hh.se
Publications
Please wait ...
Simple search
Advanced search -
Research publications
Advanced search -
Student theses
Statistics
English
Svenska
Norsk
Jump to content
Change search
Search
Search
Only documents with full text in DiVA
Cite
Export
BibTex
CSL-JSON
CSV 1
CSV 2
CSV 3
CSV 4
CSV 5
CSV all metadata
CSV all metadata version 2
RIS
Mods
MARC-XML
ETDMS
Link to record
Permanent link
https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-8817
Direct link
http://hh.diva-portal.org/smash/record.jsf?pid=diva2:363906
Cite
Citation style
apa
ieee
modern-language-association-8th-edition
vancouver
Other style
apa
ieee
modern-language-association-8th-edition
vancouver
Other style
More styles
Language
de-DE
en-GB
en-US
fi-FI
nn-NO
nn-NB
sv-SE
Other locale
de-DE
en-GB
en-US
fi-FI
nn-NO
nn-NB
sv-SE
Other locale
More languages
Output format
html
text
asciidoc
rtf
html
text
asciidoc
rtf
Create
Close
Kategorisering av fakturor
Pettersson, Håkan
Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
Szabo, Robert
Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
2000 (Swedish)
Independent thesis Basic level (degree of Bachelor)
Student thesis
Abstract [sv]
An invoice classification system designed for an industrial application is presented. Invoices are identified by matching logotypes or interpreting bank account numbers using OCR. Prior to identification it is necessary to reduce the number of possible invoice classes as they may amount to 50 000. Methods introduced in this report benefit from the fact that information unique to the supplier is primarily located to the upper part - called the header - of an invoice. In these parts a number of features are measured and these features span a multidimensional space. The distances from a given invoice to all possible classes are calculated and sorted. Very good results are achieved when a grid is applied to the header and for each cell the number of dots relative to the total number in the header is calculated. Sorting by Manhattan distance in this multidimensional space yields high numbers of first hits.
Place, publisher, year, edition, pages
2000.
Keywords [sv]
Invoice Classification, Pattern Recognition, Feature Extraction
Identifiers
URN:
urn:nbn:se:hh:diva-8817
Local ID: U2921
OAI: oai:DiVA.org:hh-8817
DiVA, id:
diva2:363906
Uppsok
Technology
Note
Denna uppsats kan beställas från arkivet / This paper can be ordered from the archive. Kontakta / Contact: arkivet@hh.se
Available from:
2010-11-09
Created:
2010-11-09
Bibliographically approved
Open Access in DiVA
No full text in DiVA
By organisation
School of Information Science, Computer and Electrical Engineering (IDE)
Search outside of DiVA
Google
Google Scholar
urn-nbn
Altmetric score
urn-nbn
Total: 72 hits
Cite
Export
BibTex
CSL-JSON
CSV 1
CSV 2
CSV 3
CSV 4
CSV 5
CSV all metadata
CSV all metadata version 2
RIS
Mods
MARC-XML
ETDMS
Link to record
Permanent link
https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-8817
Direct link
http://hh.diva-portal.org/smash/record.jsf?pid=diva2:363906
Cite
Citation style
apa
ieee
modern-language-association-8th-edition
vancouver
Other style
apa
ieee
modern-language-association-8th-edition
vancouver
Other style
More styles
Language
de-DE
en-GB
en-US
fi-FI
nn-NO
nn-NB
sv-SE
Other locale
de-DE
en-GB
en-US
fi-FI
nn-NO
nn-NB
sv-SE
Other locale
More languages
Output format
html
text
asciidoc
rtf
html
text
asciidoc
rtf
Create
Close
v. 2.44.0
|
WCAG
|
Halmstad University Library
|
Info for students
|
Info for researchers
|
Log in
DiVA
Logotyp