ENHANCED CRIME SUSPECT IDENTIFICATION SYSTEM USING DEEP NEURAL VISION   PROCESSING TECHNIQUE

Authors

  • Odo J.I.` Dept. of Computer Science, Peter University, Achina-Onneh, Anambra State, Nigeria.
  • E.F. Nworabude Dept of Electronic & Computer Engineering, Nnamdi Azikiwe University, Awka, Nigeria.
  • Onyia T.C. Dept of Electronic & Computer Engineering, Nnamdi Azikiwe University, Awka, Nigeria.
  • Obianyo O.R. Dept of Computer Engineering, Madonna University of Nigeria, Akpugo Campus, Enugu State, Nigeria.

Keywords:

Facial recognition, deep neural vision, biometrics, and rendering model.

Abstract

 

This paper discusses the improved facial recognition system in crime suspect identification system using deep neural vision processing technique. The research was motivated based on the problem of identification of crime suspect which security agents do experience these days. Several models like discrete wavelet transform model, rendering model, convolutional neural network model were used to design the new system which utilizes enhanced facial recognition approach and implemented on a Mathlab environment. The system was tested and validated using tenfold cross validation technique and the accuracy achieved was 99.22% which is very good. The system was later deployed at the Nigerian Police Force and tested for reliability using various facial expressions of volunteered criminals; and the result was excellent.

Downloads

Published

2023-12-28

Issue

Vol. 1 No. 2 (2023): International Journal of Computing, Science and New Technologies (IJCSNT) Vol.1 No.2 December 2023

Section

Articles