Accurate Color Reproduction of Cultural Heritage Using Digital Photography and Machine Learning

A recent study at Kongju National University has made significant breakthroughs in accurately recording the colors of cultural heritage objects using digital photography and machine learning algorithms. The research aimed to reproduce colors that closely match those of the object, enabling precise documentation and analysis for conservation, restoration, and research purposes.

Key Takeaways:

• The study employed a systematic process that included photography, digital color correction, and digital color space configuration to enhance the reliability of color reproduction.
• The research utilized the device-independent CIE L*a*b* color space to ensure consistent color reproduction across different devices.
• The study compared the spectral color measurement results of a color chart with the color differences observed in the reproduced images, achieving accurate color reproduction.
• Approximately 30 million pixels were classified using the K-means machine learning algorithm, enabling the extraction of representative colors and various analytical outcomes.
• The research enabled oil paintings to be documented with accurate colors, offering valuable insights into color usage patterns and chromatic painting techniques of an artist.
• The method used in this study provides a valuable tool for conserving and analyzing cultural heritage objects, and for verifying the authenticity of artworks.

Statistics:

• The study analyzed approximately 30 million pixels classified using the K-means machine learning algorithm.
• The research extracted representative colors using a machine learning algorithm, with various analytical outcomes such as the number of pixels, representative CIE L*a*b* color coordinates, and the percentage composition of each representative color.
• The study achieved accurate color reproduction by comparing the spectral color measurement results of a color chart with the color differences observed in the reproduced images.

Sources:

• Study on the Color Characteristics of Reproduced Oil Paintings Using a Machine Learning Algorithm. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2025, XLVIII-M-9-2025()->1395-1400.
• The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - http://www.isprs.org/publications/archives.aspx
• The publisher for The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences is Copernicus Publications.