8,634 Hits in 5.6 sec

A Case-Based Reasoning Approach for Invoice Structure Extraction

H. Hamza, Y. Belaid, A. Belaid
2007 Proceedings of the International Conference on Document Analysis and Recognition  
This paper shows the use of case-based reasoning (CBR) for invoice structure extraction and analysis.  ...  Applied on 950 invoices, CBR-DIA reaches a recognition rate of 85.29% for documents of known classes and 76.33% for documents of unknown classes.  ...  Conclusion and future works A CBR approach for invoice document analysis and interpretation was proposed in this paper.  ... 
doi:10.1109/icdar.2007.4378726 dblp:conf/icdar/HamzaBB07 fatcat:b7f3r7hj6bau5odvreh7odteni

Case-Based Reasoning for Invoice Analysis and Recognition [chapter]

Hatem Hamza, Yolande Belaïd, Abdel Belaïd
Lecture Notes in Computer Science  
This paper introduces the approach CBRDIA (Case Based Reasoning for Document Invoice Analysis) which uses the principles of case-based reasoning to analyze, recognize and interpret invoices.  ...  Applied on 923 invoices, CBRDIA reaches a recognition rate of 85,22% for documents of known classes and 74,90% for documents of unknown classes.  ...  Another type of related works concerns systems using multiple CBR reasoners. In CBRDIA, we will use 2 CBR reasoners (one for invoices of known class, and another for invoices of unknown class).  ... 
doi:10.1007/978-3-540-74141-1_28 fatcat:zulvjeca45eqja7s6vtlh4tpfi

Seizing the Treasure: Transferring Knowledge in Invoice Analysis

Frederick Schulz, Markus Ebbecke, Michael Gillmann, Benjamin Adrian, Stefan Agne, Andreas Dengel
2009 2009 10th International Conference on Document Analysis and Recognition  
This paper deals with the transfer of knowledge on invoice document layout and extraction strategies.  ...  This knowledge has been automatically generated by self-teaching mechanisms of the invoice analysis software smartFIX over several years of operation.  ...  no need for a case base update mechanism.  ... 
doi:10.1109/icdar.2009.47 dblp:conf/icdar/SchulzEGAAD09 fatcat:2zhkurqhe5ckzkvpzvqxoyjsda

Information extraction from scanned invoice images using text analysis and layout features

H.T. Ha, A. Horák
2021 Signal processing. Image communication  
Using an open source OCR, the system is able to recover the invoice data in 90% for English and in 88% for the Czech set.  ...  In this paper, we introduce the OCRMiner system for information extraction from scanned document images which is based on text analysis techniques in combination with layout features to extract indexing  ...  Acknowledgements This work has been partly supported by the Ministry of Education of CR within the LINDAT/ CLARIAH-CZ research infrastructure LM2018101 and by Konica Minolta Business Solution Czech within  ... 
doi:10.1016/j.image.2021.116601 fatcat:ri3amhwsije7bmm5jagudnvzmm

Administrative Document Analysis and Structure [chapter]

Abdel Belaïd, Vincent Poulain D'Andecy, Hatem Hamza, Yolande Belaïd
2011 Studies in Computational Intelligence  
After the presentation of the context related to the administrative document flow and its requirements in a real time processing, we present a case based reasonning for invoice processing.  ...  This chapter reports our knowledge about the analysis and recognition of scanned administrative documents.  ...  We proposed in [38] a case-based reasoning system to model and train the knowledge for the recognition of administrative documents corresponding to different kind of invoices.  ... 
doi:10.1007/978-3-642-22913-8_3 fatcat:noiu4hv4c5fpjhiaifybamuira

Recognition of Invoices from Scanned Documents

Hien Thi Ha
2017 Recent Advances in Slavonic Natural Languages Processing  
This can be applied to document management systems, document analysis systems, pre-processing of information extraction systems. We also present our experiments on Czech and English invoice data set.  ...  In this paper, we describe the work of recognition the first page of an invoice from a set of scanned business documents.  ...  Acknowledgements This work has been partly supported by Konica Minolta Business Solution Czech within the OCR Miner project and by the Masaryk University project MUNI/33/55939/2017.  ... 
dblp:conf/raslan/Ha17 fatcat:dds5jq2orvddtcihpxbbwl2wli

Graph-Based Keyword Spotting in Historical Documents Using Context-Aware Hausdorff Edit Distance

Michael Stauffer, Andreas Fischer, Kaspar Riesen
2018 2018 13th IAPR International Workshop on Document Analysis Systems (DAS)  
ACKNOWLEDGMENT The authors would like to thank the Siemens Postal, Parcel & Airport Logistics GmbH for funding this work.  ...  For this reason, semiassisted approaches based on handwriting recognition 1 [6] and keyword spotting [8] have been investigated.  ...  Regarding the speed improvement, Odate and Goto developed a candidate reduction method based on a tree-based dictionary and the Linear Discriminant Analysis (LDA) for HCCR.  ... 
doi:10.1109/das.2018.31 dblp:conf/das/Stauffer0R18 fatcat:2r2cjpiitfcs5knjtqbfvcuwsi

