The most comprehensive OCR SDK for software developers

Providing high flexibility for image input, ABBYY FineReader Engine can receive images from many sources.

 

Scanning via TWAIN or WIA interface is a common way to directly convert paper documents – however, photographing documents by smartphones or tablets is an increasingly popular way for document input, especially in companies with mobile workforce.

 

Already saved images, such as digital archives in TIFF or JPEG formats, can be easily imported. Even photos from industrial cameras as used within machine vision projects for test automation, can be imported and subsequently processed. For business areas requiring high security standards, files can be loaded directly from memory without saving them to the disk first.

 

In addition to document images such as scans, photos or screenshots, ABBYY FineReader Engine can receive and process documents available in Office formats, for example Word, Excel or PowerPoint as well as different types of PDF.

With its powerful document scanning options, ABBYY FineReader Engine enables flexible management of the scanning process and provides access to the individual scanning parameters, such as brightness, color settings, resolution, image size, duplex scanning, pause between pages setup and more.

Scanning API features:

• Extended access to scan settings, including access to scan source capabilities
• Filtration of scan sources by available user interfaces or scan API types (TWAIN, WIA)
• Ability to specify compression type of scanned images
• Asynchronous scanning - ability to start recognition of already scanned pages before scanning of all pages is finished

The OCR SDK supports the majority of image formats, including multi-page TIFF and JPEG 2000 (part1), and works with black-and-white, grayscale and color images. It opens digitally created PDF files by utilizing the Adobe® PDF Library and processes different types of PDF documents, even if they are not compliant the PDF standards.