壁画病害边缘自动提取方法研究

Research on Automatic Edge Extraction of Mural Diseases

本文针对目前壁画病害手动调查方法在精度和效率上的劣势,研究新的病害边缘自动提取方法.首先,制作壁画正射影像图;其次,在正射投影图上应用顾及紧凑度的SLIC超像素分割方法,得到分类规则、边缘紧凑的超像素;再次,应用最大相似度区域合并算法对超像素进行聚类,得到病害高精度边缘数据;最后,获取病害在正射影像图上的区域,并进行定量及定性表达.应用真实的壁画数据进行实验,证明了本文方法的正确性和可行性,研究方法为壁画类文物病害自动调查提供了新的思路.

Aiming at the disadvantages of accuracy and efficiency of the current manual investigation methods of mural diseases,this paper studies a new automatic edge extraction method.First,make the orthophoto map of the mural;Secondly,the SLIC super-pixel segmentation method considering compactness is applied to the orthophoto projection map to obtain the super-pixel with compact edge of classification rules;Thirdly,the maximum similarity region merging algorithm is used to cluster the super pixels to obtain the disease high-precision edge data;Finally,the region of the disease on the orthophoto map is obtained and expressed quantitatively and qualitatively.Experiments with real mural data prove the correctness and feasibility of this method.The research method provides a new idea for the automatic investigation of mural cultural relics.