Automatic Generation of a Custom Corpora for Invoice Analysis and Recognition

Jerome Blanchard, Yolande Belaid, Abdel Belaid
2019 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW)  
Then, to show the interest of the generator, we proposed a system of invoice recognition based on graph convolutional neural network.  ...  The experiments took place in excellent conditions since we had all the possibilities to vary the classes, the samples in the classes, and their parameters.  ...  Fixed based layout Fixed based layout are a simple static based combination of existing elements to produce a "clone" of a real invoice and to use it for the generation of many invoices with various data  ... 
doi:10.1109/icdarw.2019.60121 dblp:conf/icdar/BlanchardBB19 fatcat:r3iszqerlnbxrgajhiytydrfh4

Context-based Information Classification on Hungarian Invoices

Gábor Szegedi, Diána Bajdikné Veres, Imre Lendák, Tomás Horváth
2020 Conference on Theory and Practice of Information Technologies  
The template-less design is important as invoices can have many different structure based on the issuer.  ...  First we feed the invoice image to a commercially available Optical Character Recognition (OCR) engine which returns the extracted texts with their bounding boxes.  ...  Related Work The main approaches to invoice recognition are Template based, Graph Convolutional Neural Network (CNN) based and direction based.  ... 
dblp:conf/itat/SzegediVLH20 fatcat:j3vny5u2x5c5vdwvzlbyl74eq4

Using Hidden Markov Models for the accurate linguistic analysis of process model activity labels

Henrik Leopold, Han van der Aa, Jelmer Offenberg, Hajo A. Reijers
2019 Information Systems  
Link to publication General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of  ...  accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the  ...  The reason for these erroneous classifications can be mainly related to cases of zero-derivation ambiguity. As examples, consider the labels ''Contact maintenance'' and ''Order checkout''.  ... 
doi:10.1016/ fatcat:nrpaxeqmind2pawwcq7ykv7nf4

Detecting Structured Image Region Using Local Features and Clustering Analysis

Huei-Yung Lin, Chin-Yu Hsu, Yung-Yang Chiang
2013 IAPR International Workshop on Machine Vision Applications  
Different from the existing techniques, our approach is able to deal with more influential factors in the images and suitable for many application scenarios.  ...  The structured regions in an image usually contain important clues for information understanding. Proper extraction of those regions is often a key to success for a computer vision system.  ...  The experimental results on the text detection and recognition of invoice, banknote and license plate have demonstrated the effectiveness of the proposed technique.  ... 
dblp:conf/mva/LinHC13 fatcat:oqigy3u33fap7f3mji4qst4yua

Analysis of GNSS integrity requirements for road user charging applications

Daniel Salos, Christophe Macabiau, Anais Martineau, Bernard Bonhoure, Damien Kubrak
2010 2010 5th ESA Workshop on Satellite Navigation Technologies and European Workshop on GNSS Signals and Signal Processing (NAVITEC)  
This paper analyzes the required parameters to develop RAIM algorithms for road tolling applications in urban and rural environments.  ...  GNSS-based Road User Charging (RUC) systems are particularly interesting because of their flexibility and reduced roadside infrastructure.  ...  requirements (x%, X%) in the worst case is: ( ) ⎡ ⎤1 100 error GO 100 1 case worst , , − ⎟ ⎠ ⎞ ⎜ ⎝ ⎛ − = x X x X P (4) Worst case values of P GO error are collected in TABLE 1 for different invoice  ... 
doi:10.1109/navitec.2010.5708007 fatcat:o25glfpkwnbbzigxjdugj2sype

Automated detection & identification of textual areas in dematerialization process

Mohammed Moujabbir, Mohammed Ramdani
2013 Applied Mathematical Sciences  
We focus on recognition the entire element of textual sectors -items contained in area text-.  ...  Documents Management System (DMS) are systems that read information depending on document's categories and suggest item.  ...  the -1/number of cases in analysis table-value.  ... 
doi:10.12988/ams.2013.36334 fatcat:7vsnl5u3vfecrhzwymnekphn6q

Matching Cost Against Revenue at Royalty Expenses

Muhammad Rifky Santoso
2021 The Indonesian Accounting Review  
This paper finds that a net sales-based royalty fee scheme can be estimated at the end of the year and deducted from gross income without waiting for a certainty on the amount of royalty expense on invoices  ...  By using a case in a tax court in Indonesia, there is a taxpayer who does not meet the matching cost against revenue principle when recording royalty expenses.  ...  This paper analyzed a selected tax court case using related kinds of literature. The analysis was carried out by desk-based.  ... 
doi:10.14414/tiar.v11i2.2558 fatcat:irfxnc4zcvclfmpygfq7f37d4u

Information Extraction from Invoices

Ahmed Hamdi, Elodie Carel, Aurélie Joseph, Mickael Coustaty, Antoine Doucet
2021 Zenodo  
Invoices are semi-structured documents in which data can be located based on the context.  ...  The present paper is focused on information extraction from key fields of invoices using two different methods based on sequence labeling.  ...  Our two approaches based on named entity recognition and document analysis are detailed in Section 4.  ... 
doi:10.5281/zenodo.5562411 fatcat:lzxcx3l6rna6lbi4vfxmxxszoi
« Previous Showing results 1 — 15 out of 8,634 results