PROJECT TITLE :

Local directional mask maximum edge patterns for image retrieval and face recognition

ABSTRACT:

This study proposes a brand new feature descriptor, native directional mask most edge pattern, for image retrieval and face recognition applications. Native binary pattern (LBP) and LBP variants collect the relationship between the centre pixel and its surrounding neighbours in an image. Therefore, LBP based mostly features are very sensitive to the noise variations in an image. Whereas the proposed technique collects the maximum edge patterns (MEP) and most edge position patterns (MEPP) from the magnitude directional edges of face/image. These directional edges are computed with the help of directional masks. Once the directional edges (DE) are computed, the MEP and MEPP are coded based mostly on the magnitude of DE and position of maximum DE. Additional, the robustness of the proposed methodology is increased by integrating it with the multiresolution Gaussian filters. The performance of the proposed methodology is tested by conducting four experiments onopen access series of imaging studies-magnetic resonance imaging, Brodatz, MIT VisTex and Extended Yale B databases for biomedical image retrieval, texture retrieval and face recognition applications. The results once being investigated the proposed method shows a important improvement as compared with LBP and LBP variant features in terms of their evaluation measures on respective databases.