Text Segmentation Approach Based on Recursive Particle Filter

In order to solving segment text accurately and robustly from a video sequences. This paper presents a new approach for text segmentation in video sequences by using recursive particle filter. This approach presents a probabilistic algorithm for segmenting text in video sequences based on adaptive thresholding using a Bayes filtering method. First, we describe adaptive mixture model for video text segmentation. Second, the Bayesian filtering is implemented by a recursive particle filter. Finally, we output the text string that corresponds to the segmentation with the highest data likelihood. The proposed algorithm is compared with other algorithms. The experimental results demonstrate that the proposed algorithm obtained satisfactory results.