Abstract: Video text information plays an important role in semantio-based video analysis, indexing and retrieval. The grade of gray in the video text and background is different,so an approach to video text localization using gradient disCrete cosines transform(DCT) was proposed. Firstly, the video frame is divided into N X N macro-blocks, and we can get the DCT coefficients from every macro-block. Then the gradient operator value considered as block intensity is calculated and we deal with it by using of smooth filter and morphology processing. Lastly, the horizontal and vertical projection can be obtained, the number of text line can be got and the text region is marked with text box hhe experimental results show that the proposed method is efficient on the localization of the static and rolling video text, especially the accuracy and integrality of character localization with the less strokes.

Key words: Next localization, Video frame, Gradient