Output details
15 - General Engineering
Brunel University London
Combining Perceptual Features With Diffusion Distance for Face Recognition
Face recognition has been an active research area for at least 3 decades but patchy performance has been the main drawback of conventional solutions. This paper pursues an approach for consistent recognition performance with the use of perceptual features by Gabor filtering in combination with diffusion distance. The algorithm has demonstrated a significant improvement in recognition performance compared to several state of the art algorithms. The work has been cited by leading researchers and is currently being used in discriminative image representations that aim at classifying human faces in large databases. <EU grant RUSHES>