Rock painting restoration method based on saliency detection and TV model
Yue Yin, Jun Ping Zhou · 2021 International Conference on Computer Engineering and Application (ICCEA) · 2021
Traditional restoration algorithms are not effective enough to fully repair rock paintings. The barley lithology is used as an example in this work to demonstrate a novel repair algorithm based on saliency detection and total variation (TV). The damage detection area of the rock painting image is extracted by saliency detection, then the improved TV model is applied to complete the repair. Experiments show that the proposed algorithm can effectively improve the poor robustness and virtual boundary of the traditional TV model image restoration algorithm, and make the image smoother and achieve better repair results. At the same time, a set of solutions for the extraction and restoration of structural rock paintings has been formed.