I am trying to find a solution for this AR app as the topic tells.
I want my app to recognize a hand-written number by the user.
The app will tell the user to write down for example number 24 on a paper and move the camera over the written number to see the 3d object.
This might be used for saving a Birthday, a wedding date .. etc
For accuracy, the app instructions will show the user a preview to tell please write the number 24 similar to this..
Although each hand writing will differ, but at least we do not get curly "2"-s or "4" with an open edge ..etc
So here we need AR to recognize the number, or be able to read the number according to approximation.
And the first question is: Is such a behavior doable or anyone familiar with a similar concept?
After searching similar apps, I found "Ink Hunter" apps for tatoo preview-s, although these apps use symbols not number, but we can think of a number as a symbol as well.
Also as this video: https://www.youtube.com/watch?v=9rXJcIE2Fcs shows, each user draws the symbol in a different way and still they get it working.
I am using Unity3d and Vuforia.
Vuforia offers free samples(unity3d packages) on the website, and there is one named "Text Recognition" , and here's the tutorial link: https://www.youtube.com/watch?v=W3MK6nC5FWE
But unfortunately couldn't make it work.
If someone has developed such a functionality using these sample projects from vuforia or have any ulternative method please I need you help :)
thanks in advance moghes
Here's a tutorial our team created on text recognition using the Hololens and Vuforia with Unity: https://www.youtube.com/watch?v=WdMeHgD4fMY. In the first portion of the video, we show how to get text recognition working with just Vuforia and Unity - no Hololens required. For your application, just change the text to numbers.
I believe the biggest challenge you will have is the "hand-written" component. From our research, Vuforia prefers computer-generated, predefined font types.
Related
Im trying to create a AR Game in Unity for educational project.
I want to create something like pokemon go: when the camera open the object will be fixed somewhere on the real world and you will have to search for it with the camera.
My problem is that ARCore and vuforia groundDetection (I dont want to use targets) are only limited for few types of phone and i tried to use kudan sdk but it didnt work.
Any one can give me a tool or a tutorial on how to do this? I just need ideas or someone to tell me where to start?
Thanks in advance.
The reason why plane detection is limited to only some phones at this time is partially because older/less powerful phones cannot handle the required computing power.
If you want to make an app that has the largest reach, Vuforia is probably the way to go. Personally, I am not a fan of Vuforia, and I would suggest you use ARCore (and/or ARKit for iOS).
Since this is an educational tool and not a game, are you sure Unity is the way to go? I am sure you may be able to do it in Unity, but choosing the right platform for a project is important - just keep that in mind. You could make a native app instead.
If you want to work with ARCore and Unity (which is a great choice in general), here is the first in a series of tutorials that can get you started as a total beginner.
Let me know if you have other questions :)
You can use GPS data from phone to display object when the user arrived specific place you can show the object. You can search GPS based Augmented Reality on google. You can check this video : https://www.youtube.com/watch?v=X6djed8e4n0
Me and a friend are trying to develop an app with a very unique and strange concept. I have a rubiks cube, where all the stickers have been replaced with QR Codes,
So that to the naked eye, they are impossible to distinguish from each other, but through a QR-Code reader (and a fair bit of patience) you can scan one and one sticker to reveal which color it in fact is, and use this system to ultimately solve the rubiks cube. The idea was widely received in the cubing community, and I am now looking to expand on that idea by making an app that recognizes each sticker, tracks them using a tracking plugin, and virtually colors in that sticker, so that through the lens of my smartphone, the stickers have colors. I have so far made a simple version of the app, using the Vuforia tracking plugin, and it's produced really promising results Screenshot from said app
My problem though, is that Vuforia only allows 2-3 stickers to be tracked and painted at a time, and while I've had it read 6 stickers before, that requiered me to hold the cube very still. I am developing a brand new set of stickers that isn't QR Codes, but rather random patterns that hopefully will be easier for the app to recognize, but what I really need is a tracking plugin that allows more stickers to be tracked at once. Vuforia is, to my understanding, the best free tracking plugin out there, but are there any other tracking plugins that can produce the results I'm seeking? Optimally, I would like to track 27 stickers at once, as that's the maximum amount of stickers visible on a rubiks cube at a time. but if that's too much, 9 stickers, which is the amount of stickers for each side, would do just fine too. Can anyone with more knowledge to tracking and extended tracking help me? I didn't make this app, only the stickers, cube and concept, so I don't know how to use the plugins. Would it be possible to use several plugins at once? I am willing to pay for the license for a better plugin if that's what it takes. If there are any better ways to approach my idea, I am also very open to hear them. Thank you very much for your time
I am working on an app that requires the use of a camera to scan in text. Basically without getting too detailed, I need to point the camera at something (for my purposes here I will say a license plate) and i need to point the camera at the plate, and have it somehow save the digits into a string within the app. i guess its similar to Word Lens or red laser where it doesnt actually take a picture, it just scans the view and returns information. i have not been able to find much about this so any help on how to write this kind of code would be greatly appreciated!!
This is not barcode scanning. This is called OCR (optical character recognition), and there are some free and opensource libraries available that do this.
For example, Tesseract is a complete OCR engine written in C++ (it has a C++ interface, so it can be easily used from within an iOS app).
The other solution is gocr, the GNU Optical Character Recognizer. This is supposed to be a standalone program (a command line tool), but I've had success extracting its essential parts into a library (and I used it in an iOS project of mine as well).
OpenCV is a complete computer vision library. You can implement OCR using it - just google for the adequate documentation and tutorials.
I want to implement an speech recognition feature in my iPhone app by research i came to know about OpenEars library and i downloaded that and got a sample project along with it i got a sample project,when i run it and if i say "hello" it is returning as "you said LEFT",i tried for many word combinations but i'm getting only Left,Right,Down,Forward & etc certain set of responses. Is this a bug in openears? if so is there any way to correct this?
Any help is appreciated in advance.Thank you.
Take a look at Using OpenEars In Your App
There's a corpus.txt file in your example which allows it to recognize only:
GO
FORWARD
BACKWARD
LEFT
RIGHT
START
STOP
TURN
You can add other words or even phrases though.
I wanted to write an Android and/or an iPhone app that entails taking a picture of something (right now, I just want to limit to text) after which the app parses the text to make use of it. For example, perhaps taking picture of a sentence (or may be just fragments) will be then parsed by the app to bring up more information about the book. Title, author, ISBN etc. And even may be information about other books that are similar in content to this book.
Is this possible to do something like this? Is there an API that exists already that parses the content of an image? How is an image stored in Android and iPhone? Is it possible to implement the app in one platform and not the other?
I'd appreciate any input or advice that you guys have to offer. Thank you!
You're looking for this, possibly.
It's called OCR, or Optical Character Recognition.
Also check out ZXing a great library for decoding one- and two-dimensional barcodes. There are both iPhone and Android versions.