http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
SEL-RefineMask: A Seal Segmentation and Recognition Neural Network with SEL-FPN
Ze-dong Dun,Jian-yu Chen,Mei-xia Qu,Bin Jiang 한국정보처리학회 2022 Journal of information processing systems Vol.18 No.3
Digging historical and cultural information from seals in ancient books is of great significance. However,ancient Chinese seal samples are scarce and carving methods are diverse, and traditional digital imageprocessing methods based on greyscale have difficulty achieving superior segmentation and recognitionperformance. Recently, some deep learning algorithms have been proposed to address this problem; however,current neural networks are difficult to train owing to the lack of datasets. To solve the afore-mentionedproblems, we proposed an SEL-RefineMask which combines selector of feature pyramid network (SEL-FPN)with RefineMask to segment and recognize seals. We designed an SEL-FPN to intelligently select a specificlayer which represents different scales in the FPN and reduces the number of anchor frames. We performedexperiments on some instance segmentation networks as the baseline method, and the top-1 segmentation result of 64.93% is 5.73% higher than that of humans. The top-1 result of the SEL-RefineMask network reached67.96% which surpassed the baseline results. After segmentation, a vision transformer was used to recognizethe segmentation output, and the accuracy reached 91%. Furthermore, a dataset of seals in ancient Chinesebooks (SACB) for segmentation and small seal font (SSF) for recognition were established which are publiclyavailable on the website.