A new face recognition system is proposed using a nonlinear image enhancement algorithm
incorporated in a synthetic discriminant function based shifted phase-encoded fringe-adjusted joint
transform correlation (SDF-SPFJTC) technique as a preprocessing step. The given input image recorded
from a long distance is improved by using adaptive dynamic range compression and local contrast
enhancement schemes. The Viola-Jones technique is then applied to detect any human face in the scene and
hence correct its size. Finally the SDF-SPFJTC technique yields the recognition of the target face along
with its location. Computer simulation performed on real life scenes shows efficient and successful
recognition performance in varying environmental conditions.
- Downloading of the abstract is permitted for personal use only.