机构地区: 广州大学
出 处: 《计算机应用研究》 2004年第12期166-167,共2页
摘 要: 视频数据中的文本能提供重要的语义信息。针对视频中的文本检测问题,提出了用基于边缘信息和LH的方法检测视频帧文本所在的位置,方法简单,能快速地定位文本区域,且不受文本颜色、语种、文本字体大小的限制。检测和分割效果良好。 Text in video can provide an important supplemental source of index semantic information. In this paper, a segmentation algorithm based on edge information and LH for segmenting text from video frames is presented. This algorithm consists of several steps: edge intensity detection, edge density detection, convex detection based LH, post-processing and text locating. Experiments show that the proposed algorithm can detect text region simply and effectively.
领 域: [自动化与计算机技术] [自动化与计算机技术]