Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I have images of the following type
etc..
What would be the easiest way of identifying what piece it is and if it is black or white? Do I need to use machine learning or is there an easier way?
It depends on your inputs. If all of your data looks like this (nice and clean, with contours being identical, just background and color changes), you could probably use some kind of pixel + color matching and you could be good to go.
You definitely know that deep learning and machine learning only approximate function (functions of pixels in this case), if you can find it (the function) without using those methods (with sensible amount of work), you always should.
And no, machine learning is not a silver bullet, you get an image and you throw it into convolutional neural networks black-box magic and you get your results, that's not the point.
Sorry but deep learning might be just an overkill to recognize a known set of images. Use template matching!
https://machinelearningmastery.com/using-opencv-python-and-template-matching-to-play-wheres-waldo/
You could do this using machine learning (plan or convolutional neural nets). This isn't that hard of a problem, but you have to do manual work of creating proper dataset with lots of pictures.
For example: For each piece you need to create picture with white/black field color. And you have to do different combinations, different chess piece sets vs. different table color schema. In order to make the system more robust to color schema you can try different color channels.
There are lots of questions, will the pictures you test always be in same resolution? If they aren't then you should also take that into consideration when creating dataset.
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 2 years ago.
Improve this question
I'm curious what a 3D implementation of conway's game of life would look like and thought it would make a fun side project. I'm trying to decide how to render the live/dead cells in 3D.
I'd like all the visuals to occur within an n * n * n cube, like a rubik's cube where all internal cells are also used. The only functionality I really need is the ability to change the colors of the "cells" after a certain time interval. Is there a framework or library that I could use to make the creation of the cube?
I created an implementation with Matplotlib using the "voxels" function but after about 150 boxes it gets too slow to even rotate, and seeing as it is going to be changing every hundredth of a second I dont anticipate mpl could handle it without some optimization that I'm as of yet unaware of. I've been trying to find more information about Python volume rendering techniques for this specific problem but i cant find the term for a "cube made out of cubes" so it has been difficult.
Thanks for any help.
The update rule for the game of life (in any dimension) is based on the value of the convolution of the board with a "counting" mask. (all ones in a little 3x3 (or 3x3x3 in your case) region. So, I would suggest using something like tensorflow (probably pytorch works fine too) and using tf.nn.conv3d to do that step fast. You probably need the GPU anyway to be able to rotate the thing quickly.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I'm currently trying to write a bot to play tetris on tetrisfriends.com to practice machine-learning, but I've become stuck. I'm trying to find a way to read the players score from the game but Tesseract doesn't recognize the font/numbers and I don't think I can retrain Tesseract to recognize the numbers either because it isn't a full font being used, just numbers.
The image that I'm trying to read the numbers from is this:
https://imgur.com/a/OVwV5
When I use Tesseract I can get it to recognize other words on the page, just not the numbers which is the part I need.
Does anyone have a way to do this, either by retraining Tesseract, another method, or any other way?
I'm not very familiar with Tesseract in particular, but it might not your best bet here. If the end goal was just to make a bot, you could probably pull the text directly from the app rather than worrying about OCR, but if you want to learn more about machine learning and you haven't done them already the MNIST and CIFAR-10 datasets are fantastic places to start.
Anyway! The image you're trying to test has very low contrast, and the font is heavily stylised. Looking at the website itself it looks like the characters are coloured yellow:
If you preprocessed your image so that yellow pixels are black and all others are white you would have a much cleaner source to work with e.g.:
If you want to push forward with Tesseract for this and the preprocessing isn't enough then you will probably have to retrain it for this font. You will need to prepare a corpus, process it similarly to how you expect your source data to look, and then use something like qt-box-editor to correct the data. This guide should be able to walk you through the basic steps of retraining.
Closed. This question needs details or clarity. It is not currently accepting answers.
Want to improve this question? Add details and clarify the problem by editing this post.
Closed 5 years ago.
Improve this question
I am trying to find out how to estimate position and orientation of an object using stereo camera images.
