finished result, and the time taken, provided it doesn't run for more than a few weeks, is usually not much of an issue.

Re:Bullshit FTA

[EB FE]

The claim of TFA is not that their algorithm can take one blurry image and generate a less blurry image. The algorithm uses a series of pictures of the same subject (I assume something similar to bracketing exposures) and use the data from most of those images to sharpen edges in the image that already contains the most clearly defined edges. Imagining how this works is pretty simple. Suppose the best image has an edge that appears to be on pixel columns x and x+1 and those pixels have luminance values a and b. Another image of the same subject may have the corresponding edge on columns x+1 and x+2 with lum vals c and d, and so forth... Then, it's a matter of combining the information from the pixels to produce a better edge. Fair results could probably be achieved with something like a weighted average, but I'm sure the algorithm the researchers in the article use is better.

Re:The only problem...

[ceoyoyo]

Two excellent points about why you wouldn't want to apply a GA to photography, one yours and one mine.

Mine first: you're right, GAs are easy to program, once you know the selection criteria. How do you have the computer select the best looking photo? Photoshop has for years had a feature where the computer will supply some altered images and let YOU pick the right one, but how do you give the computer a sense of esthetics?

Yours: GAs are great for finding finished products that you can then use. Both GAs and neural networks can turn up interesting algorithms etc. But they're not great algorithms for getting things done. I don't want to have to apply them to each photograph, I want to have them produce an algorithm or trained network or something of that nature that I can in turn apply to each photograph.