If I have a large set of data that describes physical 'things', how could I go about measuring how well that data fits the 'things' that it is supposed to represent?
An example would be if I have a crate holding 12 widgets, and I know each widget weighs 1 lb, there should be some data quality 'check' making sure the case weighs 13 lbs maybe.
Another example would be that if I have a lamp and an image representing that lamp, it should look like a lamp. Perhaps the image dimensions should have the same ratio of the lamp dimensions.
With the exception of images, my data is 99% text (which includes height, width, color...).
I've studied AI in school, but have done very little outside of that.
Are standard AI techniques the way to go? If so, how do I map a problem to an algorithm?
Are some languages easier at this than others? Do they have better libraries?
thanks.
Your question is somewhat open-ended, but it sounds like you want is what is known as a "classifier" in the field of machine learning.
In general, a classifier takes a piece of input and "classifies" it, ie: determines a category for the object. Many classifiers provide a probability with this determination, and some may even return multiple categories with probabilities on each.
Some examples of classifiers are bayes nets, neural nets, decision lists, and decision trees. Bayes nets are often used for spam classification. Emails are classified as either "spam" or "not spam" with a probability.
For you question you'd want to classify your objects as "high quality" or "not high quality".
The first thing you'll need is a bunch of training data. That is, a set of objects where you already know the correct classification. One way to obtain this could be to get a bunch of objects and classify them by hand. If there are too many objects for one person to classify you could feed them to Mechanical Turk.
Once you have your training data you'd then build your classifier. You'll need to figure out what attributes are important to your classification. You'll probably need to do some experimentation to see what works well. You then have your classifier learn from your training data.
One approach that's often used for testing is to split your training data into two sets. Train your classifier using one of the subsets, and then see how well it classifies the other (usually smaller) subset.
AI is one path, natural intelligence is another.
Your challenge is a perfect match to Amazon's Mechanical Turk. Divvy your data space up into extremely small verifiable atoms and assign them as HITs on Mechanical Turk. Have some overlap to give yourself a sense of HIT answer consistency.
There was a shop with a boatload of component CAD drawings that needed to be grouped by similarity. They broke it up and set it loose on Mechanical Turk to very satisfying results. I could google for hours and not find that link again.
See here for a related forum post.
This is a tough answer. For example, what defines a lamp? I could google images a picture of some crazy looking lamps. Or even, look up the definition of a lamp (http://dictionary.reference.com/dic?q=lamp). Theres no physical requirements of what a lamp must look like. Thats the crux of the AI problem.
As for data, you could setup Unit testing on the project to ensure that 12 widget() weighs less than 13 lbs in the widetBox(). Regardless, you need to have the data at hand to be able to test things like that.
I hope i was able to answer your question somewhat. Its a bit vauge, and my answers are broad, but hopefully it'll at least send you in a good direction.
Related
Could a CNN tell the difference between different size range of the same organism? Like a puppy vs a adult or a child vs an adult? Or more like a large fly vs a small fly, where they look identical but one is just larger than the other?
This is a tricky question to answer but usually theoretical CNN is able to do. It is mainly dependent on the training data itself. In case of a child vs adult, you can gather a dataset that includes alot of variances in sizes and ages in order to make sure that you will have CNN model that able to find patterns and generalize at the end. At the end, the CNN will learn many other features that make the classification scale or size invariant (In dependent of Size) such as shapes,colors, clothes and face features ....etc. Such Intra-class classification problems, it is not easily tackled with traditional supervised learning and therefore some researchers are applying an approach called "Deep Metric Learning".
Metric learning is the task of learning a distance function over objects. A metric or distance function has to obey four axioms: non-negativity, identity of indiscernibles, symmetry and subadditivity (or the triangle inequality). In practice, metric learning algorithms ignore the condition of identity of indiscernibles and learn a pseudo-metric.Wiki Definition
It would be better to differentiate the metric that you mention in the question. At first, it is a different task to recognize age and size.
About the age, yes, it is doable. For deep learning-based approach, you will need appropriate data. For non-training based approach (old-school image processing), you would need to create some metrics for each object based on age (counting the wrinkle, white hair etc. for humans)
About the size, unfortunately, it is still under research and it is not clear to mention if it is properly doable or not. Whenever we mention object size recognition from a single image, there are more things to consider. The first thing is the perspective. If the object found in the image is large with respect to the image coordinates, is it close to the camera, even though its size is tiny, hence, it is showing as large or it is really huge but too far away from the camera? Such a problem may be overcome by knowing the object geometry in prior and by developing an algorithm based on that geometry along with deep learning. However, current deep learning technology is not accurate enough to distinguish the dimensions and location, hence object geometry precisely yet.
Another alternative would be to control the environment. For example, if you know that both objects lie on the same plane (i.e. on the table, next to each other) in the real world, the rest is a trivial problem to resolve.
