Philippine E-Journals

Face Recognition using Back-propagation Neural Networks and OpenCV®

Romulo Maratas Estrera | Elmer A. Maravillas | Cherry Lyn C. Sta. Romana

Discipline: Information Technology

 

Abstract:

In today’s digital world, the need to maintain the security of information or physical property is becoming both increasingly important and increasingly difficult. Face recognition is one of the few biometric methods, which is very complicated system since the human faces change depending on their age, appearance. Every human being has several of facial expressions. So it is not possible to learn all types of facial characteristics into the network. As a result, there is a solution for the unrecognized. Moreover, due to the performance variations of the input device, face cannot be detected correctly, and pattern may change extremely. In this paper, we have developed and illustrated a recognition system for human faces using neural network approach. Facial recognition has virtually many areas of application. Implementation uses the back propagation neural network algorithm and backed-up by OpenCV (open source library for computer vision). Such implementation is carefully integrated to work with the (.Net) framework using Visual C# and intended to be as accurate and even surpass industry standard benchmarks using other face-recognition algorithms.