Intelligent Restoration Technology of Mural Digital Image Based on Machine Learning Algorithm

Influenced by the natural environment and preservation conditions, frescoes in monastery were damaged to some extent. In order solve fresco image restoration conversion structural decomposition defects, an intelligent digital technique based on machine learning algorithm is proposed. Firstly, information of mural collected a scanning program, data database extracted. The mean filter template used restore color image, Gaussian details. two are superimposed ensure that not affected distortion halo, so as clarity boundary. depth model local fuzzy feature obtained using multimodal method, realized this model. experimental results show method can effectively repair features image. precision more than 95.7% fills missing from quality good.