A recovery system of broken relics using least squares fitting and vector similarity techniques

Authors:
Ho Seok Moon;Taewoo You;Hun Woo Yoo;Myung Ho Sohn;Dong Sik Jang
Affiliations:
Industrial Systems and Information Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul 136-701, South Korea;Business Administration, Myongji College, 356-1, Hongeun 3-Dong, Seodaemun-Ku, Seoul 120-776, South Korea;Center for Cognitive Science, Yonsei University, 134, Shinchon-Dong, Seodaemun-Ku, Seoul 120-749, South Korea;Business Administration, Myongji College, 356-1, Hongeun 3-Dong, Seodaemun-Ku, Seoul 120-776, South Korea;Industrial Systems and Information Engineering, Korea University, 1, 5-ka, Anam-Dong, Sungbuk-Ku, Seoul 136-701, South Korea
Venue:
Expert Systems with Applications: An International Journal
Year:
2005

Citing 6
Cited 0

Solving jigsaw puzzles by computer

Annals of Operations Research
On curve matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
Decimation of triangle meshes

SIGGRAPH '92 Proceedings of the 19th annual conference on Computer graphics and interactive techniques
A global approach to automatic solution of jigsaw puzzles

Proceedings of the eighteenth annual symposium on Computational geometry
Assembling virtual pots from 3D measurements of their fragments

Proceedings of the 2001 conference on Virtual reality, archeology, and cultural heritage
Toward a framework for assembling broken pottery vessels

Eighteenth national conference on Artificial intelligence

Quantified Score

Hi-index	12.05

Visualization

Abstract

We propose a new system for recovering the broken fragments of relics into an original form. This paper presents a system with an application to tombstones-objects of flat plane with letters carved in-for assembling the fragments by placing their respective fragments in the right position. The matching process contains three sub-processes: aligning the front and letters of an object, identifying the matching directions, and determining the detailed matching positions. We apply least squares fitting and vector similarity methods to the matching process. It turned out that 2D translations via fragments-alignment enable us to save the computational load significantly. Based on experimental results from the damaged cultural fragments, the performance of the proposed method is illustrated.