I am using the Caffe framework for CNN training. My aim is to perform simple object recognition for a few basic object categories. Since pretrained networks are not an alternative for my proposed usage I prepared an own training- and testset with about 1000 images for each of 2 classes (say chairs and cars).
The results are quite good. If I present an yet unseen image of a chair it is likely classified as such, same for a car image. My problem is that the results on miscellaneous images that do not show any of these classes often shows a very high confidence (=1) for one random class (which is not surprising regarding the onesided training data but a problem for my application). I thought about different solutions:
1) Adding a third class with also about 1000 negative examples that shows any objects except a chair and a car.
2) Adding more object categories in general, just to let the network classify other objects as such and not any more as a chair or car (of course this would require much effort). Maybe also the broader prediction results would show a more uniform distribution at negative images, allowing to evaluate the target objects presence based on a threshold?
Because it was not much time-consuming to grab random images as negative examples from the internet, I already tested my first solution with about 1200 negative examples. It helped, but the problem remains, perhaps because it were just too few? My concern is that if I increment the number of negative examples, the imbalance of the number of examples for each class leads to less accurate detection of the original classes.
After some research I found one person with a similar problem, but there was no solution:
Convolutional Neural Networks with Caffe and NEGATIVE IMAGES
My question is: Has anyone had the same problem and knows how to deal with it? What way would you recommend, adding more negative examples or more object categories or do you have any other recommendation?
The problem is not unique to Caffe or ConvNets. Any Machine Learning technique runs this risk. In the end, all classifiers take a vector in some input space (usually very high-dimensional), which means they partition that input space. You've given examples of two partitions, which helps to estimate the boundary between the two, but only that boundary. Both partitions have very, very large boundaries, precisely because the input space is so high-dimensional.
ConvNets do try to tackle the high-dimensionality of image data by having fairly small convolution kernels. Realistic negative data helps in training those, and the label wouldn't really matter. You could even use the input image as goal (i.e. train it as an autoencoder) when training the convolution kernels.
One general reason why you don't want to lump all counterexamples is because they may be too varied. If you have a class A with some feature value from the range [-1,+1] on some scale, with counterexamples B [-2,-1] and C [+1,+2], lumping B and C together creates a range [-2,+2] for counterexamples which overlaps the real real range. Given enough data and powerful enough classifiers, this is not fatal, but for instance an SVM can fail badly on this.
What are the different options and solutions (software) that will help distinguish professional (good) from amateur (bad) photo?
The criteria can be the contrast, sharpness, noise, presence of compression artifacts, etc. The question is, what are the tools that allow all this to determine it (the machine, not the man). For all of these criteria can be represented as mathematical models, you think?
Or in other words - to "feed" tool 1000 high-quality photos and 1000 substandard. And machine itself has identified the factors that distinguish the good from the bad image.
This is a quite vague definition of a problem. The only thing you have is 1000 high-quality photos and 1000 substandard photos. Your application however, is quite concrete, and I doubt (but I'm not sure) that you will find such a software.
Without looking to your images and have some tests is also difficult to say if contrast/gamma would be enough to classify them properly.
What you can do, if you know a bit of coding in matlab/python/C, is to use some existing libraries to try to solve your problem. I can't help you with that, as this itself is a quite tedious work, but, I can give you some insights.
To define your problem you will need:
Input: 1000 pro images, 1000 std images
You can represent this as 2000 images and a 2000 binary vector (1 for pro, 0 for std)
Features
Images itself might not give you enough information. What you can do is extract features from images. This step is called feature extraction and is an open research field in Computer Vision. There several feature extractors out there, you can try a couple of the most used ones, such as HoG or SIFT (have a look here for examples).
This feature extractors will give you a 1xM numerical vector for each image. With N images, you have a NxM matrix composed of N images and their descriptor.
Classification:
Once you managed to extract features from the image, having X = NxM data and y = label binary vector, you can use any machine learning algorithm, such as Deep Neural Networks, Random Forests, Supported Vector Machines, or any other one, to train your data, and classify it later.
By putting everything together, you might be able to get decent results.
Is this professional vs amateur photographer or equipment classification? I mean like distinguishing between a DLSR photo or a cell phone photo. Or is this distinguishing between an amateur with a DLSR and a professional with the same equipment? Or, are we talking about photoshop editing at the end.
In the case of equipment, I think features to look at would be noise, contrast, color gamut. In the case of skill of the photographer, you will probably have to look at features based on edge representations, natural scene metrics etc.
But, you will need to create a data matrix and then run a machine learning classification algorithm on it and hopefully find some features.
Are you making or looking for art for humans or for robots?
The definition of a great photo is subjective by definition. What to one person may be junk to another is genius. Trying to take that and turn it into an equation is asking for AI to take over humankind.
