Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1810617,
author = {Ha, Hien Thi and Horák, Aleš},
address = {St. Petersburg, Russia},
booktitle = {SPECOM 2021: 23rd International Conference on Speech and Computer},
doi = {http://dx.doi.org/10.1007/978-3-030-87802-3_23},
editor = {Karpov A., Potapova R.},
keywords = {OCR; Invoice; Block type classification; Seller; Buyer; Delivery address},
howpublished = {elektronická verze "online"},
language = {eng},
location = {St. Petersburg, Russia},
isbn = {978-3-030-87801-6},
pages = {250-261},
publisher = {Springer},
title = {Who is Selling to Whom – Feature Evaluation for Multi-block Classification in Invoice Information Extraction},
url = {https://link.springer.com/chapter/10.1007/978-3-030-87802-3_23},
year = {2021}
}
TY - JOUR
ID - 1810617
AU - Ha, Hien Thi - Horák, Aleš
PY - 2021
TI - Who is Selling to Whom – Feature Evaluation for Multi-block Classification in Invoice Information Extraction
PB - Springer
CY - St. Petersburg, Russia
SN - 9783030878016
KW - OCR
KW - Invoice
KW - Block type classification
KW - Seller
KW - Buyer
KW - Delivery address
UR - https://link.springer.com/chapter/10.1007/978-3-030-87802-3_23
N2 - The invoice information extraction task aims at unifying the automatized processing of invoices in structured forms and in the form of a scanned image. Recognizing the pieces of information where a specific value is identified with a keyword (such as the invoice date) is a relatively well-managed task. On the other hand, identification of multi-block information on the invoice, such as distinguishing the seller, buyer, and the delivery address, is much more challenging due to versatile invoice layouts. In this work, we present a new technique of feature extraction and classification to recognize the seller, buyer, and delivery address text blocks in scanned invoices based on a combination of complex layout and annotated text features. The method does not only consider the block positional features but also the relation between blocks and block contents at a higher level. The technique is implemented as a module of the OCRMiner system. We offer its detailed evaluation and error analysis with a dataset of more than five hundred Czech invoices reaching the overall macro average F1-score of 94%.
ER -
HA, Hien Thi and Aleš HORÁK. Who is Selling to Whom – Feature Evaluation for Multi-block Classification in Invoice Information Extraction. Online. In Karpov A., Potapova R. \textit{SPECOM 2021: 23rd International Conference on Speech and Computer}. St. Petersburg, Russia: Springer, 2021, p.~250-261. ISBN~978-3-030-87801-6. Available from: https://dx.doi.org/10.1007/978-3-030-87802-3\_{}23.
|
