Real-time liveness detection algorithm based on eyes detection and utilize age estimation technique to build a controllable environment

الملخص EN

Detecting liveness and age estimation have many applications and attract many researchers.

There are many approaches for detecting liveness and estimating age, still some limitations can be addressed such as they are focusing on image quality, eyelid motion, and facial expression to analyze spoof images.

In addition, existing methods proposed for either detecting liveness with the aim of preventing spoof attack, or for estimating age with the aim of grouping facial images or classifying them.

In this research, a method for liveness detection and age estimation based on low camera resolution is proposed for the aim of building controllable environment that allow parents from dominating the usage of computers by young children.

The idea is based on combining liveness detection techniques with age estimation.

Firstly, the method detecting the movements in the eye region and weighing these movements from number of selected frames from the recorded video.

Then the method determines whether the user is live person or no to take a decision in next step after estimating user age.

The obtained results show that, the method was able to accurately determine the liveness as well as take a decision based on the recorded video using low resolution camera.

Furthermore, due to the nature of the data employed in this study, the researchers generated some data for the real users using low resolution building webcam device by recording video of users’ face images on mobile device.

With that, number of different videos had been used to detect the liveness.

The results also show the ability of the proposed algorithms in achieving the intended objectives whereby these algorithms can be used to build a controllable environment in which the specific age can access or restricted from accessing internet explorer as example.