In this paper we propose a framework for 3D Face Recognition System (3DFRS) using segmentation by grouping of regions of facial images before and after fusion of two modalities (color and depth images). Firstly, the detection of face region is based on the localization of nose tip and integral projection curves. Then, the features resulting from Principle Component Analyses (PCA) followed by Enhanced Fisher Model (EFM) are extracted. Finally, the classification process is performed with two methods, distance measurement L3 and Support Vector Machine (SVM). Experiments are performed on the CASIA3D face database which contains 123 persons under varying illumination and expression. We have tried to examine all the variants associated with our algorithms in order to optimize the maximum our recognition system. The promising results of the experimental evaluation show that our proposed approach achieves a high recognition performance.
Indoor positioning systems are crucial for preserving and promoting cultural heritage sites by providing visitors with accurate location information and real-time exhibit details. These systems also offer valuable insights into visitor behavior for museums and cultural institutions to optimize their offerings and enhance the overall visitor experience. Their importance lies in driving engagement, fostering deeper connections with visitors, and providing data for future decision-making. This study proposes a magnetic field-based pedestrian localization algorithm as a solution to the challenge of providing accurate location information for visitors in indoor environments during virtual tours. The proposed approach uses magnetic field sequences to identify unique landmarks and a deep neural network (VGG-16) to analyze magnetic signal features and determine the visitor's location based on the nearest landmark. The study's results indicate that this magnetic field-based approach can be reliable for providing location information in indoor environments.