Face detection method using voice

A face detection method, which is performed by a server associated with a user terminal, comprising:

• receiving video data and voice data from the user terminal;
• deriving a first interval related to a predetermined first message based on the received voice data;
• configuring a second interval based on the derived first interval, wherein the second interval is located after the first interval in time series within the voice data;
• extracting a part of the video data corresponding to the second interval;
• deriving a video frame which satisfies a predetermined criterion from the extracted video data based on the second interval;
• and
• detecting a facial image included in each of the derived video frame based on the second interval,
• wherein the predetermined first message comprises a message for guiding a user to align a face toward a front of a camera unit included in the user terminal,
• wherein a start point of the second interval is set based on an end point of the derived first interval,
• wherein an end point of the second interval is set to a point where a predetermined second message different from the predetermined first message is outputted,
• wherein the predetermined first message and the predetermined second message are outputted to the user terminal in a form of the voice data under control of the server,
• wherein respective output time points of the first message and the second message outputted in the form of the voice data are used in a process of selecting a time boundary in which the facial image is to be detected from the video data, and
• wherein the extracting the part of the video data comprises detecting the facial image not in the first interval corresponding to the first message, but in the second interval defined from an end point of the first interval to a point where the second message is outputted.