5

Right now I'm making an OCR app using Android OCR rmtheis(https://github.com/rmtheis/android-ocr) as a scaffold.

However, I'm far from satisfied.

My main issues:

  1. It returns only a fraction of the containing characters correct when scanning ultra-tiny texts with a few different fonts with irrelavant clutter such as images and barcodes included (from a product manual in this case).

  2. The autofocus is looping in a way that if you press the camerabutton when the image is as it's sharpest shape, you might be 0.02 seconds too late and scan the blurry image. So I prefer an autocapture when text is included in the selected view.

Is there any high quality OCR solutions for Android that can capture tricky and small text and getting it all correct almost every time?

Just to clarifie: I use tesseract(tess-two) already through the android-ocr project

On another note: It needs to return close to 100% correct results almost everytime. No language support required, Im only going to use it to catch codes such as 842EAB842EAB842EAB84?2EAB842EAB842EAB with irrelevant english text besides it. Therefore, I need no language support at all.

Edit: This seems to be what I'm looking for: http://www.abbyy.com/mobileocr/features/

Is there any solution with even higher quality output than Abbyy?

Anders Persson
  • 118
  • 3
  • 12
  • tesseract is a well established library - https://code.google.com/p/tesseract-android-tools/ – Ben Pearson Feb 04 '14 at 12:38
  • Are you sure it's really suitable for really high-quality needs? It gets several characters wrong when scanning tiny texts with irrelevant stuff. – Anders Persson Feb 04 '14 at 13:30
  • What have you tried - there is good documentation on improving the quality of scanning: https://code.google.com/p/tesseract-ocr/wiki/ImproveQuality – Ben Pearson Feb 04 '14 at 13:59
  • Thanks, but I want the OCR-software(or OCR + text-rotation-software) to address issues such as rotation of text in place. And I don't mean 90/180/270 as gautam. I guess it should be quite standard for Android apps to build in such feature so I hope there's an all in one packages to actually generate text from a very bad image in an effective matter. – Anders Persson Feb 04 '14 at 19:38
  • If you need even higher accuracy than has ABBYY Mobile OCR Engine you should try Cloud OCR SDK (ocrsdk.com). It uses the same core technology as ABBYY FineReader Engine – the most powerful OCR SDK by ABBYY. You can download here several samples see the accuracy: http://cloud.ocrsdk.com/Demo – Vitalik Kudryavtsev May 23 '14 at 19:40
  • Hi,I am using the same project and need to get the small text from the image.I am stuck here.The image may contain tables, spaces or image may contain bills like bank generated slips.I need to get the small text from bills.Please Help me ASAP.Thanks in Advance. – Naveen Aug 03 '16 at 06:53

2 Answers2

3

I've also been researching for high quality and free OCR solutions for Android, and finally I've chosen tess-two fork in one of my projects because other options had more disadvantages than advantages. As @realkarim says, it's not 100% accurate but the results are optimal.

Link for an OCR example using tess-two

Try it and comment us your experience ;)

gonver
  • 349
  • 1
  • 12
2

Well, a year ago I was planning to create an Android application in which I needed an OCR, first of all and I'm sorry to say that but you won't find a free "high quality OCR solutions for Android" :/ I used tess-two which is the best free OCR available for android but still it wasn't 100% accurate, probably if I had more time I could add some image processing to enhance the output.

link for the OCR: https://github.com/rmtheis/tess-two

an example of a running application using it: http://www.youtube.com/watch?v=Ho5DyK1hKdw

my application: http://www.youtube.com/watch?v=2PRQo7EWYd8

try it, and add some image processing to the image before using the OCR if you can :)

realkarim
  • 61
  • 1
  • 6
  • So what's your experience? Which paid solution do you recommend? – Anders Persson Feb 04 '14 at 13:31
  • I don't know any paid solution. however, the guy who created the first example I mentioned published his code -> https://github.com/GautamGupta/Simple-Android-OCR you can check it to know how to reach the maximum benefit of this OCR. he did a great job btw! – realkarim Feb 04 '14 at 13:52
  • Thanks! But try to rotate the phone 15 degrees when taking the picture. It wont pick the correct text then. – Anders Persson Feb 04 '14 at 19:47
  • Tesseract does not give great results, may be a lot of training can improve. – sudhanshu Aug 04 '15 at 13:24
  • Hi, I need to scan small text(Textsize nearly 8 to 10sp) from the hard copy(hard copy like current bills,etc...). I am using this github.com/rmtheis/android-ocr Project. How to scan smaller text ?I am struck here.Please help me ASAP.Thanks in Advance. – Naveen Aug 08 '16 at 08:18