PROJECT TITLE :

Local-Gravity-Face (LG-face) for Illumination-Invariant and Heterogeneous Face Recognition

ABSTRACT:

This paper proposes a completely unique method known as native-gravity-face (LG-face) for illumination-invariant and heterogeneous face recognition (HFR). LG-face employs an idea known as the native gravitational force angle (LGFA). The LGFA is that the direction of the gravitational force that the middle pixel exerts on the opposite pixels among a local neighborhood. A theoretical analysis shows that the LGFA is an illumination-invariant feature, considering only the reflectance part of the local texture result of the neighboring pixels. It also preserves edge information. Rank one recognition rates of ninety seven.seventy eightpercent on the CMU-PIE database and 97.thirty onep.c on the Extended Yale B database are achieved under varying illumination, demonstrating that LG-face is a good methodology of illumination-invariant face recognition. For HFR, when faces appear in different modalities, LG-face produces a standard feature illustration. Rank one recognition rates of ninety nine.96% on the CUFS database, ninety eight.67p.c on the CUFSF database, and 99.78% on the CASIA-HFB database show that the LG-face is additionally an effective method for HFR. The proposed technique additionally performs consistently in the presence of complicated variations and noise.