Improved Accuracy of Face Recognition System to Identify Criminal Based on Innovative Feature Extractor to Improve Accuracy Using Deepface over LBPH Algorithm
DOI:
https://doi.org/10.47750/pnr.2022.13.S04.051Keywords:
Facial Image, Innovative Deepface, Image Classification, Machine Learning, Local Binary Pattern Histograms (LBPH).Abstract
Aim: Criminal face recognition system helps in identifying the suspect and also helps in retrieving information about the
suspect. Innovative Deepface algorithm is used for the face recognition method. Materials and Methods: Face detection for
identifying the criminals is performed using Deep Face (N=10) over LBPH model (N=10) with Gpower of 80% and alpha
=0.05, with split size of 70% and 30 % for training and testing model respectively. Results: It is found that the accuracy of
Deepface is 91.90% which is higher than the LBPH model 90.80% and attained the significance value of p=0.0294 (p<0.05),
showing that there is a significant difference between the groups.. Conclusion: For the face identification purpose Innovative
Deepface algorithm is preferred than LBPH algorithm.
