Probability density function based fusion of CNN models for face recognition from video

Abstract

This thesis describes Face recognition using CNN classifiers and final ranking for class predicted by the proposed method is done using rank-level fusion. This thesis works on multi instance of individual faces, multi algorithms based on probability density approaches and multiple classifiers. Fuzzy ranking is generated by outputs (confidence factors) of classifier using the density functions based formulation. VGG16, InceptionResnetV2 and Xception are used as CNN classifiers. For mathematical formulation used three different probability density functions are Gaussian Density Function, Triangle Density function and Trapezoidal Density function. Rank-level fusion is done to generate final ranking. Later, comparison between three density functions are implemented. The proposed method is successfully tested two datasets. One is Chokepoint dataset and another Custom dataset. The datasets are created by cropping faces from videos using MTCNN and OpenCV. The rank-level fusion is performing better than used three CNN models according to accuracy. The accuracy scores for Chokepoint dataset corresponding to Gaussian density function, Triangle Density function and Trapezoidal Density Function are 99.802%, 99.904% and 99.896% respectively and accuracy scores for Custom dataset are 99.762%, 99.716% and 99.75% respectively. It shows a supremacy regarding to face recognition.