Background: Biometric testing concerning face recognition makes it hard to solve due
to the inaccuracy problem. Alongside the present progress in many technological fields, there are
still different critical issues that affect the performance of real-time face recognition systems.
Methods: Recent publications and patent databases related to face recognition are reviewed to find
the best classifier of face recognition. In addition, these publications and patents are concerned to
improve the face recognition system especially its real-time performance. In this paper, we introduce
a new multi-agent system that will improve the face recognition system especially its real-time performance.
Results: Face recognition done using multi-classifier (K-NN, NN, and CART) and multi-agents incorporated
agent with a multi-feature approach. Five types of agents are used in our experiments
namely; information agent, preprocessing agent, classifier agent, headquarters agent, and communication
agent. The experimental results showed that the recognition rate improved. Face recognition
accuracy up to 99.5% interpreted as 1.5 seconds in threading mode, and 1 second in distributed
Conclusion: By using multiple agents, the recognition processing time was improved. The use of
multi-feature extraction turned out to be more efficient in the recognition accuracy. The proposed
model proved to be robust in time using distributed mode execution for the classifier agents group.
In addition, tapping the issue of distributed vs. threading mode distribution of agents makes a great
link to the upcoming challenges of nowadays-modern sciences.