Table of Contents
Mobile OCR Engine
- Development for Mobile Platforms
Desktop and server OCR have been established for quite some time. ABBYY Mobile OCR Engine, allows developers to integrate text recognition on mobile devices. The SDK has been designed especially for the mobile platform and enables the development for a large spectrum of applications.
- Mobile applications that have ABBYY OCR inside are able to transform digital images of
- documents
- notes
- newspaper clippings
- business cards
- timetables
- menus and other text taken with a built-in camera
- Mobile Developers can “pimp” their existing mobile apps and use the OCRed data within their own applications. So OCR
- reduces manual text/data input by the user
- generates a new usability of the app
- opens a new way of dealing with information
- At the end the application more value for users and developers can charge more for it ;o)
- ABBYY first premiered the small code-sized version (V1.0) of its toolkit in 1999 when the technology was integrated into the C-Pen, a small hand-held pen scanner. OCR implementation in the C-Pen required less than 2 MB of disk space and was combined with the ABBYY Lingvo Russian-English dictionary.
Processing Overview
Binarisation is always executed before the character recognition
- Original
- Binary - Black/White Result
Requirements & Recommendations
- To enable the OCR SDK to deliver usable results, the device should have a auto focus lens with more than 3 mega pixel
(as usual: more = better) - These devices normally have CPUs with more than 500 MHz.
(as usual: faster = better) - Memory:
Exact memory requirements vary depending on the operating system and specific recognition tasks (e.g. multilingual recognition requires more memory).- OCR of Latin and Cyrillic characters: 8 MB ROM, 10 MB RAM;
- Chinese and Japanese OCR: 14 MB ROM, 22 MB RAM;
- Korean OCR: 18 MB ROM, 28 MB RAM.
Documents
Technical Specifications
Different versions of Mobile OCR Engine
Mobile OCR technology is already available for several years and the importance for light OCR technology is increasing with the growing market of smart phones.
FineReader Engine for the most operating systems is already available for 2 technology cycles :