Research on born-digital image text extraction based on conditional random field

Research on born-digital image text extraction based on conditional random field
复制标题

基于条件随机场的原生数字图像文本提取研究

DOI:
10.1504/ijhpsa.2014.059873
复制
发表时间:
2014-03
期刊:
Int. J. High Performance Systems Architecture
影响因子:
--
通讯作者:
Hong Zhao
Hong Zhao
中科院分区:
其他
文献类型:
--
作者:
Jian Zhang;Renhong Cheng;Kai Wang;Hong Zhao

文献摘要

参考文献

相似文献

随着电子邮件和网页中数字视频和数字图像的数量急剧增加,从图像中提取文本变得比以往任何时候都更加重要。数字图像是由计算机直接生成的,图像中的文字对于图像的语义理解具有重要意义。虽然在过去的几年里已经提出了许多从自然场景图像中提取文本的方法,但是从出生的数字图像中检测和提取文本仍然是一个挑战。提出了一种从数字图像中分割文本连通分量CCS的新方法。首先,基于小波理论对给定的图像进行二值化,得到所有候选文本CCS。其次,基于自然语言处理中广泛使用的概率图模型--条件随机场CRF,对抽取的CCS进行分类来标注文本CCS。实验结果表明,该方法能有效地从生成的数字图像中提取文本。
With the number of digital videos and digital images increasing tremendously in e-mails and web pages, text extraction from images becomes important more than ever. Born-digital images are generated directly with the computer and the text in the images is important to help the semantic understanding of the images. Although there are many methods proposed over the past years for text extraction from natural scene images, the text detection and extraction from born-digital images remains a challenge. This paper proposes a novel method to segment the text connected components CCs from a born-digital image. Firstly, binarisation is conducted on the given image to get all candidate text CCs based on wavelet theory. Secondly, classification is conducted on the extracted CCs to label text CCs based on conditional random field CRF - a probabilistic graph model that has been widely used in natural language processing. Experimental results show that the proposed method can effectively extract text from the born-digital images.
DOI: 10.1109/icip.2007.4378890
发表时间: 2007-11
期刊: 2007 IEEE International Conference on Image Processing
影响因子: --
作者:
Farhad Faradji;A. Rezaie;M. Ziaratban
通讯作者: Farhad Faradji;A. Rezaie;M. Ziaratban
DOI: 10.1109/cvpr.2010.5540072
发表时间: 2010-06
期刊: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
M. P. Kumar;D. Koller
通讯作者: M. P. Kumar;D. Koller
DOI: 10.1109/tmm.2007.898913
发表时间: 2007-08
期刊: IEEE Trans. Multim.
影响因子: --
作者:
M. Worring;G. Schreiber
通讯作者: M. Worring;G. Schreiber
DOI: 10.1109/icdar.2011.148
发表时间: 2011-09
期刊: 2011 International Conference on Document Analysis and Recognition
影响因子: --
作者:
Hongwei Zhang;Changsong Liu;Cheng Yang;Xiaoqing Ding;Kongqiao Wang
通讯作者: Hongwei Zhang;Changsong Liu;Cheng Yang;Xiaoqing Ding;Kongqiao Wang
DOI: 10.1109/icdar.2011.208
发表时间: 2011-09
期刊: 2011 International Conference on Document Analysis and Recognition
影响因子: --
作者:
Xujun Peng;Huaigu Cao;R. Prasad;P. Natarajan
通讯作者: Xujun Peng;Huaigu Cao;R. Prasad;P. Natarajan