Wet Face Recognition in Uncontrolled Scenario

摘要: Research in face recognition has been much advanced addressing several factors including pose, illumination and expression variations, facial occlusions etc. However, the adverse weather conditions such as higher humidity, unexpected rain, snow fall fog have a greater impact on performance of an autonomous automated access control system. Therefore, we propose to work wet recognition. In this work, wet-face based intelligent controlled system is studied. An effective approach proposed for same. Extensive experiments demonstrate effectiveness method eliminating from face. Specially, accuracy impressive achieves 95.72% 97.23% with single two authentication respectively.