Change search
ReferencesLink to record
Permanent link

Direct link
Automatic reading and interpretation of paper invoices: ADC invoice
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
2016 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Manually typing long numbers on paper invoices is tedious and timeconsuming work. The task of typing all the fields of an invoice into a text editor was given to two subjects working with bookkeeping, and the average time consumed was measured to be five minutes. The time and cost spent on manual typing will accumulate for companies that receive a lot of invoices. Swedbank along with other banks, have addressed this issue with a mobile application that reads and interprets the numbers on an invoice using the built in camera. This solution is directed to the public and the extracted information cannot be imported into bookkeeping software. A standalone software for digital reading and interpretation of scanned invoices is our solution for companies in regards to this issue.

There is already technology available that will interpret written text. These techniques were applied in our work, but the focus of this project was to implement algorithms for finding the location for a specific number and resolve what bookkeeping terms the number references e.g. OCR, IBAN numbers, etc. This is hampered by the missing of a general invoice layout.

52% of all the sought information was extracted correctly and almost 95% of the bookkeeping details that are changed most frequently on invoices from the same service providers were extracted correctly. The average time it takes for the application to extract the vital data is 30-40 seconds.

Abstract [sv]

Manuell inmatning av alla långa nummer på en pappersfaktura är ett tråkigt och tidskrävande arbete. Uppgiften att skriva in alla fält från en faktura till en ordbehandlare gavs till några personer som jobbar med bokföring. Tiden mättes till ett snitt på 5 minuter. Tiden det tar och den kostnad det medför kommer att ackumuleras för företag som får regelbundna fakturor från sina leverantörer. Swedbank, och andra banker, har adresserat problemet med en mobil applikation som kan läsa och tolka nummer på en faktura via mobilkameran. Den här lösningen riktar sig mot privatpersoner och den extraherade informationen skickas direkt till banken och kan inte importeras i ett bokföringsprogram. Ett fristående program för digital läsning och tolkning av inskannade fakturor är vår lösning till företagen för detta problem.

Det finns redan väldigt kraftfull teknologi för att tolka skriven text. Dessa tekniker användes i vårt arbete, men svårigheten i detta projekt var att implementera algoritmer för att lokalisera ett nummer och lista ut vilken bokförings referens det representerar, t.ex. OCR, IBAN etc. Detta försvåras av avsaknaden av ett generellt faktura format.

52% av den önskade information var korrekt extraherad och nästan 95% av bokförings-detaljerna som ändras mest mellan fakturor med samma avsändare extraherades korrekt. Tiden det tog var i genomsnitt för programmet att extrahera informationen var vid dessa försök 30-40 sekunder.

Place, publisher, year, edition, pages
2016. , 38 p.
Series
Independent Project in Computer and Information Engineering, 2016-014
National Category
Computer Systems Engineering and Technology
Identifiers
URN: urn:nbn:se:uu:diva-302830OAI: oai:DiVA.org:uu-302830DiVA: diva2:967971
External cooperation
Crowderia AB
Educational program
Master of Science Programme in Information Technology Engineering
Supervisors
Examiners
Available from: 2016-09-19 Created: 2016-09-10 Last updated: 2016-09-19Bibliographically approved

Open Access in DiVA

fulltext(1124 kB)2 downloads
File information
File name FULLTEXT01.pdfFile size 1124 kBChecksum SHA-512
b9323ed4b12ef7f5bc25d8ffff1d5e79d9102a5cf69a57bdebf9b1b661169cb8b86bd4f6c9aab9f91e53030a97beae2a62d1cd6a30c4abad24098b4d2589dd93
Type fulltextMimetype application/pdf

By organisation
Department of Information Technology
Computer SystemsEngineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 2 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 51 hits
ReferencesLink to record
Permanent link

Direct link