I have more than a million images those I will like to use as training data. How do I make this data available freely without compromising security?
I want the users to be able to use it quickly for training purpose, without giving hackers a chance to rebuild images from the open source data. At the same time I do not want that the training quality will be affected in any way.
In other words how do I safely open-source images?
For e.g. This code generates numpy array. I just want to make it very difficult to reconstruct the original image from the ndarray "x" in this case.
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
i = load_img('some_image.jpg' )
x = img_to_array(i)
x = x.reshape((1,) + x.shape)
I can share the array x once I know that the hackers can not use the data and create the same image.
If you aim to publish open-source pictures, a good start would be to understand how WikiCommons works. They had and must face many challenges of this kind, there is a lot of things to learn from there.
If your audience needs the complete picture to be served to make their models work, then no matter how you try to obfuscate the array containing the data. Smart guys that have enough time and creativity will be able to reconstruct the original picture. This is not a viable solution, it only provides a false secure feeling.
If you choose a destructive approach, not to serve the actual picture, but some digest/hash/fingerprint of it, then you will probably reduce the risk of reconstructing the original picture (beware there are very clever guys with strong cryptographic skills). But then your audience will not be able to learn from the picture itself so you may not achieve your goal.
Less destructive and may not fit your requirement: adding noise. It will not prevent disclosure of sensitive material (human eyes and brain are somehow good to classification) and it is a well know technique for AI confusion. Not a good solution too.
In anyway, if you serve without care sensitive material that does not fit open source, then you may get yourself and other people in trouble. This is not a good option.
My advice,
If your pictures really suit to open source policy, then serve them as this and do not worry about hackers, they are customers as well;
If your picture are sensitive, then do not serve them as open source. Instead provide a framework with a layer of security and implement required regulations you must take into account (ToS, IP, Copyright, GDPR).
All machine learning algorithms take the real images and convert the images to tensors, and process them in batches (multiple images at a time).
Couple of options for you:
You can share your images with your teammates and relay on trust.
You can somehow obfuscate the images as bunch of files, or you can create the algorithm to convert them to numpy array (or tensor), obfuscate them, and provide the procedure to revert them back without losses.
But in all these cases, non wanted people can somehow guess your procedure/obfuscation.
Ideal would be to create the Machine Learning model (like VGG, ResNet, Inception) from your images, and then you can distribute your model that learned what you planed from your images.
Bottom line, in ML you need images to learn something from them, and not the images per se.
Privacy is really a problem as we can see from this document dealing with how copyright is causing a decay in public datasets.
There are no many solutions to this problem, because privacy really matters. However, this idea with GANs may be encouraging.
If you don't use GANs, it is hard to tell what would be the right set of transforms you would need to undertake to escape the privacy policy concerns.
Just if you try to flip images, scale them, remove the metadata, normalize them, or transform one pixel is not enough. You would need make them indistinguishable from the originals.
Related
I have one image stored in my bundle or in the application.
Now I want to scan images in camera and want to compare that images with my locally stored image. When image is matched I want to play one video and if user move camera from that particular image to somewhere else then I want to stop that video.
For that I have tried Wikitude sdk for iOS but it is not working properly as it is crashing anytime because of memory issues or some other reasons.
Other things came in mind that Core ML and ARKit but Core ML detect the image's properties like name, type, colors etc and I want to match the image. ARKit will not support all devices and ios and also image matching as per requirement is possible or not that I don't have idea.
If anybody have any idea to achieve this requirement they can share. every help will be appreciated. Thanks:)
Easiest way is ARKit's imageDetection. You know the limitation of devices it support. But the result it gives is wide and really easy to implement. Here is an example
Next is CoreML, which is the hardest way. You need to understand machine learning even if in brief. Then the tough part - training with your dataset. Biggest drawback is you have single image. I would discard this method.
Finally mid way solution is to use OpenCV. It might be hard but suit your need. You can find different methods of feature matching to find your image in camera feed. example here. You can use objective-c++ to code in c++ for ios.
Your task is image similarity you can do it simply and with more reliable output results using machine learning. Since your task is using camera scanning. Better option is CoreML.You can refer this link by apple for Image Similarity.You can optimize your results by training with your own datasets. Any more clarifications needed comment.
Another approach is to use a so-called "siamese network". Which really means that you use a model such as Inception-v3 or MobileNet and both images and you compare their outputs.
However, these models usually give a classification output, i.e. "this is a cat". But if you remove that classification layer from the model, it gives an output that is just a bunch of numbers that describe what sort of things are in the image but in a very abstract sense.
If these numbers for two images are very similar -- if the "distance" between them is very small -- then the two images are very similar too.
So you can take an existing Core ML model, remove the classification layer, run it twice (once on each image), which gives you two sets of numbers, and then compute the distance between these numbers. If this distance is lower than some kind of threshold, then the images are similar enough.
