计算机应用研究2024，Vol.41Issue(10)：3194-3200,7.DOI:10.19734/j.issn.1001-3695.2023.11.0594
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 inscriptions based on multi-category morphology
摘要
Abstract
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 accu-rately 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 em-ployed 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(EC A)mechanism to guide the combination of feature channels,locating multiple independent discriminative regions and refining the extraction of morpho-logical 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.关键词
未隶定青铜器铭文/细粒度识别/姿态对齐/ECA注意力机制/特征融合Key words
untranscribed bronze inscriptions/fine-grained recognition/pose alignment/EC A attention mechanism/feature fusion分类
信息技术与安全科学引用本文复制引用
刘可欣,王慧琴,王可,王展,王宏..多类别形态的未隶定青铜器铭文细粒度识别[J].计算机应用研究,2024,41(10):3194-3200,7.基金项目
陕西省自然科学基础研究计划项目(2021JM-377) （2021JM-377）
