Abstract: The present invention relates to a method and system for performing video-based automatic identity verification. The method at least comprises: generating prompt(s); capturing, a video that comprises the first user speaking the prompt(s); capturing an image of an identification document comprising an image of a second user; detecting a correctness of a speech in the video based on a deepfake detection score, a visual cues match, and a transcription match; detecting in one or more frames of the video, the first human object based on the correctness of the speech and in the image of the identification document, the second human object; generating a first similarity score, and a second similarity score, based on the detection of the first human object and second human object; and performing the identity verification of the first user, based on the first similarity score, and the second similarity score.

Abstract: The present invention relates to a method and system for performing video-based automatic identity verification. The method at least comprises: generating prompt(s); capturing, a video that comprises the first user speaking the prompt(s); capturing an image of an identification document comprising an image of a second user;, detecting a correctness of a speech in the video based on a deepfake detection score, a visual cues match, and a transcription match; detecting in one or more frames of the video, the first human object based on the correctness of the speech and in the image of the identification document, the second human object; generating a first similarity score, and a second similarity score, based on the detection of the first human object and second human object; and performing the identity verification of the first user, based on the first similarity score, and the second similarity score.