End-to-end table structure recognition and extraction in heterogeneous documents

T Kashinath, T Jain, Y Agrawal, T Anand, S Singh - Applied Soft Computing, 2022 - Elsevier
Automatically detecting and parsing tables into an indexable and searchable format is an
important problem in document digitization. It relates to computer vision, machine learning …

Improving accessibility of digitization outputs: EODOPEN project research findings

A Kavčič Čolić, A Hari - Digital Library Perspectives, 2024 - emerald.com
Purpose The current predominant delivery format resulting from digitization is PDF, which is
not appropriate for the blind, partially sighted and people who read on mobile devices. To …

HU‐PageScan: a fully convolutional neural network for document page crop

RB das Neves, E Lima, BLD Bezerra… - IET Image …, 2020 - Wiley Online Library
November The offer of online, automated, and impersonal services demand users to upload
scanned copies of their documents to the organisations. As a consequence of this …

A fast fully octave convolutional neural network for document image segmentation

RB das Neves, LF Verçosa, D Macêdo… - … Joint Conference on …, 2020 - ieeexplore.ieee.org
The Know Your Customer (KYC) and Anti Money Laundering (AML) are worldwide practices
to online customer identification based on personal identification documents, similarity and …

Robust detection of tables in documents using scores from table cell cores

M Ajij, S Pratihar, DS Roy, T Hanne - SN Computer Science, 2022 - Springer
Table detection is an essential step in many document analysis systems. Tabular data are a
pivotal form of information representation that can organize data in a conventional structure …

[HTML][HTML] Towards enabling blind people to fill out paper forms with a wearable smartphone assistant

S Feiz, A Borodin, X Bi… - Proceedings. Graphics …, 2021 - ncbi.nlm.nih.gov
We present PaperPal, a wearable smartphone assistant which blind people can use to fill
out paper forms independently. Unique features of PaperPal include: a novel 3D-printed …

Classification of handwritten annotations in mixed-media documents

A Dash, AB Albu - 2022 19th Conference on Robots and Vision …, 2022 - ieeexplore.ieee.org
Handwritten annotations in documents contain valuable information, but they are
challenging to detect and identify. This paper addresses this challenge. We propose an al …

A fast fully octave convolutional neural network for document image segmentation

RBN Junior, LF Verçosa, D Macêdo… - arXiv preprint arXiv …, 2020 - arxiv.org
The Know Your Customer (KYC) and Anti Money Laundering (AML) are worldwide practices
to online customer identification based on personal identification documents, similarity and …

Parameter free approach for segmenting complex manhattan layouts

L Melinda, C Bhagvati - Multimedia Tools and Applications, 2023 - Springer
This paper presents a two-stage parameter-free technique for the physical layout analysis of
a document. In the first stage, Gaussian Mixture Model (GMM) with Expectation …

An efficient method for stamps verification using haar wavelet sub-bands with histogram and moment

MA Rajab, LE George - 2021 1st Babylon International …, 2021 - ieeexplore.ieee.org
Stamps have been used as visible certificates for documents since long time ago. At present,
they are used for certifying official books, memos, agreements those government institutions …