关键词: 维吾尔文, 边缘检测, 模糊C均值聚类, 文本基线

Abstract: This paper proposes a specific method for localization and validation of Uyghur text in video frames according to the characteristics of Uyghur font. This method gets four edge maps separately in horizontal, vertical, up-right and up-left direction by using the RGB color edge detection operator, then the improved fuzzy C-means clustering algorithm is applied to detect candidate text regions according to the weighed edge map, the false text regions are removed under the heuristic rules of true text regions. The characteristic of the Uyghur text baseline is used to check whether the detected text regions are true Uyghur text regions or not. The experimental results show that the proposed method achieves good effects in the Uyghur video images both in simple background and complex background.

Key words: Uyghur, edge detection, fuzzy C means clustering, text baseline