Text Extraction from Video Using Conditional Random Fields
Text Extraction from Video Using Conditional Random Fields
复制标题
DOI：
10.1109/icdar.2011.208
复制
发表时间：
2011-09
期刊：
影响因子：
--
通讯作者：
Xujun Peng;Huaigu Cao;R. Prasad;P. Natarajan
中科院分区：
文献类型：
--
作者：
Xujun Peng;Huaigu Cao;R. Prasad;P. Natarajan
在本文中，我们描述了一种方法，从广播视频中提取文本。根据边缘提取结果检测候选块。角和几何特征用于初始分类的目的，这是通过使用支持向量机（SVM）进行。考虑到图像中不同区域的空间相关性，我们提出了一种新的基于条件随机场（CRF）的框架，该框架将SVM的输出集成到系统中，以提高块标记的准确性。实验结果表明，该系统实现了可靠的性能，从视频文本检测/提取。
In this paper, we describe an approach to extract text from broadcast videos. Candidate blocks are detected based on edge extraction results. Corners and geometrical features are used for the purpose of initial classification which is carried out by using a support vector machine (SVM). Considering the spatial inter-dependencies of different regions in the image, we propose a novel conditional random field (CRF) based framework which integrates the outputs of SVM into the system to improve the accuracy of labeling for blocks. The experimental results show that the proposed system achieves reliable performance for text detection/extraction from videos.