I am trying to develop an Android application that uses OCR. The application should be able to scan business cards and other documents in order to pull content.
Is it possible to implement this using Google Docs Api? How to do it?
The Google Docs API list allows you to download PDF files or images and automatically run OCR to extract their text.
You can use Tesseract . It is a powerful library, and it has a java Tess4j shell.
You can use the Google Cloud Vision API . Its free for 1-1000 units per month. you can check the price here
you may find OpenCV useful. This is a powerful native wrapper library for Android.
Source: https://habr.com/ru/post/916429/More articles:JasperReports: how to format numeric data with Excel exporter - jasper-reportsGroovy *. Operators - groovyTelephone: Scroll to the top of the status bar - iosGet parent instance of class - c #Avoid wrapping object type name from JSON I / O (CXF web service) - jsonjava.nio Selectors and SocketChannel to continue - javaAndroid - Backstack when replacing a fragment in ViewPager - androidUnresponsive script - can this be avoided? - jqueryC ++ The difference between constant positioning - c ++Batch file to start, run,% TEMP% and delete all - batch-fileAll Articles