ChronSeg: Novel dataset for segmentation of handwritten historical chronicles

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F21%3A43962097" target="_blank" >RIV/49777513:23520/21:43962097 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.researchgate.net/publication/349201748_ChronSeg_Novel_Dataset_for_Segmentation_of_Handwritten_Historical_Chronicles" target="_blank" >https://www.researchgate.net/publication/349201748_ChronSeg_Novel_Dataset_for_Segmentation_of_Handwritten_Historical_Chronicles</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0010317203140322" target="_blank" >10.5220/0010317203140322</a>

Jazyk výsledku

angličtina

Název v původním jazyce

ChronSeg: Novel dataset for segmentation of handwritten historical chronicles

Popis výsledku v původním jazyce

The segmentation of document images plays an important role in the process of making their content electronically accessible. This work focuses on the segmentation of historical handwritten documents, namely chronicles. We take image, text and background classes into account. For this goal, a new dataset is created mainly from chronicles provided by Porta fontium. In total, the dataset consists of 58 images of document pages and their precise annotations for text, image and graphic regions in PAGE format. The annotations are also provided at a pixel level. Further, we present a baseline evaluation using an approach based on a fully convolutional neural network. We also perform a series of experiments in order to identify the best method configuration. It includes a novel data augmentation method which creates artificial pages.

Název v anglickém jazyce

ChronSeg: Novel dataset for segmentation of handwritten historical chronicles

Popis výsledku anglicky

The segmentation of document images plays an important role in the process of making their content electronically accessible. This work focuses on the segmentation of historical handwritten documents, namely chronicles. We take image, text and background classes into account. For this goal, a new dataset is created mainly from chronicles provided by Porta fontium. In total, the dataset consists of 58 images of document pages and their precise annotations for text, image and graphic regions in PAGE format. The annotations are also provided at a pixel level. Further, we present a baseline evaluation using an approach based on a fully convolutional neural network. We also perform a series of experiments in order to identify the best method configuration. It includes a novel data augmentation method which creates artificial pages.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

O - Projekt operacniho programu

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence

ISBN

978-989-758-484-8

ISSN

2184-433X

e-ISSN

—

Počet stran výsledku

9

Strana od-do

314-322

Název nakladatele

ScitePress

Místo vydání

Setúbal

Místo konání akce

Online Streaming

Datum konání akce

4. 2. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000661455800031