2015 | OriginalPaper | Buchkapitel
Palmprint Liveness Detection by Combining Binarized Statistical Image Features and Image Quality Assessment
verfasst von : Xiaoming Li, Wei Bu, Xiangqian Wu
Erschienen in: Biometric Recognition
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper proposes a method based on Binarized Statistical Image Features (BSIF) and Image Quality Assessment for palmprint anti-spoofing approach. Firstly, BSIF computes a binary code for each pixel by filters, whose basis vectors are learnt from natural images via independent component analysis. For palmprint, it provides more texture information than the features in the original image. Image Quality Assessments are suitable measures since the recaptured images have features of blur and less details. Secondly, a new feature vector is formed by the former feature vectors. Finally, a SVM classifier is trained to discriminate the live and fake palmprint image. We collect a new database using iphone5 and iphone5s, which is the first one for palmprint liveness detection. Experiments on this database show great efficiency and high accuracy.