Realtime Criminal Face Recognition System based on Innovative Facial Classification to Improve Accuracy using Arcface over Deepface

Aim: The objective of this study is to use face recognition technology to identify the suspects through facial biometrics which helps in identification of criminals in a better way. LBPH algorithm is used for the face recognition method. Materials and Methods: Face detection for identifying the criminals is performed using Arcface (N=10) over Deepface model (N=10) with Gpower of 80% and alpha =0.05, split size of 70% and 30 % for training and testing model respectively. Results: It is found that the accuracy of Arcface is 92.50% which is higher than the Deepface model 91.90% and attained the significance value of p=0.0118 (p<0.05), showing that there is a significant difference between the groups.. Conclusion: For the face identification purpose Arcface algorithm is preferred than Deepface algorithm.