Xiao Zhou

Palm-leaf manuscripts (PLMs), essential Asian cultural artifacts, necessitate accurate species identification for their preservation. Traditional destructive analysis or manual inspection prone to errors hampers large-scale conservation efforts. To address this, we present PLNet, a lightweight framework integrating Lion-optimized EfficientNetB2 with domain-specific augmentation strategies. Lion optimizer enhances training stability, while task-driven augmentation simulates manuscript degradation. PLNet achieves exceptional performance on a diverse test set: 99.07% accuracy and 99.21% F1-score, outperforming ResNet50, DenseNet169, and YOLOv11-cls. Crucially, PLNet operates with high efficiency, utilizing only 7.7 million parameters and processing a folio in 0.31 s. To enable practical application, we developed PLNet-GUI for large-scale identification. Validated on 142,679 PLMs from 8 countries, the framework demonstrates robust real-world applicability, reveals regional species distribution patterns, and establishes a method shift in heritage conservation by replacing destructive practices with AI-driven preservation.

Background: Hyperspectral technology has made it possible to perform completely non-invasive investigations on pigment analysis, in particular, on pigment identification. The most commonly used method of pigment identification is to compare the spectral similarity between ones of unknown target and ones in spectral library, which requires a comprehensive and complete spectral library and is based on overall shape of the spectrum. To a certain extent, it may ignore some of the key absorption characteristics of the spectrum. Methods: A novel spectral matching method was proposed based on the spectrum divided into subsections for identification according to the main ion absorption characteristics. Main works: (1) establishing a spectral library suitable for typical pigment identification of painting; (2) discussing the main components, as well as the absorption positions of the ions and functional groups contained in pigments frequently used by artists; (3) presenting a novel spectral matching algorithm carried on spectral subsections for pigment identification; (4) verifying the feasibility and applicability of proposed method by a Chinese painting and a fresco. Conclusions: The proposed method can correctly identify the main pigments or components contained in the mixed area, which is better than the traditional method and more convenient than the unmixing method, except for some limitations in detecting white and black pigments.