A Novel Approach to End-to-End Facial Recognition Framework with Virtual Search Engine ElasticSearch

Facial recognition has been one of the most intriguing, interesting research topics over years. It involves some specific face-based algorithms such as facial detection, facial alignment, facial representation, and facial recognition as well; however, all of these algorithms are derived from heavy deep learning architectures, which leads to limitations on development, scalability, flawed accuracy, and deployment into publicity with mere CPU servers. It also requires large datasets containing hundreds of thousands of records for training purposes. In this paper, we propose a full pipeline for an effective face recognition application which only uses a small Vietnamese-celebrity datasets and CPU for training that can solve the leakage of data and the need for GPU devices. It is based on a face vector-to-string tokens algorithm then saves face's properties into Elasticsearch for future retrieval, so the problem of online learning in Facial Recognition is also tackled. In comparison with another popular algorithms on the dataset, our proposed pipeline achieves not only higher accuracy, but also faster inference time for real-time face recognition applications.