[1]杨浩,安国成,陈向东,等.一种基于实例的文本图像超分辨率重建算法[J].东南大学学报(自然科学版),2008,38(2):191-194.[doi:10.3969/j.issn.1001-0505.2008.02.001]
　Yang Hao,An Guocheng,Chen Xiangdong,et al.Algorithm for document image super-resolution reconstruction based on examples[J].Journal of Southeast University (Natural Science Edition),2008,38(2):191-194.[doi:10.3969/j.issn.1001-0505.2008.02.001]
点击复制

一种基于实例的文本图像超分辨率重建算法()
分享到：

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
38
期数:
2008年第2期
页码:
191-194
栏目:
信息与通信工程
出版日期:
2008-03-20

文章信息/Info

Title:
Algorithm for document image super-resolution reconstruction based on examples
作者:
杨浩1;  安国成1;  陈向东2;  吴镇扬1
1 东南大学信息科学与工程学院, 南京 210096; 2 黄淮学院信息工程系, 驻马店 463000
Author(s):
Yang Hao1;  An Guocheng1;  Chen Xiangdong2;  Wu Zhenyang1
1 School of Information Science and Engineering, Southeast University, Nanjing 210096, China
2 Department of Information Engineering, Huanghuai University, Zhumadian 463000, China
关键词:
图像超分辨率;  基于实例;  图像库
Keywords:
image super-resolution reconstruction;  example-based;  image database
分类号:
TN911.73
DOI:
10.3969/j.issn.1001-0505.2008.02.001
摘要:
为了从一幅包含文字、公式和图形等内容的低分辨率文本图像重建高分辨率图像,提出了一种获取重建图像先验知识的新方法.利用实例图像和图像降质模型建立图像库,图像重建时,将低分辨率观测图像分成若干子块,每个子块分别从图像库中找到一块最佳匹配的高分辨率实例图像块,将这些实例图像块依次拼成一幅大图,并把该大图各点的灰度值作为重建图像各点灰度值的均值,以此先验知识采用最大后验概率(MAP)准则估计出高分辨率文本图像.实验结果表明本文的方法能够取得较好的重建效果.
Abstract:
In order to produce a high-resolution image from a low-resolution document image containing characters, equations and graphics, a new method to obtain the prior knowledge of the high-resolution image is proposed. Image examples and degradation model are used to generate example image database. A high-quality patch is assigned to each block in the observed low-resolution image, whose corresponding low-quality patch is found as the nearest neighbor in the image database. These high-quality patches are mosaicked to produce an enlarged image whose pixel intensities are taken as the mean values of the pixel intensities of the desired high-resolution image. A maximum a posteriori(MAP)estimator is used to estimate the high-resolution image. Experimental results show that the new method improves the reconstruction results significantly.

参考文献/References:

[1] Park S C,Park M K,Kang M G.Super-resolution image reconstruction:a technique overview [J]. IEEE Signal Processing Magazine,2003,20(3):21-36.
[2] Farsiu S,Robinson D,Elad M,et al.Advances and challenges in super-resolution [J]. International Journal of Imaging Systems and Technology,2004,14(2):47-57.
[3] Datsenko D,Elad M.Example-based single document image super-resolution:a global MAP approach with outlier rejection [J]. Multidimensional Systems and Signal Processing,2007,18(2/3):103-121.
[4] Freeman W T,Jones T R,Pasztor E C.Examples-based super-resolution [J]. IEEE Computer Graphics Applications,2002,22(2):56-65.
[5] Corduneau A,Platt J C.Learning spatially-variable filters for super-resolution of text [C] //IEEE International Conference on Image Processing.Genoa,Italy,2005:849-852.
[6] Pickup L C,Roberts S J,Zisserman A.A sampled texture prior for image super-resolution [J]. Advances in Neural Information Processing Systems,2004,16:1587-1594.
[7] Park J,Kwon Y,Kim J H.An example-based prior model for text image super-resolution [C] //Proceeding of the 2005 Eighth International Conference on Document Analysis and Recognition.Seoul,Korea,2005:374-378.
[8] Nene A S,Nayar S K.A simple algorithm for nearest neighbor search in high dimensions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(9):989-1003.
[9] Capel D,Zisserman A.Super-resolution from multiple views using learnt image models [C] //Proceeding of International Conference Computer Vision Pattern Recognition.Santa Barbara,CA,1998:885-891.
[10] Baker S,Kanade T.Limits on super-resolution and how to break them [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002, 24(9):1167-1183.

备注/Memo

备注/Memo:
作者简介: 杨浩(1969—),男,博士生; 吴镇扬(联系人),男,教授,博士生导师,zhenyang@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(60672094).
引文格式: 杨浩,安国成,陈向东,等.一种基于实例的文本图像超分辨率重建算法[J].东南大学学报:自然科学版,2008,38(2):191-194.
更新日期/Last Update: 2008-03-20