What product to choose?

I need to choose what tools is suits better for my purpose. Have read a lot different staff on ABBYY's sites, and i'm lost.

What i need is to make some application that will process the PDF files and get from there only data from some particular areas. As far as i know it calls Zonal recognition. Some zones are just words/numbers, but one zone is the 'table' that has rows and columns.

We have different types of files, and have to use separate template for each one.

Also we have huge set of files that should to be scraped, so subscription with payment by document is very expensive. The best option is what we can host on our server with some fixed price.

Integration that can be used are: nodejs, python, CLI. OS to run - Linux (debian)

So my questions are:

1. What product is the best for me? 

2. Is there any examples of zonal recongition for some tools? I saw the cloud OCR has Zonal recognition, but page with API description is not so clean. So some hints/examples will be great.



1 comment

  • Avatar
    Helen Osetrova



    Please take a look at our Data Capture product line: ABBYY FlexiCapture and ABBYY FlexiCapture Engine. They both afford an opportunity for fields recognition and document classification.


    Here is how it performs:

    FlexiCapture Engine can process fixed forms and flexible documents within the FlexiCapture projects. To use this functionality, you should first create a project with the help of ABBYY FlexiCapture and then use it in ABBYY FlexiCapture Engine.

    The project is a single environment that unites collections of the documents and the settings required to process them. Such collections of the documents submitted for processing are called the document batches. The project structure (including the batches and the documents) is reproduced in the FlexiCapture Engine objects. The most critical part is a set of Document Definitions – fixed and flexible layouts – which are used for data extraction and which determine the quality of data obtained after processing.

    In order to process the documents, you add the images to a batch in the project. During recognition, the program selects the Document Definition appropriate for the document pages, applies it, and performs data recognition in the regions found in the document with the help of the selected Document Definition. The processed data are then transferred to external files.


    If you are interested in these products, please request the demo versions of ABBYY FlexiCapture and ABBYY FlexiCapture Engine on corresponding pages. The code samples are also included into the distribution kit. 


Please sign in to leave a comment.