smartFIX: A Requirements-Driven System for Document Analysis and Understanding

Abstract

Abstract.Although the internet offers a wide-spread platform for information interchange, day-to-day work in large companies still means the processing of tens of thousands of printed documents every day. This paper presents the system smartFIX which is a document analysis and understanding system deve loped by the DFKI spin-off INSIDERS. It permits the processing of documents ranging from fixed format forms to unstructured letters of any format. Apart from the architecture, the main components and system characteristics, we also show some results when applying smartFIX to medical bills and prescriptions.

The Search for Genericity in Graphics Recognition Applications: Design Issues of the Qgar Software System

“…In particular, special operations to edit for both bitmap and vectorial images are supported, such as copy and paste of bitmap images, creation and modification of vectorization components, etc. The interface is implemented in C++ using the Qt framework 4 and is distributed under the QPL license. This makes it easy to be upgraded or customized by anyone interested in its features.…”

“…For instance, there is good know-how in building flexible and versatile OCR and page reader systems, taking into account segmentation, feature extraction, classification, and various linguistic post-processing steps [3]. Extending the concept to various business documents, Dengel et al have also developed a very mature system, capable of adaptation to different types of documents [4,5]. Other specific application domains have their mature systems, such as bank check processing software [6], table recognition [7], or forms processing [8].…”

Results of a Study on Invoice-Reading Systems in Germany

“…(cf. [1,2,5]) However, in ,56 it is sensible to simply consider the creditor as the classification. Then, as explained above, the creditor can be used to retrieve from an online ERP-connection the list of possible invoice line items.…”

“…Our consortium of four companies (their specific experiences are each in brackets) with experience in the ,56 field, interim2000 (documents analysis marketing and consulting), Pylon (document process consulting), Integra (market analysis), and DFKI (document analysis science, [1,2,3]), detected the emergence of a demand for invoice reading systems (,56) on the German market. Eleven companies supply systems for invoice reading, see Table 1.…”

Spotting handwritten words and REGEX using a two stage BLSTM-HMM architecture

“…Some REGEX spotting systems have been designed for electronical documents, using Natural Language Processing methods. 1,2 In this case, the REGEX spotting is rather straightforward as it consists in applying exact string matching methods on the ASCII text. When dealing with document images, a recognition step is needed in order to produce the ASCII transcription before processing the input data.…”