Face Recognition in an Unconstrained and Real-Time Environment Using Novel BMC-LBPH Methods Incorporates with DJI Vision Sensor

• DOI: 10.3390/jsan9040054
• Publication Date: 2020-11-30T02:00:57Z
• Authors: Md Manjurul Ahsan; Yueqing Li; Jing Zhang; Md Tanvir Ahad; Munshi Md. Shafwa...
• Keywords: Local Binary Patterns; Robustness; Eigenface

Face recognition (FR) in an unconstrained environment, such as low light, illumination variations, and bad weather is very challenging still needs intensive further study. Previously, numerous experiments on FR environment have been assessed using Eigenface, Fisherface, Local binary pattern histogram (LBPH) algorithms. The result indicates that LBPH the optimal one compared to others due its robustness various lighting conditions. However, no specific experiment has conducted identify best setting of four parameters LBPH, radius, neighbors, grid, threshold value, for techniques terms accuracy computation time. Additionally, overall performance environments are usually underestimated. Therefore, this work, in-depth carried out evaluate two face datasets: Lamar University data base (LUDB) 5_celebrity dataset, a novel Bilateral Median Convolution-Local (BMC-LBPH) method was proposed examined real-time rainy unmanned aerial vehicle (UAV) incorporates with 4 vision sensors. experimental results showed BMC-LBPH outperformed traditional methods by achieving 65%, 98%, 78% LU weather, respectively. Ultimately, provides promising solution facial UAV.