4 years ago I posted this question and got a few answers that were unfortunately outside my skill level. I just attended a build tour conference where they spoke about machine learning and this got me thinking of the possibility of using ML as a solution to my problem. i found this on the azure site but i dont think it will help me because its scope is pretty narrow.
Here is what i am trying to achieve:
i have a source image:
and i want to which one of the following symbols (if any) are contained in the image above:
the compare needs to support minor distortion, scaling, color differences, rotation, and brightness differences.
the number of symbols to match will ultimately at least be greater than 100.
is ML a good tool to solve this problem? if so, any starting tips?
As far as I know, Project Oxford (MS Azure CV API) wouldn't be suitable for your task. Their APIs are very focused to Face related tasks (detection, verification, etc), OCR and Image description. And apparently you can't extend their models or train new ones from the existing ones.
However, even though I don't know an out of the box solution for your object detection problem; there are easy enough approaches that you could try and that would give you some start point results.
For instance, here is a naive method you could use:
1) Create your dataset:
This is probably the more tedious step and paradoxically a crucial one. I will assume you have a good amount of images to work with. What would you need to do is to pick a fixed window size and extract positive and negative examples.
If some of the images in your dataset are in different sizes you would need to rescale them to a common size. You don't need to get too crazy about the size, probably 30x30 images would be more than enough. To make things easier I would turn the images to gray scale too.
2) Pick a classification algorithm and train it:
There is an awful amount of classification algorithms out there. But if you are new to machine learning I will pick the one I would understand the most. Keeping that in mind, I would check out logistic regression which give decent results, it's easy enough for starters and have a lot of libraries and tutorials. For instance, this one or this one. At first I would say to focus in a binary classification problem (like if there is an UD logo in the picture or not) and when you master that one you can jump to the multi-class case. There are resources for that too or you can always have several models one per logo and run this recipe for each one separately.
To train your model, you just need to read the images generated in the step 1 and turn them into a vector and label them accordingly. That would be the dataset that will feed your model. If you are using images in gray scale, then each position in the vector would correspond to a pixel value in the range 0-255. Depending on the algorithm you might need to rescale those values to the range [0-1] (this is because some algorithms perform better with values in that range). Notice that rescaling the range in this case is fairly easy (new_value = value/255).
You also need to split your dataset, reserving some examples for training, a subset for validation and another one for testing. Again, there are different ways to do this, but I'm keeping this answer as naive as possible.
3) Perform the detection:
So now let's start the fun part. Given any image you want to run your model and produce coordinates in the picture where there is a logo. There are different ways to do this and I will describe one that probably is not the best nor the more efficient, but it's easier to develop in my opinion.
You are going to scan the picture, extracting the pixels in a "window", rescaling those pixels to the size you selected in step 1 and then feed them to your model.
If the model give you a positive answer then you mark that window in the original image. Since the logo might appear in different scales you need to repeat this process with different window sizes. You also would need to tweak the amount of space between windows.
4) Rinse and repeat:
At the first iteration it's very likely that you will get a lot of false positives. Then you need to take those as negative examples and retrain your model. This would be an iterative process and hopefully on each iteration you will have less and less false positives and fewer false negatives.
Once you are reasonable happy with your solution, you might want to improve it. You might want to try other classification algorithms like SVM or Deep Learning Artificial Neural Networks, or to try better object detection frameworks like Viola-Jones. Also, you will probably need to use crossvalidation to compare all your solutions (you can actually use crossvalidation from the beginning). By this moment I bet you would be confident enough that you would like to use OpenCV or another ready to use framework in which case you will have a fair understanding of what is going on under the hood.
Also you could just disregard all this answer and go for an OpenCV object detection tutorial like this one. Or take another answer from another question like this one. Good luck!
can someone tell me how i can detect pictures of architecture or sculpture?
I think hough-transforming is a good approach. But i'm new in CV and maybe there a better methods to detect pattern. I heard about haarcascade. can i take this for architecture,too?
For example i want to detect those kind of pictures:
Image Hosted by ImageShack.us http://img842.imageshack.us/img842/4748/resizeimg0931.jpg
If you want an algorithm to detect them, then detecting an object from an image need a description of that object which can be understood by a machine or computer. For a sculpture or architecture, how can you have such uniform definition since they vary a lot in every sense? For example both your input images vary a lot. How can we differentiate between a house and an architecture? A lot of problems will rise in your question. Even with Hough Transforming, how you are supposed to differentiate a big house and a big architecture?
Check out this SOF : Image Processing: Algorithm Improvement for 'Coca-Cola Can' Recognition
He wants to detect coca-cola cans, and not coca-cola bottles. But if you look into it clearly, you will understand can and bottles are almost alike and it will be difficult to differentiate between them. You can find a lot of its difficulties in subsequent answers. Major problem is that, in some cases, it will be difficult for humans as well to differentiate them.
