Graph-based approach to scene text localisation and tracking in videos

摘要

A text localisation and tracking method is presented that finds text-regions in videos and assigns unique IDs to their trajectories. For the goal, a graph-based framework that can work with existing text detection methods is developed. To be precise, graphs are built where vertices are image-level text detection results and edges represent the correspondence scores of the vertices. From these graphs, text-region trajectories by using the graph-cut algorithm are extracted. This approach allows considering false positives and misses, as well as their patch-based tracking results at the same time, and text trajectories are reliably extracted. Finally, the results are refined by interpolating misses and filtering out false positives. The proposed method is submitted to the International Conference on Document Analysis and Recognition 2015 robust reading competition (video text localisation) and the method showed the best performance in terms of CLEAR MOT metrics and was ranked third place according to VACE metrics among the seven participating methods.