I don't mean to be harsh in my assessment. My degree is in Fine Art, Painting. I put a lot of time and effort into thinking about images. It's a wonder to me how a child might make an image that seemed to be thoughtless but was a breakthrough in my perception. Conversely you can work for hours, day, months or even years and then feel like the result just doesn't measure up.
Photography is an ingenious invention, therefore all photography is a source for amazement.
I do agree with you however. Some photos are truly impressive. I think that if we approach this as coders than what we are seeking is 'likes' or 'page views' or some other method of getting counts from many people. I know that is not the answer you were looking for but I don't think you can find a better one. I wish you well on your quest.
If you want to judge a photo on technicalities then the edge of the physics should be your target. Currently that would be mirrorless cameras and 3d imaging.
I have a pairs of images (input-output) but I don't know the transformation to going from A (input) to B (output). I want to record image A and get image B. Physically I can change the setup to get A or B, but I want to do it by software.
If I understood well, a trained Artificial Neural Network is able to do that, having an input can give the corresponding output, is it right?
Is there any software/ANN that just "training" it with entering a number of input-output pairs will be able to provide the correct output if the input is a new (but similar to the others) image?
Thanks
If you have some relevant amount of image pairs (input/output pair) and you don't know transformation between input and output you could train ANN on that training set to imitate that unknown transformation. You will be able to well train your ANN only if you have sufficient amount of training image pairs, but it could be pretty impossible when that unknown transformation is complicated.
For example if that transformation simply increases intensity values of pixels at input image by given value, ANN will very fast learn to imitate that behavior, but if that unknown transformation is some complicated convolution or few serial convolutions or something more complicated it will be very hard, near impossible to train ANN to imitate that transformation. So, more complex transformation will need bigger training set and more complex ANN design.
There are plenty of free opensource ANN libraries implemented in many languages. You could start for example with that tutorial: http://www.codeproject.com/Articles/13091/Artificial-Neural-Networks-made-easy-with-the-FANN
What you are asking is possible in principle -- in theory, an ANN with sufficiently many hidden units can learn an arbitrary function to map inputs to outputs. However, as the comments and other answers have mentioned, there may be many technical issues with your particular problem that could make it impractical. I would classify these problems as (a) mapping complexity, (b) model complexity, (c) scaling complexity, and (d) implementation complexity. They are all somewhat related, but hopefully this is a useful way to break things down.
Mapping complexity
As mentioned by Springfield762, there are many possible functions that map from one image to another image. If the relationship between your input images and your output images is relatively simple -- like increasing the intensity of each pixel by a constant amount -- then an ANN would be able to learn this mapping without much difficulty. There are probably many more transformations that would be similarly easy to learn, such as skewing, flipping, rotating, or translating an image -- basically any affine transformation would be easy to learn. Other, nonlinear transformations could also be feasible, such as squaring the intensity of each pixel.
As a general rule, the more complicated the relationship between your input and output images, the more difficult it will be to get a model to learn this mapping for you.
Model complexity
The more complex the mapping from inputs to outputs, the more complex your ANN model will be to be able to capture this mapping. Models with many hidden layers have been shown in the past 10 years to perform quite well on tasks that people had previously thought impossible, but often these state-of-the-art models have millions or even billions of parameters and take weeks to train on GPU hardware. A simple model can capture many simple mappings, but if you have a complex input-output map to learn, you'll need a large, complex model.
Scaling complexity
Yves mentioned in the comments that it can be difficult to scale models up to typical image sizes. If your images are relatively small (currently the state of the art is to model images on the order of 100x100 pixels), then you can probably just throw a bunch of raw pixel data at an ANN model and see what happens. But if you're using 6000x4000 images from your shiny Nikon DSLR, it's going to be quite difficult to process those in a reasonable amount of time. You'd be better off compressing your image data somehow (PCA is a common technique) and then trying to learn the mapping in the compressed space.
In addition, larger images will have a larger space of possible mappings between them, so you'll need more of your larger images as training data than you would if you had small images.
Springfield762 also mentioned this: If the mapping between your input and output images is simple, then you'll only need a few examples to learn the mapping successfully. But if you have a complicated mapping, then you'll need much more training data to have a chance at learning the mapping properly.
Implementation complexity
It's unlikely that a tool already exists that would let you just throw image data into an ANN model and have a mapping appear. Most likely you'll need, at a minimum, to implement some code that will pre-process your image data. In addition, if you have lots of large images you'll probably need to write code to handle loading data from disk, etc. (There are a lot of "big data" tools for things like this, but they all require some amount of work to get set up.)
There are many, many open source ANN toolkits out there nowadays. FANN (already mentioned) is a popular one in C++ with bindings in other languages. Caffe is quite popular, and is also implemented in C++ with bindings. There seem to be many toolkits that use Python and Theano or some other GPU acceleration library -- Keras, Lasagne, Hebel, Pylearn2, neon, and Theanets (I wrote this one). Many people use Torch, written in Lua. Matlab has at least one neural network toolbox. I'm less familiar with other ecosystems, but Java seems to have Deeplearning4j, C# has Accord, and even R has darch.
