A Study on Seal Recognition Method Based on Data Augmentation and Vision Transformer
Seal recognition poses challenges due to difficulties in data collection,annotation,and image degradation.This study aims to alleviate data scarcity through data augmentation and improve the model's ability to recognize seals in com-plex scenarios by using the vision transformer(ViT)model to extract global features.First,the contextual characteristics of the seals are analyzed,implementing data augmentation strategies based on the analysis results to expand the training set.Seal images are then input into the ViT model for feature extraction and recognition.We collected and annotated 1,259 seals from 16 calligraphy and painting works,such as"Lanting Xu."After applying 11 data augmentation modules,the training set expanded to include 127,159 seal images.Compared with the baseline model ResNet50,the F1 score improved by 12.17%.When the extended data obtained through data augmentation is removed,all models fail to converge.However,the proposed method lacks semantic reasoning ability and cannot recognize seals not present in the training set.In scenari-os with limited annotated data,the combination of data augmentation techniques and the utilization of the ViT model can facilitate accurate seal image recognition.
seal recognitiondeep learningdata augmentationdigital humanities
NETL
NSTL
万方数据
维普
