利用曲率特征虚拟拼接青铜器小碎片的方法

doi:10.3969/j.issn.1001-2400.2016.06.024

Abstract

Abstract:

For the time-consuming problem of manual stitching small bronze fragments,an approach for virtual small bronze fragments reassembly based on curvature feature is proposed. First, we extract and smooth the 2d contour of the small bronze fragment, and then compute the curvature of each point on the contour and regard the local maxima of the curvature as the candidate corners. After that, the round corners and false corners are eliminated according to the support region. And then the chord lengths between the adjacent corners are calculated as the feature sequences to find the match. Finally, the reassembled result is obtained and refined by applying the invariance of the vector module. Experimental result proves that the method can effectively improve the efficiency of stitching and the effect of matching.

Key words: bronze, image fragments, stitching, contour match, corner detection

LIN Suzhen;WANG Dongjuan;ZHONG Jiarang;ZHU Xiaohong;ZHANG Shangmin. Approach to reassembling virtual small bronze fragments using the curvature feature[J].Journal of Xidian University, 2016, 43(6): 141-146.

[1]	HUANG Zhangqin,MU Zhao,CEN Chen,GAO Han. 360-degree real-time stitching technology for multi-channel video [J]. Journal of Xidian University, 2020, 47(2): 1-8.
[2]	CHEN Hongmeng;LI Ming;JIA Lu;WU Yan. High precision stitching algorithm for the DBS image [J]. J4, 2014, 41(2): 37-43.
[3]	ZHANG Weichuan;SHUI Penglang;XU Guojing. Corner detection via anisotropic Gaussian kernels information entropy on edge contours [J]. J4, 2013, 40(4): 119-124+129.

Approach to reassembling virtual small bronze fragments using the curvature feature

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 3

Metrics

Comments

Recommended 10