The text of the video can provide important information for video description and retrieval. First,the paper adopts Maximum Gradient algorithm which is based on the Sobel Gradient operator to detect the edge of the text. Second, with regards to the rich information of the edge of text, variance projection is employed to detect text zones and to filtrate false text zones by calculating the Regional Density. Finally, Image Morphology is employed to treat the edge of the text. It is to get position and color information of pixels of original image and extract text from complex background. A large number of experiments to prove that the algorithm is very effective.