Family Coat of Arms and Armorial Achievement Classification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU132055" target="_blank" >RIV/00216305:26230/19:PU132055 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.fit.vut.cz/research/publication/11848/" target="_blank" >https://www.fit.vut.cz/research/publication/11848/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-16660-1_56" target="_blank" >10.1007/978-3-030-16660-1_56</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Family Coat of Arms and Armorial Achievement Classification

Popis výsledku v původním jazyce

This paper presents an approach to classification of family coats of arms and armorial achievement. It is difficult to obtain images with coats of arms because not many of them are publicly available. To the best of our knowledge, there is no dataset. Therefore, we artificially extend our dataset using Neural Style Transfer technique and simple image transformations. We describe our dataset and the division into training and test sets that respects the lack of data examples. We discuss results obtained with both small convolutional neural network (convnet) trained from scratch and modified architectures of various convents pretrained on Imagenet dataset. This paper further focuses on the VGG architecture which produces the best accuracy. We show accuracy progress during training, per-class accuracy and a normalized confusion matrix for VGG16 architecture. We reach top-1 accuracy of nearly 60% and top-5 accuracy of 80%. To the best of our knowledge, this is the first family coats of arms classification work, so we cannot compare our results with others.

Název v anglickém jazyce

Family Coat of Arms and Armorial Achievement Classification

Popis výsledku anglicky

This paper presents an approach to classification of family coats of arms and armorial achievement. It is difficult to obtain images with coats of arms because not many of them are publicly available. To the best of our knowledge, there is no dataset. Therefore, we artificially extend our dataset using Neural Style Transfer technique and simple image transformations. We describe our dataset and the division into training and test sets that respects the lack of data examples. We discuss results obtained with both small convolutional neural network (convnet) trained from scratch and modified architectures of various convents pretrained on Imagenet dataset. This paper further focuses on the VGG architecture which produces the best accuracy. We show accuracy progress during training, per-class accuracy and a normalized confusion matrix for VGG16 architecture. We reach top-1 accuracy of nearly 60% and top-5 accuracy of 80%. To the best of our knowledge, this is the first family coats of arms classification work, so we cannot compare our results with others.

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

<a href="/cs/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Intelligent Systems Design and Applications

ISBN

—

ISSN

2194-5357

e-ISSN

—

Počet stran výsledku

9

Strana od-do

577-586

Název nakladatele

Springer International Publishing

Místo vydání

Los Alamitos

Místo konání akce

Vellore

Datum konání akce

6. 12. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—