jroriz Active Member Licensed User Longtime User Oct 19, 2022 #1 Could someone help me to write a program to recognize playing cards using opencv? The cards always appear in the same place and always with the same pattern. What can change is the window size, which the user can freely change, but always in the same proportion. Where the cards are is not my problem. I can with basic math know the size of the window and where the cards would be. Then I would crop the part of the screen where the cards are and apply opencv to the cropped image.
Could someone help me to write a program to recognize playing cards using opencv? The cards always appear in the same place and always with the same pattern. What can change is the window size, which the user can freely change, but always in the same proportion. Where the cards are is not my problem. I can with basic math know the size of the window and where the cards would be. Then I would crop the part of the screen where the cards are and apply opencv to the cropped image.
jroriz Active Member Licensed User Longtime User Oct 31, 2022 #21 The point is: OCR has become a problem due to the constant updates of the apps and also because the solution I developed (a HUD to help players make decisions) is for many different poker platforms. In two of them the cards are arranged at an angle of up to 45 degrees! That's why I would like to use opencv, which I believe could recognize the cards regardless of platform or resolution (as long as a minimum resolution is observed). Upvote 0
The point is: OCR has become a problem due to the constant updates of the apps and also because the solution I developed (a HUD to help players make decisions) is for many different poker platforms. In two of them the cards are arranged at an angle of up to 45 degrees! That's why I would like to use opencv, which I believe could recognize the cards regardless of platform or resolution (as long as a minimum resolution is observed).
E emexes Expert Licensed User Longtime User Oct 31, 2022 #22 jroriz said: In two of them the cards are arranged at an angle of up to 45 degrees! Click to expand... ? it's almost like they're actively trying to throw a spanner in your works Upvote 0
jroriz said: In two of them the cards are arranged at an angle of up to 45 degrees! Click to expand... ? it's almost like they're actively trying to throw a spanner in your works
jroriz Active Member Licensed User Longtime User Oct 31, 2022 #23 emexes said: ? it's almost like they're actively trying to throw a spanner in your works Click to expand... No, it's just a matter of design. See how different apps can be: https://www.pokerlistings.com/blog/the-most-addictive-useful-free-poker-apps-for-android-iphone I use emulators like ldplayer to run apps on PC. Upvote 0
emexes said: ? it's almost like they're actively trying to throw a spanner in your works Click to expand... No, it's just a matter of design. See how different apps can be: https://www.pokerlistings.com/blog/the-most-addictive-useful-free-poker-apps-for-android-iphone I use emulators like ldplayer to run apps on PC.
E emexes Expert Licensed User Longtime User Oct 31, 2022 #24 jroriz said: See how different apps can be: Click to expand... Ah, I thought you meant the one app kept changing their design subtly to thwart automatic screen readers. Upvote 0
jroriz said: See how different apps can be: Click to expand... Ah, I thought you meant the one app kept changing their design subtly to thwart automatic screen readers.
jroriz Active Member Licensed User Longtime User Nov 1, 2022 #25 Actually this happens too, but most of the time it's just a layout upgrade. The problem with using OCR is that if the layout changes even a few pixels to the left or right, it already interferes with the recognition of the letters. Upvote 0
Actually this happens too, but most of the time it's just a layout upgrade. The problem with using OCR is that if the layout changes even a few pixels to the left or right, it already interferes with the recognition of the letters.
E emexes Expert Licensed User Longtime User Nov 1, 2022 #26 jroriz said: if the layout changes even a few pixels to the left or right, it already interferes with the recognition of the letters. Click to expand... I suspect that moving by a fraction of a pixel is causing most of that problem. And then with subpixel rendering on top of that... I am impressed that OCR works as well as it mostly does. Upvote 0
jroriz said: if the layout changes even a few pixels to the left or right, it already interferes with the recognition of the letters. Click to expand... I suspect that moving by a fraction of a pixel is causing most of that problem. And then with subpixel rendering on top of that... I am impressed that OCR works as well as it mostly does.
jroriz Active Member Licensed User Longtime User Nov 1, 2022 #27 emexes said: I suspect that moving by a fraction of a pixel is causing most of that problem. And then with subpixel rendering on top of that... I am impressed that OCR works as well as it mostly does. Click to expand... When the user reduces the size of the app's screen, the recognition of the letters becomes very difficult, even "isolating" the letters of the playing cards. One feature that greatly improved recognition was repeating the image several times next to each other. For example: if the card is an A, I duplicate the image several times, say 5 times, which will generate AAAAA. Upvote 0
emexes said: I suspect that moving by a fraction of a pixel is causing most of that problem. And then with subpixel rendering on top of that... I am impressed that OCR works as well as it mostly does. Click to expand... When the user reduces the size of the app's screen, the recognition of the letters becomes very difficult, even "isolating" the letters of the playing cards. One feature that greatly improved recognition was repeating the image several times next to each other. For example: if the card is an A, I duplicate the image several times, say 5 times, which will generate AAAAA.
