Face Recognition: Challenges and Issues in Smart City/Environments

Abstract

Smart city challenges, like increased traffic, risk to public safety, effective law enforcement and the smart environment challenges on improving personalized services such as health care and home environment need person identification. Face recognition has proved to be useful and amicable bio-metric for smart city and smart environment challenges. In this paper, we review the use cases pertaining to smart city and smart environment leading to use case specific requirements on Face recognition. We describe the open challenges in anti-spoofing and standardization to make face recognition a fool proof system. For applications with demand for low power, we show that with proper considerations on training data, cost function, and model architecture we could build a low-complex CNN model with reasonable accuracy (91.4% on LFW data set).