Face Recognition from Color Images Using Sparse Projection Analysis

The paper presents a novel feature extraction technique for face recognition which uses sparse projection axes to compute a lowdimensional representation of face images. The proposed technique derives the sparse axes by first recasting the problem of face recognition as a regression problem and then solving the new (under-determined) regression problem by computing the solution with minimum L1 norm. The developed technique, named Sparse Projection Analysis (SPA), is applied to color as well as grey-scale images from the XM2VTS database and compared to popular subspace projection techniques (with sparse and dense projection axes) from the literature. The results of the experimental assessment show that the proposed technique ensures promising results on un-occluded as well occluded images from the XM2VTS database. Key words: Image processing, biometrics, face recognition, regression problem, sparse projection axes.

• Type: Journal
• Year: 2010
• Where: ICIAR
• Authors: Vitomir Struc, Nikola Pavesic
• Keywords: ICIAR 2010, Image Analysis, Regression Problem, Sparse, Sparse Projection