Attention-enhanced U-Net for automatic crack detection in ancient murals using optical pulsed thermography.

• Demonstrate the feasibility of optical pulsed thermography for crack detection in Tang murals. • Propose a novel attention U-Net that combines an attention and a U-Net for enhanced crack feature extraction. • Evaluate attention U-Net's effectiveness and generalizability compared to wavelet edge detection and traditional U-Net. Ancient mural degradation and destruction may result from various natural causes, resulting in cracks, peeling, or bulging. As such, regular testing and evaluation of ancient murals are indispensable for protecting and preserving cultural relics. In many scenarios, the acquisition of detection data can be expedited through the use of mechanical arms and imaging equipment. However, the subsequent data analysis relies on experienced human inspectors, resulting in a laborious and time-consuming process. This study focuses on automated analysis of cracks in ancient murals using optical pulsed thermography. A technique that combines an attention mechanism and the U-Net neural network is proposed for refined crack feature extraction. Concerning the identification of ancient mural cracks based on limited training data, U-Net with the attention mechanism demonstrates superior performance over both the conventional U-Net and a traditional image segmentation algorithm. [Display omitted] [ABSTRACT FROM AUTHOR]