A novel hybrid biometric software application for facial recognition considering uncontrollable environmental conditions

Abstract

Human face recognition research in biometric applications is a popular research subject because of its various applications and challenges, including camera type, pose, light or illumination, resolutions, wearing or not wearing glasses, and expressions, among others. This study presents a novel hybrid biometric software application for facial recognition considering uncontrollable environmental conditions. The proposed system uses two features namely, Laplace of Gaussian filter-based Discrete Wavelet Transform (LGDWT) and Discrete Cosine Transform Compressed based Log Gabor Filter (DCTLGF). The combined LGDWT and DCTLGF features were used by a Multiclass Support Vector Machine (MSVM) classifier to create the desired class label of individual faces. Our work was tested on a face dataset comprising 25 people of 200 face images which are taken using a five-megapixel low-goal web camera and yielded good results in different bounds in contrast to existing techniques.

Keywords

• Face recognition
• Biometric applications
• Wavelet transform
• Logarithmic gabor
• Classification