Assume a description of an object is given either by its edges and edge-relations, or points, or other features. The images are taken from above by a set of two cameras that have a fixed position relative to each other (like Microsoft Kinect gives you).
With Python's skimage toolkit I am able to recognise the similarites in the picture without telling if the searched object is in the images, but that is as far as I get.
What I want to do more is to segment the known object from the background and to be able to tell its position relatively to the cameras (e.g. by comparing its calculated position with the position of a known mark on the floor or something similar which I don't think will be too hard).
I know Python pretty well and have some experience in basic image processing. If this problem is already solved in OpenCV, I can work with that as well.
Thank you in advance for any help you give, either by naming keywords to improve my search, links, or by sharing your experience in this field!
To illustrate my problem: You have a bunch of same kind (shape+color) lego bricks laying in a chaotic manner, e.g. they are overlaying completely/partially or not at all and have an arbitrary orientation. The floor underneath is of the same color as the bricks. Cameras look straight down. Task is to find as many as bricks as possible and tell there location.
edit: added illustration
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 7 years ago.
Improve this question
I am doing a project where I am attempting to take out the green screen on a video on python but I do not know how to go about it.
Thank you!
well...I presume you have some kind of RGB image for each frame of video.
I.e an N by 3 array.
(You could use OpenCV to read each frame.)
So it is case of going through the image and locating all the green and replacing it with what you want.
E.g if the array is called arr then for each row, i, you would check whether arr[i] == [0,255,0].
But due to the nature of film, you aren't going to have a perfectly uniform 0,255,0 green. There will be shadows and other slight variations. Perhaps it wasn't even 0,255,0 to start out with.
So you are going to be looking at removing a range of colours. Now for each row we are searching for a range of colours and replacing them with your choice.
We now run the risk of identifying a colour for removal that we don't actually want removing....so how can we check for that...
We still probably won't get a perfect match around the edges (of the objects/people we want to keep in the image), so to make this less obvious, we might want to use a little bit of blur and so on and so forth.
Look at this video: https://www.youtube.com/watch?v=rIWoLCFvjME
Try to think about what logic code is required for each little step the user takes.
Also think about all the decision the user makes that are purely subjective. Obviously these would be nigh-on impossible to automate reliably. So now we are talking about some kind of interactive application that allows the user to select different actions based on their subjective choice.
And we quickly see why green screen is often removed manually, frame by frame using a powerful editing application like photoshop, after effects etc...
OpenCV (http://opencv-python-tutroals.readthedocs.org/en/latest/) will do a lot of the algorithms for you...there is almost enough there to build your interactive greenscreen removal software...
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 8 years ago.
Improve this question
In sliding window object detectors, is it possible to do object detection "intelligently"? For example, if a human is looking for a vehicle, they're not going to look into the sky for a car. But an object detector that uses a sliding window is going to slide the window across the entire image (including the sky) and run the object classifier on each window, resulting in a lot of wasted time. Are there are any techniques out there to make sure it only looks in reasonable places?
Edit
I understand we'll have to look through everything at least once, but I wouldn't want to run a heavy complicated classifier on each window. A pre-classification classifier of sorts, perhaps?
Have you considered looking at saliency detection algorithms? Saliency detection algorithms give you an indication of where in the image a human would most likely focus on. A good example would be a human in an open field. The sky would have low saliency while the human a high one.
Maybe put your image through a saliency detection algorithm first, then threshold and find regions of where to search instead of the entire image.
A great algorithm for this is by Stas Goferman: Context-Aware Saliency Detection - http://webee.technion.ac.il/~ayellet/Ps/10-Saliency.pdf.
There is also code here to get you started: https://sites.google.com/a/jyunfan.co.cc/site/opensource-1/contextsaliency
Unfortunately it is in MATLAB, and from your tag you want to look at Python. However, there are many similarities between numpy / scipy and MATLAB so hopefully that will help you if you want to transcribe any code.
Check it out!