Contour-based two-dimensional fragment splicing method

Abstract

The invention discloses a contour-based two-dimensional fragment splicing method which comprises the steps of: a first step, obtaining a scanned fragment image and extracting a fragment contour curve; a second step, performing polygonal approximation and feature extraction on the contour, thereby obtaining two feature sequences, namely a rotation angle sequence and a side length sequence; a third step, searching for partial candidate matching segments between random two fragments based on the feature sequences, thereby searching for partial matching among the N fragments, comparing random two fragments of the N fragments, thereby obtaining a final partial matching set; and a fourth step, in the final partial matching set, searching a global path for partial matching based on a rotation angle which is required for splicing the fragments according to partial matching, and integrating all determined path to a path which contains all fragments, thereby realizing splicing. Compared with a best priority method, the contour-based two-dimensional fragment splicing method is advantageous in that the global path searching method based on partial matching splicing rotation angle measurement sufficiently utilizes local matching pairs; a correct matching path and a fragment reconstruction path are determined; and the matching efficiency is improved.

Description

technical field [0001] The invention relates to a contour-based two-dimensional fragment mosaic method. Background technique [0002] In the fields of archaeological cultural relics restoration, judicial evidence identification, broken RMB merging and other fields, the problem of fragment mosaic is common. When the number of fragments is large, the task of merging by manual comparison is complicated, and it may cause secondary damage to the object. Therefore, computer-aided fragmentation Automatic or semi-automatic splicing becomes necessary. The small and negligible fragments produced by murals, tiles, cloth, oil paintings, etc. are called two-dimensional fragments, and the related splicing problem is called two-dimensional fragment splicing problem. [0003] Two-dimensional irregular fragment mosaic can be divided into contour-based and content-based mosaic. Due to the limitations of fragment content (color, texture, etc.), it is usually used in combination with contour, ...

AI Technical Summary

Problems solved by technology

The amount of calculation of the contour is large because of the uniform sampling points of the contour. When the number of fragments increases, the amount of comparison in the matching stage increases faster and is easily affected by noise.

The method of extracting contour key points or polygon approximation can reduce the amount of calculation and has a certain tolerance to noise, but it may not describe the contour shape completely

[0009] The global matching process can be divided into two methods, one is the best priority method, that is, after the local matching, the best pair is selected among the candidate matching pairs, and after being assembled, it will be used as a new fragment to participate in the next round of local matching process, and the process is repeated. The process until the global splicing is realized. This method does not make full use of the candidate matching information, which is greatly affected by the last round of splicing results, and the efficiency is low; the other is to search for the possible global splicing relationship of all matching pairs to obtain a globally consistent splicing result. The existence of a large number of false matching pairs will reduce the search efficiency of the method

Images