One-Shot Template Matching for Automatic Document Data Capture

Dhakal, Pranjal; Munikar, Manish; Dahal, Bikram

doi:10.1109/aitb48515.2019.8947440

Cited by 10 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ensure a high variance of document layouts in the dataset, unlabeled documents were clustered into layouts 5 . Only a limited number of documents per layout were selected for annotation.…”

Section: Dataset Characteristicsmentioning

confidence: 99%

“…Information extraction approaches must handle varying layouts, semantic fields and multiple input modalities at the intersection of computer vision, natural language processing and information retrieval. While there has been progress on the task [4,7,14,15,18,19,25,34], there is no publicly available large-scale benchmark to train and compare these approaches, an issue that has been noted by several authors [5,16,24,26,29]. Existing approaches are trained on privately collected datasets, hindering their reproducibility, fair comparisons and tracking field progression [11,23,24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DocILE 2023 Teaser: Document Information Localization and Extraction

Šimsa¹,

Müller²,

Skalický³

et al. 2023

Preprint

View full text Add to dashboard Cite

The lack of data for information extraction (IE) from semistructured business documents is a real problem for the IE community. Publications relying on large-scale datasets use only proprietary, unpublished data due to the sensitive nature of such documents. Publicly available datasets are mostly small and domain-specific. The absence of a large-scale public dataset or benchmark hinders the reproducibility and cross-evaluation of published methods. The DocILE 2023 competition, hosted as a lab at the CLEF 2023 conference and as an ICDAR 2023 competition, will run the first major benchmark for the tasks of Key Information Localization and Extraction (KILE) and Line Item Recognition (LIR) from business documents. With thousands of annotated real documents from open sources, a hundred thousand of generated synthetic documents, and nearly a million unlabeled documents, the DocILE lab comes with the largest publicly available dataset for KILE and LIR. We are looking forward to contributions from the Computer Vision, Natural Language Processing, Information Retrieval, and other communities. The data, baselines, code and up-to-date information about the lab and competition are available at https://docile.rossum.ai/.

show abstract

Section: Dataset Characteristicsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

DocILE 2023 Teaser: Document Information Localization and Extraction

Šimsa¹,

Müller²,

Skalický³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…One-shot principle is studied in information extraction and can be also applied without the need of any learnable parameters, for example as templates matching [7].…”

Section: Previous and Other Workmentioning

confidence: 99%

Learning from similarity and information extraction from structured documents

Holeček

2020

Preprint

View full text Add to dashboard Cite

Neural networks have successfully advanced in the task of information extraction from structured documents. In business document processing more precise techniques equal more automation and less manual work.In this paper we will design and examine various fully trainable approaches to use siamese networks, concepts of similarity, one-shot learning and context/memory awareness. The aim is to improve micro F 1 of per-word classification on a testing split of an existing real world document dataset.The results verify the hypothesis, that access to a similar (yet still different) page with it's target information improves the information extraction. Furthermore the added contributions (in addition to siamese networks) of employing a class information, query-answer attention module and skip connections to the similar page are all required to beat the previous results.Our best model improves previous state-of-art results by 0.0825 gain in F 1 score. All the techniques used are not problem-specific and should be generalizable to help in other tasks and contexts. The code and anonymized version of the dataset are provided.

show abstract

“…However, such methods often fail when a document with unseen template is encountered [22]. To improve template-based methods, in [5] an one-shot template-matching algorithm invariant to changes in position is proposed. Methods that work on unseen document formats were proposed in [19,13].…”

Section: Introductionmentioning

confidence: 99%

Automatic travel pattern extraction from visa page stamps using CNN models

Ledinauskas¹,

Ruseckas²,

Marozas³

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose an automated document analysis system that processes scanned visa pages and automatically extracts the travel pattern from detected stamps. The system processes the page via the following pipeline: stamp detection in the visa page; general stamp country and entry/exit recognition; Schengen area stamp country and entry/exit recognition; Schengen area stamp date extraction. For each stage of the proposed pipeline we construct neural network models. We integrated Schengen area stamp detection and date, country, entry/exit recognition models together with graphical user interface into an automatic travel pattern extraction tool, which is precise enough for practical applications.

show abstract

One-Shot Template Matching for Automatic Document Data Capture

Cited by 10 publications

References 13 publications

DocILE 2023 Teaser: Document Information Localization and Extraction

DocILE 2023 Teaser: Document Information Localization and Extraction

Learning from similarity and information extraction from structured documents

Automatic travel pattern extraction from visa page stamps using CNN models

Contact Info

Product

Resources

About