Hybrid Machine Learning Model for Face Recognition Using SVM

Face recognition systems have enhanced human-computer interactions in the last ten years. However, literature reveals that current techniques used for identifying or verifying faces are not immune to limitations. Principal Component Analysis-Support Vector Machine (PCA-SVM) and Analysis-Artificial Neural Network (PCA-ANN) among relatively recent powerful face analysis techniques. Compared PCA-ANN, PCA-SVM has demonstrated generalization capabilities many tasks, including ability recognize objects with small large data samples. Apart from requiring a minimal number of parameters detection, minimizes errors avoids overfitting problems better than PCA-ANN. PCA-SVM, however, is ineffective inefficient detecting human cases which there poor lighting, long hair, items covering subject's face. This study proposes novel PCA-SVM-based model overcome problem PCA-ANN enhance detection. The experimental results indicate proposed provides outcome PCA-SVM.