THE TECHNIQUE OF AUTOMATED IMAGE RESTORATION USING CONVOLUTIONAL NEURAL NETWORKS

Abstract

The task of restoring lost fragments of monumental painting is relevant in the context of preserving cultural heritage sites. Modern artificial intelligence technologies, including convolutional neural networks (CNN), significantly expand the possibilities of restoration, allowing for the automation of complex image restoration processes. In particular, the restoration of lost elements of frescoes requires precise analysis tools that can predict missing fragments with minimal errors, while preserving the artistic style of the original. The purpose of this study is to develop a technique of automated restoration of lost fragments of monumental painting images using CNN (using frescoes as an example). This goal was achieved by solving the following problems: obtaining fresco images using appropriate methodological and technical tools, applying the U-Net architecture for image segmentation and reconstruction, predicting lost areas based on color characteristic analysis. The photogrammetry method and the designed device, which were used to perform multi-angle shooting, provided high-quality source data for subsequent processing. Adaptation of the U-Net architecture to the image segmentation task has proven its effectiveness in identifying key structural elements of frescoes, which contributed to the accurate reconstruction of lost areas. To predict the lost areas, color characteristics were analyzed in the HSL system, which allowed the CNN to predict the missing colors with a high degree of accuracy. Brief conclusions of the study show that the proposed technique allows restoring both the shape and color of lost fragments of frescoes. The proposed technique is planned to be used for the restoration of other types of art works, which makes it promising for further research.