DETECTING TEXT IN VIDEO FRAMES

摘要

In this paper we propose an edge-based algorithm for artificial text detection in video frames. First, an edge map is created using the Canny edge detector. Then, morphological filtering is used, based on geometrical constraints, in order to connect the vertical edges and discard false alarms. A connected component analysis is performed to the filtered edge map in order to determine a bounding box for every candidate text area. Finally, horizontal and vertical projections are calculated on the edge map of every box and a threshold is applied, refining the result and splitting text areas in text lines. The whole algorithm is applied in multiresolution fashion to ensure text detection with size variability. Experimental results prove that the method is highly effective and efficient for artificial text detection.