| 基于过渡像素的视频图像文本检测与定位 |
| |
| 引用本文： | 杨高波,吴潇,张兆扬,朱宁波.基于过渡像素的视频图像文本检测与定位[J].湖南农业大学学报(自然科学版),2011,38(6):69-74. |
| |
| 作者姓名： | 杨高波 吴潇 张兆扬 朱宁波 |
| |
| 作者单位： | (1.湖南大学 信息科学与工程学院，湖南 长沙410082；2.上海大学 新型显示技术及应用集成教育部重点实验室，上海200072) |
| |
| 摘 要： | 提出一种基于过渡像素的视频流人工文本检测与定位算法.该算法在水平和垂直方向上提取过渡像素点，生成过渡图.通过块滤波器抑制背景的过渡像素，采用基于密度的快速区域生长算法形成候选文本区域；再利用改进的局部二进制模型(LBP)验证候选文本区.仿真实验结果表明，本文的改进算法相对于Kim算法，字符定位的准确率更高.
|
| 关 键 词： | 文本处理 视频流 视频文本检测 过渡图 区域生长 局部二进制模型 |
A Transition Pixels Based Text Detection and Localization for Video Images |
| |
| YANG Gao-bo,WU Xiao,ZHANG Zhao-yang,ZHU Ning-bo.A Transition Pixels Based Text Detection and Localization for Video Images[J].Journal of Hunan Agricultural University,2011,38(6):69-74. |
| |
| Authors: | YANG Gao-bo WU Xiao ZHANG Zhao-yang ZHU Ning-bo |
| |
| Abstract: | A transition pixel based detection and localization algorithm was proposed for the artificial texts in the video frame.The transition map was generated by extracting transition pixels in both horizontal and vertical directions.The transition pixels in the background were suppressed by block filtering, and candidate text regions were obtained by intensity based region growing.Finally, the candidate text regions were verified by improved local binary pattern (LBP).Experiment results have shown that, compared with Kim''s work, the proposed approach can achieve more accurate text detection and localization. |
| |
| Keywords: | |
|
| 点击此处可从《湖南农业大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《湖南农业大学学报(自然科学版)》下载全文 |
