An Earthenware Reconstruction System Considering Color Pattern and Shape Similarities

This paper proposes an earthenware reconstruction system considering surface color and pattern of potsherds, in addition to contour shape. In general, most of potsherds have complex, irregular, and weathering contours because of rain, wind and so on. Reconstruction of earthenware, therefore, is attended with much difficulties. In our previous work, a system considering surface patterns has been developed, but there is some problems, for the surface patterns are just analyzed in grayscale in the system. In this paper, we discuss a color similarity approach, and then, we propose a joint detection method based on the approach. We have implemented the method into our earthenware reconstruction system, and we also report good performance results for some weathered potsherds.

[1]  Georgios Papaioannou,et al.  Virtual Archaeologist: Assembling the Past , 2001, IEEE Computer Graphics and Applications.

[2]  Marshall W. Bern,et al.  A global approach to automatic solution of jigsaw puzzles , 2002, SCG '02.

[3]  Azriel Rosenfeld,et al.  Angle Detection on Digital Curves , 1973, IEEE Transactions on Computers.

[4]  K. Lai.  On Regularization , Formulation and Initialization of theActive Contour Models ( Snakes ) , 2007 .

[5]  Roland T. Chin,et al.  Deformable contours: modeling and extraction , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Tarak Gandhi,et al.  An automatic jigsaw puzzle solver , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[7]  Shohei Kato,et al.  Efficient Joint Detection Considering Complexity of Contours , 2000, PRICAI.

[8]  Tsukasa Ogasawara,et al.  Joint detection for potsherds of broken earthenware , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[9]  Horst Bunke,et al.  Jigsaw Puzzle Solving Using Approximate String Matching and Best-First Search , 1993, CAIP.

[10]  Alberto Del Bimbo,et al.  Visual information retrieval , 1999 .

[11]  Georgios Papaioannou,et al.  Reconstruction of Three-Dimensional Objects through Matching of Their Parts , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Shohei Kato,et al.  Earthenware Reconstruction Based on the Shape Similarity among Potsherds , 2001 .