Adaptive Superpixel Segmentation and Pigment Identification of Colored Relics Based on Visible Spectral Image

Abstract

This work explores the extraction of spatial distribution and chemical composition information of pigments used in colored relics through visible spectral images of the relics. An adaptive superpixel segmentation method is proposed first to extract the spatial distribution information of pigments. Quadtree decomposition is applied to generate nonuniform initial seed points based on image homogeneity. These seed points are used as initial cluster centers in an extended SLIC algorithm designed for visible spectral images, creating superpixels of varying sizes that reflect the homogeneity. Each superpixel is subsequently treated as an individual area within the colored relics, and a pigment identification method based on visible spectral reflectance is proposed to identify the pigments used in these areas. A standard reference database is constructed using samples that simulate the painting process of ancient wall paintings in the Mogao Grottoes. The geometric features, characterized by the linear combination of normalized visible spectral reflectance and its slope and curvature, are designed to represent the chemical composition of pigments. The geometric features of the superpixels are compared with those of the pigments in the database using Euclidean distance to determine the pigments used in each area of the colored relics. This work is expected to provide scientific guidance for pigment selection in the color restoration of colored relics.