In your second image, even if you train some cascades for second image, there is a change it will detect live lions if they are present in your image, since a sculpture lion and an original lion seems almost same for a machine.
Haar cascades may not be much effective since you have to train for a lot of these kinds of images.
If you have some sample images and want to check if those things are there in your image, may be you can use SURF features etc. But you may need some sample images first to compare. For a demo of SURF, check out this SOF : OpenCV 2.4.1 - computing SURF descriptors in Python
Another option is template matching. But it is slow, and it is not scale and orientation invariant. And you need some template images for this
I think I have seen some papers relating this topic ( but i don't remember now). May be googling will get you them. I will update the answer if I get it.
I'm starting a search to implement a system that must count people flow of some place.
The final idea is to have something like http://www.youtube.com/watch?v=u7N1MCBRdl0 . I'm working with OpenCv to start creating it, I'm reading and studying about. But I'd like to know if some one can give me some hints of source code exemples, articles and anything elese that can make me get faster on my deal.
I started with blobtrack.exe sample to study, but I got not good results.
Tks in advice.
Blob detection is the correct way to do this, as long as you choose good threshold values and your lighting is even and consistent; but the real problem here is writing a tracking algorithm that can keep track of multiple blobs, being resistant to dropped frames. Basically you want to be able to assign persistent IDs to each blob over multiple frames, keeping in mind that due to changing lighting conditions and due to people walking very close together and/or crossing paths, the blobs may drop out for several frames, split, and/or merge.
To do this 'properly' you'd want a fuzzy ID assignment algorithm that is resistant to dropped frames (ie blob ID remains, and ideally predicts motion, if the blob drops out for a frame or two). You'd probably also want to keep a history of ID merges and splits, so that if two IDs merge to one, and then the one splits to two, you can re-assign the individual merged IDs to the resulting two blobs.
In my experience the openFrameworks openCv basic example is a good starting point.
I'll not put this as the right answer.
It is just an option for those who are able to read in Portugues or can use a translator. It's my graduation project and there is the explanation of a option to count people in it.
Limitations:
It's do not behave well on envirionaments that change so much the background light.
It must be configured for each location that you will use it.
Advantages:
It's fast!
I used OpenCV to do the basic features as, capture screen, go trough the pixels, etc. But the algorithm to count people was done by my self.
You can check it on this paper
Final opinion about this project: It's not prepared to go alive, to became a product. But it works very well as base for study.
I have made a videochat, but as usual, a lot of men like to ehm, abuse the service (I leave it up to you to figure the nature of such abuse), which is not something I endorse in any way, nor do most of my users. No, I have not stolen chatroulette.com :-) Frankly, I am half-embarassed to bring this up here, but my question is technical and rather specific:
I want to filter/deny users based on their video content when this content is of offending character, like user flashing his junk on camera. What kind of image comparison algorithm would suit my needs?
I have spent a week or so reading some scientific papers and have become aware of multiple theories and their implementations, such as SIFT, SURF and some of the wavelet based approaches. Each of these has drawbacks and advantages of course. But since the nature of my image comparison is highly specific - to deny service if a certain body part is encountered on video in a range of positions - I am wondering which of the methods will suit me best?
Currently, I lean towards something along the following (Wavelet-based plus something I assume to be some proprietary innovations):
http://grail.cs.washington.edu/projects/query/
With the above, I can simply draw the offending body part, and expect offending content to be considered a match based on a threshold. Then again, I am unsure whether the method is invariable to transformations and if it is, to what kind - the paper isn't really specific on that.
Alternatively, I am thinking that a SURF implementation could do, but I am afraid that it could give me false positives. Can such implementation be trained to recognize/give weight to specific feature?
I am aware that there exist numerous questions on SURF and SIFT here, but most of them are generic in that they usually explain how to "compare" two images. My comparison is feature specific, not generic. I need a method that does not just compare two similar images, but one which can give me a rank/index/weight for a feature (however the method lets me describe it, be it an image itself or something else) being present in an image.
Looks like you need not feature detection, but object recognition, i.e. Viola-Jones method.
Take a look at facedetect.cpp example shipped with OpenCV (also there are several ready-to-use haarcascades: face detector, body detector...). It also uses image features, called Haar Wavelets. You might be interested to use color information, take a look at CamShift algorithm (also available in OpenCV).
This is more about computer vision. You have to recognize objects in your image/video sequence, whatever... for that, you can use a lot of different algorithms (most of them work in the spectral domain, that's why you will have to use a transformation).
In order to be accurate, you will also need a knowledge base or, at least, some descriptors that will define the object.
Try OpenCV, it has some algorithms already implemented (and basic descriptors included).
There are applications/algorithms out there that you can "train" (like neural networks) and are able to identify objects based on the training. Most of them (at least, the good ones) are not very popular and can only be found in research groups specialized in computer vision, object recognition, AI, etc.
Good luck!