Applicability of Face Recognition in Real-World Scenarios

Abstract

Face recognition has become one of the most popular computer technologies in the last ten years, backed by deep convolutional neural networks. It exploits its wide application in various commercial fields. Face recognition technology is relatively mature nowadays. Scientists and engineers have already implemented the necessary functions like face detection, landmarks extraction, and face identification. This paper will depict the necessary steps of those functions, and some popular face recognition libraries will also be introduced in Chapter 3. The paper aims to discuss the parameter settings of the open-source library face_recognition under real-world scenarios with distinct requirements and limitations. Finally, the paper will also go into two cases to analyze the influence of specific parameters and discuss some appropriate settings under different situations.