1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Proceedings
  5. Item

學術產出-Proceedings

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Toward Automatic Recognition of Cursive Chinese Calligraphy : An Open Dataset For Cursive Chinese Calligraphy Text
作者 廖文宏
Liao, Wen-Hung
Liang, Jung
Wu, Yi-Chieh
貢獻者 資科系
關鍵詞 Cursive Chinese Calligraphy , Text Recognition , Deep Learning
日期 2020-01
上傳時間 4-Jun-2021 14:49:11 (UTC+8)
摘要 Calligraphy is one of the most important writing tools as well as cultural heritage in ancient China. Compared with other calligraphy styles, the cursive script is least restricted and oftentimes exhibits the personality of calligraphers. However, this style-oriented expression makes the cursive script hard to recognize even for trained experts. The call for auxiliary tools for cursive Chinese calligraphy text recognition has thus arisen.Data play a key role in the era of deep learning, yet there is a lack of open databases for the cursive Chinese calligraphy. In this paper, we address this discrepancy by collecting 43000 images consisting of 5301 different cursive Chinese calligraphy text. We have augmented the database with basic image processing operations to obtain a training set containing a total of 656K images. After experimenting with several deep neural architectures, we provided a baseline model Enhanced M6 (EM6) as a proof-of-concept to tackle the classification task. The proposed EM6 model achieved 60.3% top-1 accuracy and 80.8% top-5 accuracy on the evaluation data set, an indication that deep neural network has the potential to undertake the mission of cursive calligraphy recognition.
關聯 Proceedings of 2020 14th International Conference on Ubiquitous Information Management and Communication (IMCOM), IEEE SMC Society, pp.1-5
資料類型 conference
DOI https://doi.org/10.1109/IMCOM48794.2020.9001777
dc.contributor 資科系
dc.creator (作者) 廖文宏
dc.creator (作者) Liao, Wen-Hung
dc.creator (作者) Liang, Jung
dc.creator (作者) Wu, Yi-Chieh
dc.date (日期) 2020-01
dc.date.accessioned 4-Jun-2021 14:49:11 (UTC+8)-
dc.date.available 4-Jun-2021 14:49:11 (UTC+8)-
dc.date.issued (上傳時間) 4-Jun-2021 14:49:11 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/135535-
dc.description.abstract (摘要) Calligraphy is one of the most important writing tools as well as cultural heritage in ancient China. Compared with other calligraphy styles, the cursive script is least restricted and oftentimes exhibits the personality of calligraphers. However, this style-oriented expression makes the cursive script hard to recognize even for trained experts. The call for auxiliary tools for cursive Chinese calligraphy text recognition has thus arisen.Data play a key role in the era of deep learning, yet there is a lack of open databases for the cursive Chinese calligraphy. In this paper, we address this discrepancy by collecting 43000 images consisting of 5301 different cursive Chinese calligraphy text. We have augmented the database with basic image processing operations to obtain a training set containing a total of 656K images. After experimenting with several deep neural architectures, we provided a baseline model Enhanced M6 (EM6) as a proof-of-concept to tackle the classification task. The proposed EM6 model achieved 60.3% top-1 accuracy and 80.8% top-5 accuracy on the evaluation data set, an indication that deep neural network has the potential to undertake the mission of cursive calligraphy recognition.
dc.format.extent 1499263 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Proceedings of 2020 14th International Conference on Ubiquitous Information Management and Communication (IMCOM), IEEE SMC Society, pp.1-5
dc.subject (關鍵詞) Cursive Chinese Calligraphy , Text Recognition , Deep Learning
dc.title (題名) Toward Automatic Recognition of Cursive Chinese Calligraphy : An Open Dataset For Cursive Chinese Calligraphy Text
dc.type (資料類型) conference
dc.identifier.doi (DOI) 10.1109/IMCOM48794.2020.9001777
dc.doi.uri (DOI) https://doi.org/10.1109/IMCOM48794.2020.9001777