Sparse illumination learning and transfer for single-sample face recognition with image corruption and misalignment
From MaRDI portal
Abstract: Single-sample face recognition is one of the most challenging problems in face recognition. We propose a novel algorithm to address this problem based on a sparse representation based classification (SRC) framework. The new algorithm is robust to image misalignment and pixel corruption, and is able to reduce required gallery images to one sample per class. To compensate for the missing illumination information traditionally provided by multiple gallery images, a sparse illumination learning and transfer (SILT) technique is introduced. The illumination in SILT is learned by fitting illumination examples of auxiliary face images from one or more additional subjects with a sparsely-used illumination dictionary. By enforcing a sparse representation of the query image in the illumination dictionary, the SILT can effectively recover and transfer the illumination and pose information from the alignment stage to the recognition stage. Our extensive experiments have demonstrated that the new algorithms significantly outperform the state of the art in the single-sample regime and with less restrictions. In particular, the single-sample face alignment accuracy is comparable to that of the well-known Deformable SRC algorithm using multiple gallery images per class. Furthermore, the face recognition accuracy exceeds those of the SRC and Extended SRC algorithms using hand labeled alignment initialization.
Recommendations
- Face recognition from a single image per person: a survey
- Robust, accurate and efficient face recognition from a single training image: A uniform pursuit approach
- A single gallery-based face recognition using extended joint sparse representation
- Sparse representation for face recognition based on constraint sampling and face alignment
- On solving the face recognition problem with one training sample per subject
Cites work
- rm K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
- A dual algorithm for the solution of nonlinear variational problems via finite element approximation
- Applications of a Splitting Algorithm to Decomposition in Convex Programming and Variational Inequalities
- Block-Sparse Recovery via Convex Optimization
- Dense Error Correction Via \ell^1-Minimization
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- Matrix Analysis
- Sparse illumination learning and transfer for single-sample face recognition with image corruption and misalignment
Cited in
(6)- Sparse illumination learning and transfer for single-sample face recognition with image corruption and misalignment
- A single gallery-based face recognition using extended joint sparse representation
- Face recognition from a single image per person: a survey
- On solving the face recognition problem with one training sample per subject
- Representation recovery via L₁-norm minimization with corrupted data
- Robust, accurate and efficient face recognition from a single training image: A uniform pursuit approach
This page was built for publication: Sparse illumination learning and transfer for single-sample face recognition with image corruption and misalignment
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1799989)
