http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : ( Thian Song Ong ) (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
Feature fusions for 2.5D face recognition in Random Maxout Extreme Learning Machine
Chong, Lee Ying,Ong, Thian Song,Teoh, Andrew Beng Jin Elsevier 2019 Applied soft computing Vol.75 No.-
<P><B>Abstract</B></P> <P>Contemporary face recognition system is often based on either 2D (texture) or 3D (texture + shape) face modality. An alternative modality that utilizes range (depth) facial images, namely 2.5D face recognition emerges. In this paper, we propose a 2.5D face descriptor that based on the Regional Covariance Matrix (RCM), a powerful means of feature fusion technique and a novel classifier dubbed Random Maxout Extreme Learning Machine (RMELM). The RCM of interest is constructed based on the Principal Component Analysis (PCA) filters responses of facial texture and/or range image, wherein the PCA filters are learned from a two-layer PCA network. The RMELM is an ELM variant where the activation function is based on the locally linear maxout function, in place of typical global non-linear functions in ELM. Since the RCM is a special case of symmetric positive definite matrix that resides on the Tensor manifold; a gap exists in between RCM and RMELM, which is a vector-based classifier. To bridge the gap, we flatten the manifold by transforming the RCM to a feature vector via a matrix logarithm operator. Experimental results from two public 3D face databases, FRGC v2.0 database and Gavab database, validated our proposed method is promising in 2.5D face recognition.</P> <P><B>Highlights</B></P> <P> <UL> <LI> A learning-based Regional Covariance Matrix (RCM) based on Principal Component Analysis (PCA) is proposed as a feature descriptor for 2.5D face recognition problem. </LI> <LI> PCARCM is demonstrated as an intra-feature (range features) and inter-feature (range and texture features) fusion container. </LI> <LI> Random Maxout Extreme Learning Machine as classifier is proposed to couple with PCARCM on the Tensor Manifold. </LI> </UL> </P> <P><B>Graphical abstract</B></P> <P>[DISPLAY OMISSION]</P>
-
A Revocable Fingerprint Template for Security and Privacy Preserving
( Zhe Jin ),( Andrew Beng Jin Teoh ),( Thian Song Ong ),( Connie Tee ) 한국인터넷정보학회 2010 KSII Transactions on Internet and Information Syst Vol.4 No.6
With the wide deployment of biometric authentication systems, several issues pertaining security and privacy of the biometric template have gained great attention from the research community. To resolve these issues, a number of biometric template protection methods have been proposed. However, the design of a template protection method to satisfy four criteria, namely diversity, revocability and non-invertibility is still a challenging task, especially performance degradation when template protection method is employed. In this paper, we propose a novel method to generate a revocable minutiae-based fingerprint template. The proposed method consists of feature extraction from fingerprint minutiae pairs, quantization, histogram binning, binarization and eventually binary bit-string generation. The contributions of our method are two fold: alignment-free and good performance. Various experiments on FVC2004 DB1 demonstrated the effectiveness of the proposed methods.
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
