Mosaicing of camera-captured document images

被引:10
作者
Liang, Jian [1 ]
DeMenthon, Daniel [2 ]
Doermann, David [2 ]
机构
[1] Amazon Com, Seattle, WA 98104 USA
[2] Univ Maryland, College Pk, MD 20742 USA
关键词
Camera-based document analysis; Image mosaicing; Image registration;
D O I
10.1016/j.cviu.2008.12.004
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we present a method for composing document mosaics from camera-captured images. We decompose the complexity of solving the 8-dof transformation between image pairs into two problems, that is, rectification and registration. This is achievable under a key assumption that sufficient text content forms orthogonal texture flows on the document surface. First, perspective distortion and rotation are removed from images using the texture flow information. Next, the translation and scaling are resolved by a Hough transform-like voting method. In the image composition part, Our contribution is a sharpness based selection process which composes a seamless and blur free mosaic for text content. Experiments show that our approach can produce an accurate, sharp, and high resolution mosaic of a full document page from small image patches Captured by a camera with various zooms and poses. (C) 2008 Elsevier Inc. All rights reserved.
引用
收藏
页码:572 / 579
页数:8
相关论文
共 15 条
  • [1] A MULTIRESOLUTION SPLINE WITH APPLICATION TO IMAGE MOSAICS
    BURT, PJ
    ADELSON, EH
    [J]. ACM TRANSACTIONS ON GRAPHICS, 1983, 2 (04): : 217 - 236
  • [2] A graduated assignment algorithm for graph matching
    Gold, S
    Rangarajan, A
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1996, 18 (04) : 377 - 388
  • [3] A fast and robust image registration method based on an early consensus paradigm
    Isgrò, F
    Pilu, M
    [J]. PATTERN RECOGNITION LETTERS, 2004, 25 (08) : 943 - 954
  • [4] Ke Y, 2004, PROC CVPR IEEE, P506
  • [5] LIANG J, 2008, IEEE T PAMI, V30, P291
  • [6] LIANG J, 2006, P ICPR
  • [7] MIRMEHDI M, 2001, P 9 SPAN S PAT REC I, P43
  • [8] Nakai T, 2006, LECT NOTES COMPUT SC, V3872, P541
  • [9] Scanning a document with a small camera attached to a mouse
    Nakao, T
    Kashitani, A
    Kaneyoshi, A
    [J]. FOURTH IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION - WACV'98, PROCEEDINGS, 1998, : 63 - 68
  • [10] An FFT-based technique for translation, rotation, and scale-invariant image registration
    Reddy, BS
    Chatterji, BN
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 1996, 5 (08) : 1266 - 1271