一个视频文本检测和识别系统.pdf

A VIDEO TEXT DETECTION AND RECOGNITION SYSTEM Jie X i 1, X ian-Sheng Hua 2, X iang-Rong Chen 3, Liu Weny in 3, Hong-Jiang Zhang 3 1 Department of Computer Science 2 National Lab. on Machine Perception 3 Microsoft Research China Fudan University, Shanghai 200433, China Peking University, Beij ing 100871, China 49 Zhichun Road, Beij ing 100080, China j iexi@ xshua@ {xrchen; wyliu; hj zhang}@ ABSTRACT Experimental results and a summary are presented in Section 5 and Section 6 respectively In this paper, we propose a new system for text information extraction from news videos. First of all, a method that integrates text detecting and text tracking is developed to locate text areas in the key-frames (images), together with a scheme to evaluate Text Detection Integration of the performance of this approach. To get better recognition Detection results, we then enhance the quality of the detected text blocks by Text Tracking And Tracking multi-frame averaging. Finally, we use an adaptive thresholding method to binarize the text blocks and recognize the text using an off-the-shelf OCR module. The detection and recognition rate of Multi-frame Averageing the proposed system are 94.7% and 67.5% respectively.