Keyframe-based video mosaicing for historical Ottoman documents

:Image mosaicing is a trendy research area in computer vision in recent years. Instead of images, video frames can be mosaiced to form a larger aggregate. In both cases, merging computations generally depend on the common parts in consecutive images, which are called overlapping regions. The presence of mobile devices with a camera provides higher image and video acquisition; hence video mosaicing techniques can be utilized to digitize and to create high resolution historical document images for later use in browsing and retrieval systems. Here, we present a technique to create high resolution images of historical Ottoman documents from video. The video captures the frames while tracing the document in row major ordering. In the preprocessing steps, the frames are oriented automatically by the help of tracking the optical flow, and the keyframes are selected such that a sufficient overlapping region in between is guaranteed. Then the scanning phase traces these keyframes in horizontal and vertical manner to create the final video mosaic image in higher resolution. Both horizontal and vertical scan operations utilize a distance vector to compute similarity between two adjacent images. The effectiveness of the video mosaicing approach for historical Ottoman documents is evaluated, and the results of the experiments show that the approach is expressive yet effective to create high resolution Ottoman images.

PDF

___

[1] Szielski R. Video mosaics for virtual environments. IEEE Comput Graph 1996; 16: 22-30.
[2] Doermann D, Liang J, Li H. Progress in camera-based document image analysis. In: 2003 International Conference on Document Analysis and Recognition; 36 August 2003; Edinburgh, Scotland, UK: IEEE. pp. 606-617.
[3] Abraham R, Simon P. Review on mosaicing techniques in image processing. In: 2013 International Conference on Advanced Computing and Communication Technologies; 67 April 2013; Rohtak, India: IEEE. pp. 63-68.
[4] Rav-Acha A, Pritch Y, Lischinski D, Peleg S. Dynamosaicing: mosaicing of dynamic scenes. IEEE T Pattern Anal 2007; 29: 1789-1801.
[5] Kim DW, Hong KS. Real-time mosaic using sequential graph. J Electron Imaging 2006; 15: 1-13.
[6] Yalnız ˙IZ, Altıng¨ovde ˙IS, G¨ud¨ukbay U, Ulusoy O. Ottoman archives explorer: A retrieval system for digital ottoman ¨ archives. ACM J Comput Cult Herit 2009; 2: 1-20.
[7] S¸aykol E, Sinop AK, G¨ud¨ukbay U, Ulusoy O, C¸ etin E. Content-based retrieval of historical Ottoman documents ¨ stored as textual images. IEEE T Image Process 2004; 13: 314-325.
[8] Nakao T, Kashitani A, Kaneyoshi A. Scanning a document with a small camera attached to a mouse. In: IEEE 1998 Workshop on Applications of Computer Vision; 1921 October 1998; New Jersey, USA: IEEE. pp. 63-68.
[9] Whichello AP, Yan H. Document image mosaicing. In: 1998 International Conference on Pattern Recognition; 1620 August 1998; Brisbane, Australia: IEEE. pp. 1081-1083.
[10] Lucas BD, Kanade T. An iterative image registration technique with an application to stereo vision. In: 1981 International Joint Conference on Artificial Intelligence; Vancouver, Canada: William Kaufmann. pp. 674-679.
[11] Shi J, Tomasi C. Good features to track. In: IEEE 1994 Conference on Computer Vision and Pattern Recognition; 2123 June 1994; Seattle, WA, USA: IEEE. pp. 593-600.
[12] S¸aykol E, G¨ud¨ukbay U, Ulusoy O. A histogram-based approach for object-based query-by-shape-and-color in ¨ multimedia databases. Image Vision Comput 2005; 23: 1170-1180.
[13] Zappala AR, Gee AH, Taylor MJ. Document mosaicing. Image Vision Comput 1999; 17: 585-595.
[14] Shivakumara P, Kumar GH, Guru DS, Nagabhushan P. Sliding window based approach for document image mosaicing. Image Vision Comput 2006; 24: 94-100.
[15] Marzotto R, Fusiello A, Murino V. High resolution video mosaicing with global alignment. In: IEEE 2004 Conference on Computer Vision and Pattern Recognition; 27 June2 July 2004; Washington, DC, USA: IEEE. pp. 692-698.
[16] Ligang M, Yongjuan Y. Automatic document image mosaicing algorithm with hand-held camera. In: 2011 International Conference on Intelligent Control and Information Processing, 2528 July 2011; Harbin, China: IEEE. pp. 1094-1097.
[17] Liang J, DeMenthon D, Doermann D. Camera-based document image mosaicing. In: 2006 International Conference on Pattern Recognition; 2024 August 2006; Hong Kong: IEEE. pp. 476-479.
[18] Liang J, DeMenthon D, Doermann D. Mosaicing of camera-captured document images. Comput Vis Image Und 2009; 113: 572-579.
[19] Kasar T, Ramakrishnan AG. CCD: Connected component descriptor for robust mosaicing of camera-captured document images. In: IAPR 2008 International Workshop on Document Analysis Systems; 1619 September 2008; Nara, Japan: IAPR. pp. 480-486.
[20] Hannuksela J, Sangi P, Heikkila J, Liu X, Doermann D. Document image mosaicing with mobile phones. In: 2007 International Conference on Image Analysis and Processing; 1014 September 2007; Modena, Italy: IEEE. pp. 575-582.