Local Sliced-Wasserstein Feature Sets for Illumination-invariant Face Recognition
This addresses illumination invariance in face recognition, a domain-specific problem, with incremental improvements over existing methods.
The paper tackles face recognition under varying illumination by modeling local gradient distributions with the Radon Cumulative Distribution Transform (R-CDT), showing that lighting variations correspond to deformations in this domain that form a subspace. The method outperforms alternatives in challenging illumination tasks, with experimental results demonstrating its effectiveness.
We present a new method for face recognition from digital images acquired under varying illumination conditions. The method is based on mathematical modeling of local gradient distributions using the Radon Cumulative Distribution Transform (R-CDT). We demonstrate that lighting variations cause certain types of deformations of local image gradient distributions which, when expressed in R-CDT domain, can be modeled as a subspace. Face recognition is then performed using a nearest subspace in R-CDT domain of local gradient distributions. Experiment results demonstrate the proposed method outperforms other alternatives in several face recognition tasks with challenging illumination conditions. Python code implementing the proposed method is available, which is integrated as a part of the software package PyTransKit.