Realtime human face tracking and recognition system on uncontrolled environment

Abstract

<span lang="EN-US">Recently, one of the most important biometrics is that automatically recognized human faces are based on dynamic facial images with different rotations and backgrounds. This paper presents a real-time system for human face tracking and recognition with various expressions of the face, poses, and rotations in an uncontrolled environment (dynamic background). Many steps are achieved in this paper to enhance, detect, and recognize the faces from the image frame taken by web-camera. The system has three steps: the first is to detect the face, Viola-Jones algorithm is used to achieve this purpose for frontal and profile face detection. In the second step, the color space algorithm is used to track the detected face from the previous step. The third step, principal component analysis (eigenfaces) algorithm is used to recognize faces. The result shows the effectiveness and robustness depending on the training and testing results. The real-time system result is compared with the results of the previous papers and gives a success, effectiveness, and robustness recognition rate of 91.12% with a low execution time. However, the execution time is not fixed due depending on the frame background and specification of the web camera and computer.</span>

Optimization of CPBIS methods applied on enhanced fibrin microbeads approach for image segmentation in dynamic databases

“…Al-Ghrairi et al [10] has sad that, Among the diverse array of applications, object classification stands out as a crucial task for enabling robots to comprehend and respond to their environment effectively. Niraimathi [11] has pointed out that, the potency of some of the statistics that may turn out to be potential clusters and intermediate clusters is reduced to some extent by repeated reductions to the extent that they lose the possibility of evolving to intermediate clusters.…”