But with any of these neural network toolkits, you're going to have to write some code to load the data, process it into the appropriate input format, construct (or load) a network model, train the model, etc.
The problem you're trying to solve is a canonical classification problem that neural networks can help you solve. You treat the B images as a set of labels that you match to A, and once trained, the neural network will be able to match the B images to new input based on where the network locates new input in a high-dimensional vector space. I assume you'd use some combination of convolutional networks to create your features, and softmax for multinomial classification on the output layer. More here: http://deeplearning4j.org/convolutionalnets.html
Since this has been written there has been a lot of work in the realm of cgans ( conditional generative adversarial networks ) please refer to:
https://arxiv.org/pdf/1611.07004.pdf
I have been playing around with different data clustering algorithms working on finding clusters between random data points represented an nodes, I keep reading that data clustering is used for image recognition. I am failing to make the connection, how does clustering data help in recognizing an image or in facial recognition. can someone explain this?
It's no surprise that clustering is used for pattern recognition at large, and image recognition in particular: clustering is a reducing process, and images in this megapixel era need boiling down... It is also a process which produces categories and that is of course useful.
However there are many approaches to the use of clustering as a technique for image recognition. One of the reasons for this diversity is that clustering can be applied at different level, for different purposes: from basic pixel level to feature level (feature be a line, a geometric figure...), for classification or for other purposes.
At a very high level, clustering is a statistical tool, it helps discovering the relative importance of various dimensions in defining the belonging of particular item to a particular category.
One [of many] usage[s] of such a tool, is with supervised learning, whereby a set of human-selected items (say images) are fed into the cluster-based logic, along with a label associated with a particular item ("this is an apple", "this is another apple", "this is a lemon"...), the clustering logic then determines how much each dimension of the input matters for helping each group of items (apples, lemons...) fit in a distinct cluster (for example the color may matter relatively little, but the shape, or the presence of dots, or whatever may matter a lot). After this training phase, new images can be fed to the logic and by seeing how close to a particular cluster this image falls, it is "recognized" (as a banana!).
When it comes to image processing one needs to remember that whatever is "fed" to the clustering logic is not necessarily (in fact, rarely) the raw pixels, but various "objects"
characterizing various "elements" of the original data (essentially a collection of relatively high dimension vectors, not unlike some that one may have encountered in other other data clustering examples), and produced by previous stages of the process. For example a important element of facial recognition is probably the exact distance between the center of the eyes. In previous stages, the image is processed in a way that figures out where the eyes are (possibly relying on another clustering-based logic). Then the distance between the eyes, along with many other elements are fed to the final clustering logic.
The preceding description is only one example of the use of clustering for image recognition. Indeed, various forms of neural networks have been used, very successfully, in this domain, and it can be argued that in a sense these neural networks are clustering information. One of the reasons for the success of neural nets may lie in their ability to be more respectful of the locality dimension as found in the original input, and also their ability to work in a hierarchical fashion.
A good conclusion to this write up would be a short list of online resources, but I'm pressed for time at the moment... "to be continued" ;-)
Next day edit: (failed attempt to provide an introductory online bibliography on the subject)
My search for literature on the topic of clustering as applied to artificial vision and image processing revealed two distinct... clusters ;-)
Books such as Algorithms for image processing and computer vision J Parkey pub Wiley, or Machine Vision : Theory, Algorithms, Practicalities M Seul et. Al Cambridge UP. Such books generally cover the all important techniques associated with noise reduction, Edge detection, Color or intensity conversion, and many other elements of the image processing chain, most of which do not involve clustering or even statistical methods, and they reserve only a chapter or two, or even minor mentions, to clustering, as applied to pattern recognition or to other tasks.
Scholarly papers and conference handbooks, which specifically cover clustering techniques applied to artificial vision and such, but in the narrowest and deepest fashion (ex: Variations on the Fukunaga and Narendra algorithm, for applications in character recognition, or Fast methods for selections of Nearest Neighbor candidates in whatever context.)
In short I feel ill equipped to make any specific book or article suggestion.
You may find it informative to browse titles in say Google books, keying in by "Artificial vision" or "Image Recognition" or some or the titles mentioned above. With the preview feature and also the tag cloud (btw another application of clustering) found in the "about this book" link, one can get a good idea of the various books contents and maybe decide to purchase some of them. Unfortunately the reduced readership and the potentially lucrative applications in the field make these books relatively expensive. At the other end of the spectrum, you may download, sometimes for free, research papers discussing advanced topics in the field. These will also show up on regular (web) Google, or at specialized repositories such as CiteSeer.
Good luck with your exploration in that field!