Combining Deep Learning and Lexical Analysis method for Rubbing Character Recognition

• Item type: Symposium(1)
• 公開日: 2019-12-07
• タイトル: Combining Deep Learning and Lexical Analysis method for Rubbing Character Recognition
• タイトル / 言語: en
• タイトル: Combining Deep Learning and Lexical Analysis Method for Rubbing Character Recognition
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: rubbings; deep learning; lexical analysis; culture heritage preservation
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属: Ritsumeikan University
• 著者所属: Ritsumeikan University
• 著者所属: Ritsumeikan University
• 著者所属(英): en
• 著者所属(英): Ritsumeikan University, Ritsumeikan University, Ritsumeikan University
• 著者名: Zhiyu, Zhang; Hiroyuki, Tomiyama; Lin, Meng
• 著者名(英): Zhiyu, Zhang; Hiroyuki, Tomiyama; Lin, Meng
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: As a vehicle for storing ancient historical and cultural information, rubbings have a wealth of potential knowledge. However, due to the blurriness and damage of the rubbing characters, a lot of noises in the background of the rubbings and the different grammatical structure of ancient Chinese and modern Chinese, now the rubbings are mostly manually transcribed by experts. In recent years, deep learning has made great achievements in object recognition, and researchers have begun to try to use deep learning to recognize ancient characters. Against such a backdrop, this paper proposes a method combining deep learning and lexical analysis to achieve automatic recognition of rubbing characters, and contributing to culture heritage protection and preservation. Part of rubbing of“Bei qi tian zhu shan” is used for characters recognition, and the experimental results proved the effectiveness of our proposal.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: As a vehicle for storing ancient historical and cultural information, rubbings have a wealth of potential knowledge. However, due to the blurriness and damage of the rubbing characters, a lot of noises in the background of the rubbings and the different grammatical structure of ancient Chinese and modern Chinese, now the rubbings are mostly manually transcribed by experts. In recent years, deep learning has made great achievements in object recognition, and researchers have begun to try to use deep learning to recognize ancient characters. Against such a backdrop, this paper proposes a method combining deep learning and lexical analysis to achieve automatic recognition of rubbing characters, and contributing to culture heritage protection and preservation. Part of rubbing of“Bei qi tian zhu shan” is used for characters recognition, and the experimental results proved the effectiveness of our proposal.
• 書誌情報: じんもんこん2019論文集; 巻 2019, p. 231-238, 発行日 2019-12-07
• 出版者 / 言語: ja
• 出版者: 情報処理学会