INFORMys: A Flexible Invoice-Like Form-Reader System

نویسندگان

  • Francesca Cesarini
  • Marco Gori
  • Simone Marinai
  • Giovanni Soda
چکیده

In this paper, we describe a flexible form-reader system capable of extracting textual information from accounting documents, like invoices and bills of service companies. In this kind of document, the extraction of some information fields cannot take place without having detected the corresponding instruction fields, which are only constrained to range in given domains. We propose modeling the document’s layout by means of attributed relational graphs, which turn out to be very effective for form registration, as well as for performing a focussed search for instruction fields. This search is carried out by means of a hybrid model, where proper algorithms, based on morphological operations and connected components, are integrated with connectionist models. Experimental results are given in order to assess the actual performance of the system.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

BendFlip: Examining Input Techniques for Electronic Book Readers with Flexible Form Factors

We present recommendations for the design of flexible electronic book readers, based on an empirical evaluation of form factors and input techniques in a page navigation task. We compared capacitive touch, pressure, and bend sensors between rigid and flexible form factors using a prototype electronic book reader. Results suggest that the time required to perform bend techniques is comparable to...

متن کامل

Morphology by itself in planning the production of spoken words.

The authors report a study in Dutch that used an on-line preparation paradigm to test the issue of semantic dependency versus morphological autonomy in the production of polymorphemic words. Semantically transparent complex words (like input in English) and semantically opaque complex words (like invoice) showed clear evidence of morphological structure in word-form encoding, since both exhibit...

متن کامل

A Part based Modeling Approach for Invoice Parsing

Automated invoice processing and information extraction has attracted remarkable interest from business and academic circles. Invoice processing is a very critical and costly operation for participation banks because credit authorization process must be linked with the real trade activity via invoices. The classical invoice processing systems first assign the invoices to an invoice class but an...

متن کامل

Helping SMEs Automate like Corporations: A Constraint Satisfaction Problem for Automatic Invoice Field Extraction

Invoice feature extraction has been a topic of research for many years. Current methods are, however, mainly focused on the visual and positional layout of an invoice, essentially disregarding the information in the field contents. This paper regards this research topic as a constraint satisfaction problem. It therefore first gives a comprehensive view on what field variables are commonly prese...

متن کامل

Challenges for electronic invoicing systems: A quantitative study of Vietnamese SMEs

1.10.2013 Bachelor of International Business Author Hoang Ngo Group or year of entry GloBBA 2010 Title of thesis Challenges for electronic invoicing systems: A quantitative study of Vietnamese SMEs Number of report pages and attachment pages 64+8 Thesis advisor(s) Heli Kortesalmi, Mika Mustikainen, Jutta Heikkila Alongside the traditional paper invoice, there is another type of invoice that has...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • IEEE Trans. Pattern Anal. Mach. Intell.

دوره 20  شماره 

صفحات  -

تاریخ انتشار 1998