S. A. SantoshKumar
B. K. ShreyamshaKumar
ABSTRACT
The paper proposes a new algorithm for reconstruction of torn document ripped-up by hand using a unique feature, Edge Envelope. The essence of the paper is to match the edges using high curvature points and edge variations as human visual system does while reconstructing the document. Moreover the ambiguity created during the matching of edges due to shearing can be overcome by smoothing the edge envelopes using a filter. Further, a newly defined parameter Normalized Edge Envelope Difference can be used as an effective quantitative measure for matching the edges of torn pieces, which exploits property of human visual system. The effectiveness of the algorithm is demonstrated through preliminary results by taking limited amount of torn pieces.
- A. Biswas, P. Bhowmick and B. B. Bhattacharya, "Reconstruction of Torn Documents using Contour Maps", Proceedings of International Conference on Image Processing (ICIP-05), Vol. 3, pp. 517--520, 2005.Google Scholar
Cross Ref
- R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addison-Wesley Publishing Company, 1993. Google ScholarDigital Library
- C. Harris and M. Stephens, "A Combined Corner and Edge Detector", In Proceedings of the Fourth Alvey Vision Conference, pp. 147--151, 1988.Google ScholarCross Ref
- E. Justino, L. S. Oliveira and C. Freitas, "Reconstructing Shredded Documents through Feature Matching", Forensic Science International, 160, pp. 140--147, 2006.Google ScholarCross Ref
- S. Loncaric, "A Survey of Shape Analysis Techniques", Pattern Recognition, Vol. 31, No. 8, pp. 983--1001, 1998.Google Scholar
- M. Prandtstetter, "Hybrid Optimization Methods for Warehouse Logistics and the Reconstruction of Destroyed Paper Documents", PhD Thesis, 2009.Google Scholar
- P. L. Rosin and G. A. W. West, "Non-Parametric Segmentation of Curves into Various Representations", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 12, pp. 1140--1153, Dec 1995. Google ScholarDigital Library
- P. D. Smet, "Reconstruction of Ripped-up Documents using Fragment Stack Analysis Procedures", Forensic Science International, 176(2), pp. 124--136, Apr 2008.Google ScholarCross Ref
- S. M. Smith and J. M. Brady, "SUSAN - A New Approach to Low Level Image Processing", International Journal of Computer Vision, Vol. 23, No. 1, pp. 45--78, May 1997. Google ScholarDigital Library
- C. Solana, E. Justino, L. S. Oliveira and F. Bortolozzi, "Document Reconstruction based on Feature Matching", Proceedings of 18th Brazilian Symposium on Computer Graphics and Image Processing, pp. 163--170, 2005. Google ScholarDigital Library
- M. -.J. J. Wang, W. -Y. Wu, L. -K. Huang and D. -M. Wang, "Corner Detection using Bending Value", Pattern Recognition Letters, Vol. 16, pp. 575--583, Jun 1995. Google ScholarDigital Library
- H. Wolfson, A. Kalvin, E. Schonberg, and Y. Lambdan, "Solving Jigsaw Puzzles by Computer", Annals of Operations Research, Vol. 12, pp. 51--64, 1988. Google ScholarDigital Library
- F. -H. Yao, G.-F Shao, "A Shape and Image Merging Technique to Solve Jigsaw Puzzles", Pattern Recognition Letters, Vol. 24, No. 12, pp. 1819--1835, 2003. Google ScholarDigital Library
- L. Zhu, Z. Zhou and D. Hu, "Globally Consistent Reconstruction of Ripped-Up Documents", IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 30, No. 1, pp. 1--13, Jan 2008. Google ScholarDigital Library
Index Terms
- Edge envelope based reconstruction of torn document
Recommendations
Edge connection based Canny edge detection algorithm
Double threshold method of traditional Canny operator detects the edge rely on the information of gradient magnitude, which has a lower edge connectivity and incomplete image information. Aiming at this problem, we proposed an edge detection algorithm ...
Regularized Super-Resolution Reconstruction Based on Edge Prior
Intelligent Computing MethodologiesAbstractConsidering that there is no edge constraint in general regularized algorithms, an improved super-resolution algorithm with additional regularization is presented. The Difference Curvature (DC) regularization which containing the image edge ...
Torn Document Analysis as a Prerequisite for Reconstruction
VSMM '09: Proceedings of the 2009 15th International Conference on Virtual Systems and MultimediaAn automated assembling of torn documents (2D) will support philologists, archaeologists and forensic experts. Especially if the amount of fragments is large (up to 1000), a human puzzle solver will not be feasible due to cost and time. Ancient ...
Comments