Title: An improved hybrid approach to face recognition by fusing local and global discriminant features

Authors: Jamuna Kanta Sing; Shiladitya Chowdhury; Dipak Kumar Basu; Mita Nasipuri

Addresses: Department of Computer Science and Engineering, Jadavpur University, 188 Raja S.C. Mullick Road, Kolkata 700 032, India. ' Department of Master of Computer Application, Techno India, EM-4/1, Sector V, Salt Lake, Kolkata 700 091, India. ' Department of Computer Science and Engineering, Jadavpur University, 188 Raja S.C. Mullick Road, Kolkata 700 032, India. ' Department of Computer Science and Engineering, Jadavpur University, 188 Raja S.C. Mullick Road, Kolkata 700 032, India.

Abstract: This paper presents a novel hybrid method which exploits both local and global discriminative features by a fusion for face representation and recognition. The whole face images are divided into a number of non-overlapping sub-regions to extract local discriminant features. The global discriminant features are extracted from the whole face images. The PCA and FLD methods are applied on the fused feature vector to extract lower dimensional discriminant features. The simulation results of the proposed method on the CMU PIE, FERET and AR face databases have been compared with other approaches and have demonstrated consistently improved performances.

Keywords: hybrid technique; face recognition; FLD; Fisher's linear discriminant; local features; global features; feature fusion; face representation; biometrics.

DOI: 10.1504/IJBM.2012.046245

International Journal of Biometrics, 2012 Vol.4 No.2, pp.144 - 164

Received: 09 Apr 2011
Accepted: 03 Aug 2011

Published online: 29 Nov 2014 *

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