FCN-Boosted Historical Map Segmentation with Little Training Data

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F23%3A43969346" target="_blank" >RIV/49777513:23520/23:43969346 - isvavai.cz</a>

Result on the web

<a href="https://link.springer.com/chapter/10.1007/978-3-031-41676-7_30" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-41676-7_30</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-41676-7_30" target="_blank" >10.1007/978-3-031-41676-7_30</a>

Result language

angličtina

Original language name

FCN-Boosted Historical Map Segmentation with Little Training Data

Original language description

This paper deals with automatic image segmentation in poorly resourced areas. We concentrate on map content segmentation in historical maps as an example of such a domain. In such cases, conventional computer vision (CV) approaches fail in unexpected unique regions such as map content area exceeding the map frame, while deep learning methods lack boundary localization accuracy. Therefore, we propose an efficient approach that combines conventional CV techniques with deep learning and practically eliminates their drawbacks. To do so, we redefine the learning objective of a simple fully convolutional network to make the training easier and the model more robust even with few training samples. The presented method provides excellent results compared to more sophisticated but solely deep learning or traditional computer vision techniques as shown in “MapSeg” segmentation competition, where all other approaches were significantly outperformed. We further propose two additional approaches that improve the original method and set a new state-of-the-art result on the MapSeg dataset. The methods are further tested on an extended version of the Map Border dataset to show their robustness.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2023

Confidentiality

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

Article name in the collection

Document Analysis and Recognition – ICDAR 2023

ISBN

978-3-031-41675-0

ISSN

0302-9743

e-ISSN

1611-3349

Number of pages

14

Pages from-to

520-533

Publisher name

Springer

Place of publication

neuveden

Event location

San José, CA, USA

Event date

Aug 21, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—