Zhan Wang

Among the approximately 60,000 bone stick fragments unearthed from the Weiyang Palace site of the Han Dynasty, about 57,000 bear inscriptions. Most of these fragments exhibit vertical fractures, leading to a separation between the upper and lower fragments, which poses significant challenges to digital preservation and artifact restoration. Manual matching is inefficient and may cause further damage to the bone sticks. This paper proposes a novel multimodal bone stick matching approach that integrates image, inscription, and archeological information to enhance the accuracy and efficiency of matching fragmented bone stick artifacts. Unlike traditional methods that rely solely on image data, our method leverages large-scale pre-trained models, namely Vision-RWKV for visual feature extraction, RWKV for inscription analysis, and BERT for archeological metadata encoding. A dynamic cross-modal feature fusion mechanism is introduced to effectively combine these features, enabling better interaction and weighting based on the contextual relevance of each modality. This approach significantly improves matching performance, particularly in challenging cases involving fractures, corrosion, and missing sections. The novelty of this method lies in its ability to simultaneously extract and fuse multiple sources of information, addressing the limitations of traditional image-based matching methods. This paper uses Rank-N and Cumulative Match Characteristic (CMC) curves as evaluation metrics. Experimental evaluation shows that the matching accuracy reaches 94.73% at Rank-15, and the method performs significantly better than the comparative methods on the CMC evaluation curve, demonstrating outstanding performance. Overall, this approach significantly enhances the efficiency and accuracy of bone stick artifact matching, providing robust technical support for the research and restoration of bone stick cultural heritage.

The stitching of bone stick fragments is of great significance for the inheritance of and research into the outstanding traditional culture of the Western Han Dynasty. Focused on the problem that the existing methods have a low bone stick fragment stitching success rate due to their complex edges, this paper proposes a bone stick fragment stitching method based on improved corner detection, which strengthens the features of broken edges and improves the success rate of stitching. First, the maximum outer contour of the bone stick fragment is obtained using connectivity analysis. Then, the broken edge features are enhanced by combining multi-scale and multi-stage corner detection, as well as a double screening mechanism of local template and corner density analysis. On this basis, the maximum outer contour is segmented using a region segmentation method based on corner features. Then, a priority matching strategy is used to perform multi-dimensional sequential priority matching of corner features for the densest segments and to match other contour segments in the order of density. Finally, based on the matching results, the bone stick fragment is stitched exactly and restored. Experimental results show that compared with other algorithms, the average proportion of broken corners when using the method in this paper is increased by about 44.89%, and the average comprehensive weighted similarity is increased by about 32.42%, which meets the needs of bone stick fragment stitching.

The rejoining of bone sticks holds significant importance in studying the historical and cultural aspects of the Han Dynasty. Currently, the rejoining work of bone inscriptions heavily relies on manual efforts by experts, demanding a considerable amount of time and energy. This paper introduces a multi-scale feature fusion Siamese network guided by edge contour (MFS-GC) model. Constructing a Siamese network framework, it first uses a residual network to extract features of bone sticks, which is followed by computing the L2 distance for similarity measurement. During the extraction of feature vectors using the residual network, the BN layer tends to lose contour detail information, resulting in less conspicuous feature extraction, especially along fractured edges. To address this issue, the Spatially Adaptive DEnormalization (SPADE) model is employed to guide the normalization of contour images of bone sticks. This ensures that the network can learn multi-scale boundary contour features at each layer. Finally, the extracted multi-scale fused features undergo similarity measurement for local matching of bone stick fragment images. Additionally, a Conjugable Bone Stick Dataset (CBSD) is constructed. In the experimental validation phase, the MFS-GC algorithm is compared with classical similarity calculation methods in terms of precision, recall, and miss detection rate. The experiments demonstrate that the MFS-GC algorithm achieves an average accuracy of 95.5% in the Top-15 on the CBSD. The findings of this research can contribute to solving the rejoining issues of bone sticks.

Bone sticks are composed of thin slices of animal bones created by ancient people, which mainly served the functions of fixing books, writing scripts, and divination. The bone stick script is an essential material for studying the history of Chinese Western Han script. Using a neural network for text recognition can quickly interpret ancient text, while extracting deeper semantic information, neural networks will also lose superficial image details. After multi-layer convolution and pooling of bone sticks, the continuous loss of superficial details affects classification accuracy. At the same time, the unbalanced distribution of bone stick quantity leads to a low recognition rate with small samples of bone sticks. Aiming to solve the above problems, a bone stick recognition method based on multi-scale features and focal loss function is proposed. Firstly, based on the residual network ResNet, the output features of the first layer and four Conv_x layers are pooled globally to reduce the feature dimension of each channel, and the channel splicing method is used to add different depths of base information to the original high-level features, which improves the detail feature extraction ability of the model. Secondly, in view of the unbalanced distribution of the bone stick data, the original cross-entropy loss function is replaced by the focus loss function, which increases the penalty for classification errors and improves the recognition rate of classes with few training samples. Experimental results show that the recognition accuracy of the proposed method on the bone stick data set is up to 90.5%.