问题
How to build the android native SDK for image to text recognition. (I have done well with some APIs from web services. But this time, I just want to make the app without any Internet Connection, no APIs, and no Web Services. Just an offline OCR app). So my question here is
- how to crop each and every word containing in the image?
- how to compare the cropped text with the alphabets and characters?
回答1:
I guess u can use Tesseract OCR Tool, an open source alternative by Google. How to integrate that in Android is simple via Tesseract Android Tools Have a look at the tess-two project on github, it's very easy to use and gives good OCR results
回答2:
You said you didn't want to use an API, however I suggest you use the recently released OCR API by Google: https://developers.google.com/vision/text-overview
Just add the following line to your dependecies:
compile 'com.google.android.gms:play-services-vision:9.2.0'
Note: Upon first use it will have to download some files from a google server for it to be able to work. Make sure to add this check .isOperational(). Afterwards you can use it without an internet connection.
回答3:
You can use ML Kit for Image to Text Recognition:
https://firebase.google.com/docs/ml-kit/android/recognize-text
来源：https://stackoverflow.com/questions/36453199/offline-image-to-text-recognition-ocr-in-android