藏文古籍图像二值化研究现状

Research Progress of Tibetan Ancient Image Binarization

藏文古籍是藏民族优秀文化宝库中的一颗璀璨明珠。由于年代久远及保存不当,古籍退化严重。二值化算法能够将退化古籍中的文本和背景分割开,更好地揭示古籍所记载内容,解决藏文古籍图像二值化时存在的质量差、对比度渐变、不均匀光照及字迹模糊等问题。参考文献的实验结果表明,众多的二值化算法中没有一个能够处理所有的古籍退化类型及所有的古籍图像数据库。为促进藏文古籍的保护和传播,对退化藏文古籍图像二值化研究迫在眉睫。该研究是古籍数字化和全文检索的必要步骤,蕴藏着巨大的应用价值。

Tibetan ancient document is a shining pearl of Tibetan cultural treasure-house. However, many environmental factors and improper handling cause them to suffer a high degree of degradation of various types. Binarization can segment the text from ancient document image accurately and better reveal the contents recorded in the document. As show in the Experimental Results of reference files, a problem associated with all the proposed binarization algorithms is that they can not deal with all types of degradation and with different datasets. In order to promote the protection and dissemination of Tibetan ancient document, the study of degraded Tibetan ancient document image binarization is imminent, it is also important for the ensuing document image processing tasks such as document digitization and full text retrieval and provides a huge potential market for application.