FACIAL RECOGNITION METHOD USING VOICE

Abstract

The invention relates to a method of voice-based face recognition. The voice-based face recognition method includes: receiving video and voice data from a user terminal; outputting the first time interval related to a predefined message based on the received voice data; configuring a second time interval based on the first output; extracting a portion of video data corresponding to the second time interval; outputting at least one video frame satisfying a predefined criterion from the extracted video data; and identifying the face image present in each of at least one of the output video frames.