Virtual cleaning of sooty murals in ancient temples using twice colour attenuation prior

Abstract

Murals are artworks painted on walls that represent various cultures, traditions, historical periods, spiritual narratives and civilisations. Unfortunately, before modern preventive measures were implemented, murals suffered considerable degradation from accumulating substances, such as incense oil and carbon, leading to a darkening or blackening phenomenon called soot. The soot severely and extensively damaged the murals’ colour and motifs. However, no highly effective remedy is available to restore them to their original state. A novel approach for virtual cleaning of this degradation uses hyperspectral and image enhancement technologies. Existing techniques for sooty mural image restoration primarily use dark channel prior and Retinex bilateral filtering. During this process, the dark channel prior estimates the concentration of soot and removes it, restoring the mural’s colour with Retinex bilateral filtering. However, this restoration method has issues, such as neglecting the difference between soot and haze, resulting in a generally darker mural image. This result requires brightness adjustment, and the method presents further challenges, such as texture loss, colour distortion in some areas and a reduction in clarity. Therefore, we propose a new technique that integrates an inverse operation and twice colour attenuation prior to cleaning sooty murals. This technique involves normalised cross-correlation to match and stitch images to the different synthesised bands to reconstruct the mural image to be processed, which removes black marks from areas of mural loss. The sooty mural then undergoes an inverse operation, and the colour attenuation prior is used on the inverse image. The processed mural is then inverted again, transforming the colour of soot to white. Finally, the colour attenuation prior is again applied to the colour-changing mural, enabling virtual cleaning of the sooty murals. The results confirm the enhanced adaptability of our novel approach for the virtual cleaning of sooty murals. Moreover, the proposed method exhibits superior performance for various performance parameters.