CNN Based Predictor of Face Image Quality

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00347755" target="_blank" >RIV/68407700:21230/21:00347755 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-68780-9_52" target="_blank" >https://doi.org/10.1007/978-3-030-68780-9_52</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-68780-9_52" target="_blank" >10.1007/978-3-030-68780-9_52</a>

Jazyk výsledku

angličtina

Název v původním jazyce

CNN Based Predictor of Face Image Quality

Popis výsledku v původním jazyce

We propose a novel method for training Convolution Neural Network, named CNN-FQ, which takes a face image and outputs a scalar summary of the image quality. The CNN-FQ is trained from triplets of faces that are automatically labeled based on responses of a pre-trained face matcher. The quality scores extracted by the CNN-FQ are directly linked to the probability that the face matcher incorrectly ranks a randomly selected triplet of faces. We applied the proposed CNN-FQ, trained on CASIA database, for selection of the best quality image from a collection of face images capturing the same identity. The quality of the single face representation was evaluated on 1:1 Verification and 1:N Identification tasks defined by the challenging IJB-B protocol. We show that the recognition performance obtained when using faces selected based on the CNN-FQ scores is significantly higher than what can be achieved by competing state-of-the-art image quality extractors.

Název v anglickém jazyce

CNN Based Predictor of Face Image Quality

Popis výsledku anglicky

We propose a novel method for training Convolution Neural Network, named CNN-FQ, which takes a face image and outputs a scalar summary of the image quality. The CNN-FQ is trained from triplets of faces that are automatically labeled based on responses of a pre-trained face matcher. The quality scores extracted by the CNN-FQ are directly linked to the probability that the face matcher incorrectly ranks a randomly selected triplet of faces. We applied the proposed CNN-FQ, trained on CASIA database, for selection of the best quality image from a collection of face images capturing the same identity. The quality of the single face representation was evaluated on 1:1 Verification and 1:N Identification tasks defined by the challenging IJB-B protocol. We show that the recognition performance obtained when using faces selected based on the CNN-FQ scores is significantly higher than what can be achieved by competing state-of-the-art image quality extractors.

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/GA19-21198S" target="_blank" >GA19-21198S: Složité predikční modely a jejich učení z částečně anotovaných dat</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Pattern Recognition. ICPR International Workshops and Challenges, Part VI

ISBN

978-3-030-68779-3

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

15

Strana od-do

679-693

Název nakladatele

Springer International Publishing

Místo vydání

Cham

Místo konání akce

Milan

Datum konání akce

10. 1. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—