Lipreading Using Spatiotemporal Histogram of Oriented Gradients

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F16%3A00000470" target="_blank" >RIV/46747885:24220/16:00000470 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/EUSIPCO.2016.7760575" target="_blank" >http://dx.doi.org/10.1109/EUSIPCO.2016.7760575</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/EUSIPCO.2016.7760575" target="_blank" >10.1109/EUSIPCO.2016.7760575</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Lipreading Using Spatiotemporal Histogram of Oriented Gradients

Popis výsledku v původním jazyce

We propose a visual speech parametrization based on histogram of oriented gradients (HOG) for the task of lipreading from frontal face videos. Inspired by the success of spatiotemporal local binary patterns, the features are designed to capture dynamic information contained in the input video sequence by combining HOG descriptors extracted from three orthogonal planes that span x, y and t axes. We integrate our features into a system based on hidden Markov model (HMM) and show that by utilizing robust and properly tuned parametrization this traditional scheme can outperform recent sophisticated embedding approaches to lipreading. We perform experiments on three different datasets, two of which are publicly available. In order to conduct an unbiased feature comparison, the process of model learning including hyperparameter tuning is as automatized as possible. To this end, we rely heavily on cross validation.

Název v anglickém jazyce

Lipreading Using Spatiotemporal Histogram of Oriented Gradients

Popis výsledku anglicky

We propose a visual speech parametrization based on histogram of oriented gradients (HOG) for the task of lipreading from frontal face videos. Inspired by the success of spatiotemporal local binary patterns, the features are designed to capture dynamic information contained in the input video sequence by combining HOG descriptors extracted from three orthogonal planes that span x, y and t axes. We integrate our features into a system based on hidden Markov model (HMM) and show that by utilizing robust and properly tuned parametrization this traditional scheme can outperform recent sophisticated embedding approaches to lipreading. We perform experiments on three different datasets, two of which are publicly available. In order to conduct an unbiased feature comparison, the process of model learning including hyperparameter tuning is as automatized as possible. To this end, we rely heavily on cross validation.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proc. of 24th European Signal Processing Conference (EUSIPCO 2016)

ISBN

978-0-9928626-5-7

ISSN

2219-5491

e-ISSN

—

Počet stran výsledku

4

Strana od-do

1882-1885

Název nakladatele

European Signal Processing Conference, EUSIPCO

Místo vydání

Maďarsko

Místo konání akce

Maďarsko, Budapešť

Datum konání akce

1. 1. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000391891900359