CardRecog Recognize Play Cards for Android

By Gerhard Roth
Free
User Rating

Download now

Key Details of CardRecog Recognize Play Cards

Recognizes playing cards using the camera. Works best with an autofocus camera.
Last updated on November 1, 2016
There have been 7 updates
Also available on
Virus scan status:
Clean (it's extremely likely that this software program is clean)

Developer's Description

By Gerhard Roth

Recognizes playing cards using the camera. Works best with an autofocus camera.

CardRecog is an app that recognizes playing cards from a standard deck. There are two modes; multiple card and single card. In multiple card mode you put a number of cards in front of the camera, in single card mode only a single card. You choose which mode you are in (multiple card is the default) in the settings. You touch the screen to start recognition, hold the camera still, put some cards in front, and wait. You stay in recognition mode until you touch the screen again to return to idle mode. Once recognition occurs the recognized cards are displayed and spoken and at this point no further cards will be recognized unless you restart the recognition. There are two ways to do this; the easiest is remove all cards from view for around 1/2 second, and then place the cards to be recognized in front of the camera. The second way is to touch the screen to stop recognition and go to idle, and touch it again to start recognition.When you start recognition the camera focuses (if it can auto focus), so if recognition is not working you should touch the screen to stop, and then touch again to restart recognition to be sure you have an in focus image.You can also tilt the cards slightly to see if that improves results. If recognition does not work for any card then try setting the video resolution to something higher than the default 640 by 480 resolution, or set the ISO (if it is in the settings) to the highest possible value, instead of the default automatic.For high end devices with auto focus (i.e. Nexus line) recognition works well even for a large number of cards. However, you always need an in focus image, and reasonably bright lighting. For lower end devices recognition will work well in single card mode, but fewer cards are recognized successfully at once in multiple card mode. But even for low end devices (including those with no auto focus) recognition works well in single card mode, which is the most reliable mode.In multiple card mode if the bottom of a card is seen that card is recognized twice; to stop this from happening just move all the cards down so that you only see the tops of the cards. In single card mode we look for the same card number and suit in both the top and bottom of the card. So both must be visible before the card is recognized in single card mode, but only one is required for recognition in multiple card mode. In single card mode if multiple cards are present recognition fails, you need exactly one. The current mode is shown in the action bar text.The purpose of this app is to showcase the technology for evaluation purposes. In the long run I plan to run it on Google glass (when I can get Glass in my country) and integrate it with different card games. For now, there is no integration with any card game, but in single card mode I do perform standard blackjack card counting (can force display of count in the settings) to show a simple practical application. All the card recognition systems that I know about (i.e. the Blackjack counting detection systems) look for the outline of the entire card. I believe that my method is unique since I do not require the outline of the cards, instead I only look at the card number and the associated suit. So as long as the suit and number are visible recognition will occur successfully; the rest of the card can be occluded. Skip to 1 minute, 23 seconds of the video below and you will see successful recognition of cards in the typical "fan" shape used in card games. No other system that I know of can perform this recognition. The app is real time in the sense that it is recognizing a number of times a second, but the results are grouped to achieve a consensus, which is why it takes one or two seconds for a recognition result. I believe this is the best card recognition system for something like Google glass where you are looking at the cards in someone's hands. I welcome any comments, but remember this is not a final product, it is a technology demo.Content rating: Everyone