<![CDATA[Face recognition is a widely used biometric technology in security systems, automated attendance, and surveillance applications. This study proposes an enhanced real-time face detection method by integrating a modified AdaBoost-based feature selection strategy into the Viola–Jones framework. The applied mathematical contribution of this study lies in formulating the optimization process as an empirical risk minimization model with adaptive boosting weight updates to reduce face recognition error. The proposed approach optimizes the weighting of weak classifiers by prioritizing Haar-like features with minimal weighted classification error at each boosting iteration, thereby improving discriminative capability. Experiments were conducted on a camera-based dataset consisting of face and non-face samples under varying illumination and pose conditions. Prior to optimization, the system achieved a precision of 70.04% and a recall of 70.05%. After applying the proposed enhancement, precision increased to 81.04% and recall to 90.02%. These results demonstrate that the modified AdaBoost integration significantly improves detection accuracy while remaining suitable for real-time face detection applications.]]>
Copyrights © 2026
