MagnifyMe: Aiding Cross Resolution Face Recognition via Identity Aware Synthesis
This work addresses the problem of face recognition across different image resolutions, which is important for security and surveillance applications, but it is incremental as it builds on existing super-resolution and synthesis techniques.
The researchers tackled cross-resolution face recognition by proposing the Synthesis via Deep Sparse Representation (SDSR) algorithm to synthesize high-resolution images from low-resolution inputs, achieving improved performance in face identification and image quality on four databases compared to seven existing methods.
Enhancing low resolution images via super-resolution or image synthesis for cross-resolution face recognition has been well studied. Several image processing and machine learning paradigms have been explored for addressing the same. In this research, we propose Synthesis via Deep Sparse Representation algorithm for synthesizing a high resolution face image from a low resolution input image. The proposed algorithm learns multi-level sparse representation for both high and low resolution gallery images, along with an identity aware dictionary and a transformation function between the two representations for face identification scenarios. With low resolution test data as input, the high resolution test image is synthesized using the identity aware dictionary and transformation which is then used for face recognition. The performance of the proposed SDSR algorithm is evaluated on four databases, including one real world dataset. Experimental results and comparison with existing seven algorithms demonstrate the efficacy of the proposed algorithm in terms of both face identification and image quality measures.