Magma Expert Licensed User Longtime User Nov 1, 2022 #28 Sorry, can I ask again the scope-target of recognizing? You have a counter of cards already played.. to not memorize them? Is it for personal use or something else to know? Upvote 0
Sorry, can I ask again the scope-target of recognizing? You have a counter of cards already played.. to not memorize them? Is it for personal use or something else to know?
kimstudio Active Member Licensed User Longtime User Nov 2, 2022 #29 kimstudio said: I suggest to just use template matching function from opencv to realize this: cv.matchTemplate() Click to expand... Template matching on target image blurred 3 times: Upvote 0
kimstudio said: I suggest to just use template matching function from opencv to realize this: cv.matchTemplate() Click to expand... Template matching on target image blurred 3 times:
E emexes Expert Licensed User Longtime User Nov 2, 2022 #30 jroriz said: The point is: OCR has become a problem due to the constant updates of the apps and also because the solution I developed (a HUD to help players make decisions) is for many different poker platforms. In two of them the cards are arranged at an angle of up to 45 degrees! Click to expand... Any angle is a bad angle. ? Upvote 0
jroriz said: The point is: OCR has become a problem due to the constant updates of the apps and also because the solution I developed (a HUD to help players make decisions) is for many different poker platforms. In two of them the cards are arranged at an angle of up to 45 degrees! Click to expand... Any angle is a bad angle. ?
Magma Expert Licensed User Longtime User Nov 2, 2022 #31 I think opencv with matchTemplate and "planar" objects detection... may be... help... to rotate template and then check... OpenCV: Detection of planar objects docs.opencv.org also why not also scaling width, height... 2-5 pixels... to make your life more difficult Upvote 0
I think opencv with matchTemplate and "planar" objects detection... may be... help... to rotate template and then check... OpenCV: Detection of planar objects docs.opencv.org also why not also scaling width, height... 2-5 pixels... to make your life more difficult
jroriz Active Member Licensed User Longtime User Nov 4, 2022 #32 Magma said: Sorry, can I ask again the scope-target of recognizing? You have a counter of cards already played.. to not memorize them? Is it for personal use or something else to know? Click to expand... A 'HUD' is a tool to assist in decision making. The HUD shows opponents stats (how many times he voluntarily entered a hand, if he is aggressive, passive, etc). In the case of playing cards detection, it is to know my probability of winning based on the cards I have and the cards that have already come out. See below an example of a HUD "in action": Upvote 0
Magma said: Sorry, can I ask again the scope-target of recognizing? You have a counter of cards already played.. to not memorize them? Is it for personal use or something else to know? Click to expand... A 'HUD' is a tool to assist in decision making. The HUD shows opponents stats (how many times he voluntarily entered a hand, if he is aggressive, passive, etc). In the case of playing cards detection, it is to know my probability of winning based on the cards I have and the cards that have already come out. See below an example of a HUD "in action":
jroriz Active Member Licensed User Longtime User Nov 4, 2022 #33 emexes said: Any angle is a bad angle. ? View attachment 135552 Click to expand... I thought opencv would be able to recognize playing cards at any angle and size... Upvote 0
emexes said: Any angle is a bad angle. ? View attachment 135552 Click to expand... I thought opencv would be able to recognize playing cards at any angle and size...
jroriz Active Member Licensed User Longtime User Nov 4, 2022 #34 kimstudio said: Template matching on target image blurred 3 times: View attachment 135537 Click to expand... Could you please share the code? How did you "train" opencv? Upvote 0
kimstudio said: Template matching on target image blurred 3 times: View attachment 135537 Click to expand... Could you please share the code? How did you "train" opencv?
Magma Expert Licensed User Longtime User Nov 4, 2022 #35 jroriz said: Could you please share the code? How did you "train" opencv? Click to expand... as i know is not actually training you must have all possible images (rotated images) or create them on the fly to check into the "original" image-screenshot with opencv.... see planar objects... ofcourse you can have some techniques (playing with brightness, grayscable, rgb, %-similarity)... tip: sometimes blurring, or scaling a picture to minimum size has better and faster results, but not all the time... you will need a lot time to find the right settings for your tool. Upvote 0
jroriz said: Could you please share the code? How did you "train" opencv? Click to expand... as i know is not actually training you must have all possible images (rotated images) or create them on the fly to check into the "original" image-screenshot with opencv.... see planar objects... ofcourse you can have some techniques (playing with brightness, grayscable, rgb, %-similarity)... tip: sometimes blurring, or scaling a picture to minimum size has better and faster results, but not all the time... you will need a lot time to find the right settings for your tool.
