Reconstructed error and linear representation coefficients restricted by _1-minimization for face recognition under different illumination and occlusion
Summary: The problem of recognizing human faces from frontal views with varying illumination, occlusion, and disguise is a great challenge to pattern recognition. A general knowledge is that face patterns from an objective set sit on a linear subspace. On the proof of the knowledge, some methods use the linear combination to represent a sample in face recognition. In this paper, in order to get the more discriminant information of reconstruction error, we constrain both the linear combination coefficients and the reconstruction error by \(\ell_1\)-minimization which is not apt to be disturbed by outliners. Then, through an equivalent transformation of the model, it is convenient to compute the parameters in a new underdetermined linear system. Next, we use an optimization method to get the approximate solution. As a result, the minimum reconstruction error has contained much valuable discriminating information. The gradient of this variable is measured to decide the final recognition. The experiments show that the recognition protocol based on the reconstruction error achieves high performance on available databases (Extended Yale B and AR Face database).
- Face recognition using elastic local reconstruction based on a single face image
- A fast \(\ell_1\)-solver and its applications to robust face recognition
- Fast and robust face recognition via coding residual map learning based adaptive masking
- A modular weighted sparse representation based on Fisher discriminant and sparse residual for face recognition with occlusion
- scientific article; zbMATH DE number 6129860
- A weighted block dictionary learning algorithm for classification
- Connected Component Model for Multi-Object Tracking
- Deep extreme learning machine and its application in EEG classification
- Face Recognition Under Varying Illumination Using Gradientfaces
- Face recognition using FLDA with single training image per person
- For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
- Normalization of Face Illumination Based on Large-and Small-Scale Features
- Stable signal recovery from incomplete and inaccurate measurements
- Subspace learning via local probability distribution for hyperspectral image classification
This page was built for publication: Reconstructed error and linear representation coefficients restricted by \(\ell_1\)-minimization for face recognition under different illumination and occlusion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1992344)
