Document reconstruction and recognition from an image sequence

A new method for reconstructing a document from an image sequence and recognizing contents of the document is described. In this method frame images in the image sequence are acquired as partial sub-images by a moving camera. The reconstruction includes a rather expensive registration process. To make its use practical, the proposed method registers sub-images hierarchically by sub-tree matching of the layout structure. Images of a corresponding character pair are piled using sub-pixel precision displacement and interpolated to restore image quality and resolution. The proposed method increased the character recognition rate by 6.8 points to 93.1% when resolution was 133 dpi. The computational cost was reduced to 1/23 that of registration by conventional matching.

[1]  Kiyoharu Aizawa,et al.  Two approaches for image-processing based high resolution image acquisition , 1994, Proceedings of 1st International Conference on Image Processing.

[2]  R. Oka,et al.  Spotting Recognition of Human Gestures from Motion Images , 1994 .

[3]  Ales Leonardis,et al.  Robust stereo on multiple resolutions , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[4]  Kristin J. Dana,et al.  Real-time scene stabilization and mosaic construction , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[5]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[6]  Josiane Zerubia,et al.  Subpixel image registration by estimating the polyphase decomposition of cross power spectrum , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  R. Oka,et al.  Recognition of dexterous manipulations from time-varying images , 1994, Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects.

[8]  Lawrence O'Gorman,et al.  Subpixel Precision of Straight-Edged Shapes for Registration and Measurement , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Stanley M. Dunn,et al.  An efficient registration and recognition algorithm via sieve processes , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[10]  Yoshitake Tsuji.  Document image analysis for generating syntactic structure description , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[11]  H. Bunke,et al.  3-D Object Recognition Based on Subgraph Matching in Polynomial Time , 1990 .