A New Log Gabor Approach for Text Detection from Video

Abstract

Text information embedded in video frames play an important role in content-based multimedia indexing and retrieval, as a result the automatic detection of texts from videos has gained wide attention in recent years. However,large variations in size, color, orientation and background complexity makes video text detection and extraction a challenging problem. In this paper an effective method for text detection and localization approach based on Log Gabor filter and Block Eigen map analysis is proposed. Log Gabor filter response is used to identify candidate text regions and Block wise Eigen map analysis is used to classify pixels as true text pixels. Finally,a heuristic based on gray scale pixel co-occurrence to eliminate false positives from the frame is used. Experimental results show the promising overall performance of the proposed method against the best features reported in the literature for the standard databases.