In the last decade, advancement in Artificial Intelligence attracted a lot of experts that lead to massive growth and advancement in all human life aspects. Therefore, one of the key fields to point at, which attracted a lot of attention and development lately, is Face Recognition. In recent years, Face Recognition tends to be one of the most widely used technologies in many different domains and workspaces, such as emotional recognition, security, health sector, marketing, and retail, etc. this approach will consist of an online system with real-time functionality (close to real-time), that will be responsible for the declaration of users to be recognized later. Based on the recognition results, the system will then grant the users the needed authentication. In this research, various different challenges related to the development and the use of Face Recognition, including the variations in light conditions, camera resolution, processing power, facial changes over time, number of users to be recognized, etc... During this work, “Viola and Jones” and “MTCNN” were used for face detection, and “FaceNet” was applied for facial features extraction. Also, similarity neural network (Similarity Net) has been created to regress similarity percent between user's features' vectors, beside it has been trained on user's features by exploiting the Euclidian distance between embeddings. This approach was tested on a group of datasets - personal, Kaggle and LFW dataset. The tests returned 100% successful recognitions on personal and Kaggle dataset, and 99.5% on LFW dataset.