<![CDATA[This study proposes and implements a smart glasses model specifically designed to assist blind people in identifying people around them in real-time. This system utilizes computer vision technology, specifically the Local Binary Patterns Histograms (LBPH) algorithm implemented using the OpenCV library. The research process starts from facial dataset acquisition, model training, to dynamic facial recognition using an integrated camera. Test results show that the system is able to recognize faces with a certain level of confidence using a confidence threshold parameter of 80. System performance evaluation is carried out using Accuracy, Precision, Recall, and F1-Score metrics. Based on the results of experiments on three test objects, the system obtained an accuracy level of 90%–100%, a precision value of 94.7%–100%, a recall of 94.7%–95%, and an F1-score of 94.7%–97.4%. These results indicate that the LBPH algorithm has a fairly good ability to perform real-time facial recognition on smart glasses devices. This smart glasses model is expected to increase the independence, mobility, and social interaction of blind people in their daily lives.]]>
Copyrights © 2026
