Lyric Video Analysis Using Text Detection and Tracking

TL;DR

This paper presents a method for recognizing and tracking lyric words in lyric videos by applying scene text detection, matching, and trajectory analysis to facilitate automatic lyric video generation.

Contribution

It introduces a novel approach combining text detection, frame matching, and trajectory clustering to analyze lyric word motion in videos.

Findings

Effective tracking of lyric words despite distortions and movements

Successful clustering of lyric word trajectories

Foundation for automatic lyric video generation

Abstract

We attempt to recognize and track lyric words in lyric videos. Lyric video is a music video showing the lyric words of a song. The main characteristic of lyric videos is that the lyric words are shown at frames synchronously with the music. The difficulty of recognizing and tracking the lyric words is that (1) the words are often decorated and geometrically distorted and (2) the words move arbitrarily and drastically in the video frame. The purpose of this paper is to analyze the motion of the lyric words in lyric videos, as the first step of automatic lyric video generation. In order to analyze the motion of lyric words, we first apply a state-of-the-art scene text detector and recognizer to each video frame. Then, lyric-frame matching is performed to establish the optimal correspondence between lyric words and the frames. After fixing the motion trajectories of individual lyric words from correspondence, we analyze the trajectories of the lyric words by k-medoids clustering and dynamic time warping (DTW).