多类别形态的未隶定青铜器铭文细粒度识别

Fine-grained recognition of untranscribed bronze inscriptionsbased on multi-category morphology

未隶定铭文的识别主要依靠传统卷积网络提供单一的全局特征,却忽略了部位识别和特征学习的关系,导致模型难以充分表达复杂形态的文字构造,进而产生识别误差。针对上述问题,提出了一种姿态对齐的多部位特征细粒度识别模型(MP-CNN)。在第一个阶段,构建空间转换器引导铭文统一字形姿态,辅助模型准确定位文字的鉴别性部位;在第二个阶段,构建级联的ECA(efficient channel attention)注意力机制引导特征通道组合,定位多个独立的鉴别性部位,并通过相互增强的方式细粒化地提取铭文的形态特征,解决复杂形态的文字识别问题;在第三个阶段,构建特征融合层获取识别结果。实验表明,该算法在铭文标准数据集和多类别形态数据集上的识别准确率分别为97.25%和97.18%,相比于传统卷积网络ResNet34分别提升4.63%和8.89%。结果显示,该算法能够有效针对铭文实际形态的独特性,实现未隶定铭文的细粒度识别。

Fine-grained recognition of untranscribed bronze inscriptions relies on traditional convolutional neural networks.However,this method used overlooks the relationship between localization and feature learning,leading to difficulties in accurately representing the complex structures of the text and resulting in recognition errors.This paper proposed a model,named MP-CNN,addressed this issues through a pose-aligned multi-part fine-grained recognition approach.In the first stage,it employed a spatial transformer to guide inscriptions to adopt a consistent glyph posture,aiding the model in accurately locating key text regions.The second stage incorporated constructing a cascaded efficient channel attention(ECA)mechanism to guide the combination of feature channels,locating multiple independent discriminative regions and refining the extraction of morphological features for complex text structures.Finally,in the third stage,it built a feature fusion layer to obtain the recognition results.Experimental results demonstrate that the algorithm achieves recognition accuracies of 97.25%and 97.18%on stan-dard and multi-category morphology datasets,respectively.Compared to the traditional convolutional network ResNet34,the method exhibits improvements of 4.63%and 8.89%on these datasets.The results indicate that the algorithm effectively adapts to the actual morphological variations in inscriptions,achieving fine-grained recognition of untranscribed bronze inscriptions.