CASIA OpenIR  > 智能制造技术与系统研究中心  > 多维数据分析
Perspective rectification of document images based on morphology
Ligang Miao; Silong Peng; Liang Miao
2007
Conference Name2006 International Conference on Computational Intelligence and Security ICCIAS 2006
Pagespp 1805-1808
Conference Date2006/10/3-2006/10/6
Conference Place中国Guangzhou China
AbstractDocuments may suffer from perspective distortion when captured with hand-held digital cameras. A morphology based rectification method is proposed to recoverfronto-parallel views ofperspectively distorted documents images. Firstly we extend the nearestneighbor (NN) clustering technique in document skew rectification to locate the horizontal vanishing point of the text plane. Secondly we partition the image into multiple overlapping blocks centered with the centroid ofeach connected component (CC) andpropose a runlength opening algorithm (RLOA) to compute the local orientation o vertical character stroke (VSB) which is used to locate the document's vertical vanishing point. Finally a three-step hierarchical rectification method is proposed to rectify the distorted images. Experiment results on various types of documents show that the proposed rectification method has achieved accurate recovery ofdocument images.
Keyword
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12887
Collection智能制造技术与系统研究中心_多维数据分析
Corresponding AuthorLiang Miao
Recommended Citation
GB/T 7714
Ligang Miao,Silong Peng,Liang Miao. Perspective rectification of document images based on morphology[C],2007:pp 1805-1808.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ligang Miao]'s Articles
[Silong Peng]'s Articles
[Liang Miao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ligang Miao]'s Articles
[Silong Peng]'s Articles
[Liang Miao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ligang Miao]'s Articles
[Silong Peng]'s Articles
[Liang Miao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.