Article: Face verification and identification using DCT-NNDA and SIFT with score-level fusion Journal: International Journal of Biomedical Engineering and Technology (IJBET) 2013 Vol.13 No.2 pp.154 - 176 Abstract: This paper proposes a new face verification and identification system based on the fusion of global and local features of face. DCT is used to extract global features from face images. A non-parametric discrimination method, NNDA is applied on the global features to make them more compact within the class clusters; while separating among the class clusters. The effects of expression variations are removed by DWT. It is found that DCT-NNDA is robust to small noisy (blurred) faces, but its performance degrades gradually for variations in scale, rotation, expression and pose. These issues are resolved using local feature extraction through SIFT. The work utilises strengths of DCT-NNDA and SIFT along with score level fusion. The proposed method is robust to scale, small noise, pose, expression, and illumination variations. The proposed system achieves 1% and 0.2% EER along with 99.5% and 98.6% recognition accuracy on ORL and Yale databases, respectively. Inderscience Publishers - linking academia, business and industry through research

Title: Face verification and identification using DCT-NNDA and SIFT with score-level fusion

Authors: Suryakant Tyagi; Pritee Khanna

Addresses: Computer Science and Engineering Discipline, PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, Jabalpur 482005, Madhya Pradesh, India ' Computer Science and Engineering Discipline, PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, Jabalpur 482005, Madhya Pradesh, India

Abstract: This paper proposes a new face verification and identification system based on the fusion of global and local features of face. DCT is used to extract global features from face images. A non-parametric discrimination method, NNDA is applied on the global features to make them more compact within the class clusters; while separating among the class clusters. The effects of expression variations are removed by DWT. It is found that DCT-NNDA is robust to small noisy (blurred) faces, but its performance degrades gradually for variations in scale, rotation, expression and pose. These issues are resolved using local feature extraction through SIFT. The work utilises strengths of DCT-NNDA and SIFT along with score level fusion. The proposed method is robust to scale, small noise, pose, expression, and illumination variations. The proposed system achieves 1% and 0.2% EER along with 99.5% and 98.6% recognition accuracy on ORL and Yale databases, respectively.

Keywords: face verification; face identification; DCT; NNDA; non-parametric discrimination; SIFT; scale invariant feature transform; discrete wavelet transform; discrete cosine transform; equal error rate; feature fusion; EER; biometrics; global features; local features; face images; expression variations; feature extraction; face recognition.

DOI: 10.1504/IJBET.2013.057928

International Journal of Biomedical Engineering and Technology, 2013 Vol.13 No.2, pp.154 - 176

Received: 02 Jan 2013
Accepted: 07 Oct 2013
Published online: 27 Sep 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Face verification and identification using DCT-NNDA and SIFT with score-level fusion

Keep up-to-date