Enhancing Color Texture Feature Extraction in Comprehensive Material Paintings

In the evolving landscape of contemporary art, the integration of diverse materials with artistic expression has led to the emergence of comprehensive material paintings. This innovative approach not only expands traditional boundaries but also introduces personalized schemas and techniques that resonate on aesthetic and emotional levels. Particularly, raw lacquer materials have gained attention for their unique properties, enabling artists to achieve a poetic narrative. This paper proposes an advanced algorithm that integrates Convolutional Neural Networks (CNN) with wavelet transform to enhance color texture feature extraction from comprehensive material paintings. The research tests the hypothesis that this integrated method significantly improves accuracy and efficiency in feature extraction, thereby advancing art analysis and preservation. Through rigorous testing, it is concluded that the proposed algorithm offers valuable insights into bridging traditional art forms with modern technological advancements.