User authentication is an important step to protect information and in this field face biometrics is advantageous. Face biometrics is natural, easy to use and less humaninvasive. Unfortunately, recent work has revealed that face biometrics is vulnerable to spoofing attacks using low-tech equipments. This article assesses how well existing face anti-spoofing countermeasures can work in a more realistic condition. Experiments carried out with two freely available video databases (Replay Attack Database and CASIA Face Anti-Spoofing Database) show low generalization and possible database bias in the evaluated countermeasures. To generalize and deal with the diversity of attacks in a real world scenario we introduce two strategies that show promising results.
Abstract. User authentication is an important step to protect information and in this field face biometrics is advantageous. Face biometrics is natural, easy to use and less human-invasive. Unfortunately, recent work has revealed that face biometrics is vulnerable to spoofing attacks using low-tech cheap equipments. This article presents a countermeasure against such attacks based on the LBP − T OP operator combining both space and time information into a single multiresolution texture descriptor. Experiments carried out with the REPLAY ATTACK database show a Half Total Error Rate (HT ER) improvement from 15.16% to 7.60%.
User authentication is an important step to protect information, and in this context, face biometrics is potentially advantageous. Face biometrics is natural, intuitive, easy to use, and less human-invasive. Unfortunately, recent work has revealed that face biometrics is vulnerable to spoofing attacks using cheap low-tech equipment. This paper introduces a novel and appealing approach to detect face spoofing using the spatiotemporal (dynamic texture) extensions of the highly popular local binary pattern operator. The key idea of the approach is to learn and detect the structure and the dynamics of the facial micro-textures that characterise real faces but not fake ones. We evaluated the approach with two publicly available databases (Replay-Attack Database and CASIA Face Anti-Spoofing Database). The results show that our approach performs better than state-of-the-art techniques following the provided evaluation protocols of each database.
RESUMO As expressões não manuais (ENMs) nas línguas de sinais (LS) incluem movimentos do corpo e expressões faciais. As ENMs podem desempenhar diferentes funções, tais como diferenciar itens lexicais, participar da construção sintática e contribuir com processos de intensificação. Dessa forma, as expressões faciais participam da construção do significado nas LS tanto quanto os parâmetros até então mais estudados, a saber: configuração, movimentos e localização das mãos. Este trabalho tem como objetivo analisar as ENMs produzidas por uma pessoa surda, fluente em libras, a partir de enunciados divididos nas modalidades assertiva e interrogativas parcial e total. Para a análise, foi construído um corpus de 60 enunciados constituídos da seguinte forma: 10 sinais-chave × 3 modalidades × 2 condições (neutra e intensificada). Esses enunciados foram devidamente anotados considerando as expressões não manuais e analisados estatisticamente. Neste trabalho, é avaliada a duração de sinais a fim de identificar o papel da intensificação, e são verificadas quais ENMs estão significativamente presentes nas três modalidades e nas condições neutra e intensificada. Os resultados apresentados, além de contribuírem para a pesquisa nas LS, são relevantes para a modelagem de avatares realistas sinalizadores de libras.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.