当前位置: X-MOL 学术ACM Trans. Asian Low Resour. Lang. Inf. Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Lipi Gnani
ACM Transactions on Asian and Low-Resource Language Information Processing ( IF 2 ) Pub Date : 2020-05-22 , DOI: 10.1145/3387632
H. R. Shiva Kumar 1 , A. G. Ramakrishnan 1
Affiliation  

A Kannada OCR, called Lipi Gnani , has been designed and developed from scratch, with the motivation of it being able to convert printed text or poetry in Kannada script, without any restriction on vocabulary. The training and test sets have been collected from more than 35 books published from 1970 to 2002, and this includes books written in Halegannada and pages containing Sanskrit slokas written in Kannada script. The coverage of the OCR is nearly complete in the sense that it recognizes all punctuation marks, special symbols, and Indo-Arabic and Kannada numerals. Several minor and major original contributions have been done in developing this OCR at different processing stages, such as binarization, character segmentation, recognition, and Unicode mapping. This has created a Kannada OCR that performs as good as, and in some cases better than, Google’s Tesseract OCR, as shown by the results. To the best of our knowledge, this is the maiden report of a complete Kannada OCR, handling all issues involved. Currently, there is no dictionary-based postprocessing, and the obtained results are due solely to the recognition process. Four benchmark test databases containing scanned pages from books in Kannada, Sanskrit, Konkani, and Tulu languages, but all of them printed in Kannada script, have been created. The word-level recognition accuracy of Lipi Gnani is 5.3% higher on the Kannada dataset than that of Google’s Tesseract OCR, 8.5% higher on the Sanskrit dataset, and 23.4% higher on the datasets of Konkani and Tulu.

中文翻译:

利皮·格纳尼

卡纳达语 OCR,称为利皮·格纳尼, 是从头开始设计和开发的,其动机是能够转换卡纳达语脚本中的印刷文本或诗歌,而不受词汇限制。训练和测试集是从 1970 年到 2002 年出版的超过 35 本书中收集的,其中包括用 Halegannada 编写的书籍和包含用 Kannada 脚本编写的梵语 slokas 的页面。OCR 的覆盖范围几乎是完整的,它可以识别所有标点符号、特殊符号以及印度-阿拉伯语和卡纳达语数字。在开发此 OCR 的不同处理阶段,如二值化、字符分割、识别和 Unicode 映射,已经完成了几个次要和主要的原始贡献。这创造了一个卡纳达语 OCR,其​​性能与谷歌的 Tesseract OCR 一样好,在某些情况下甚至更好,如结果所示。据我们所知,这是完整的卡纳达语 OCR 的首次报告,处理所有涉及的问题。目前,没有基于字典的后处理,获得的结果完全是由于识别过程。已经创建了四个基准测试数据库,其中包含来自卡纳达语、梵语、孔卡尼语和图卢语书籍的扫描页面,但它们都以卡纳达语脚本打印。Lipi Gnani 在 Kannada 数据集上的单词级识别准确率比 Google 的 Tesseract OCR 高 5.3%,在梵语数据集上高 8.5%,在 Konkani 和 Tulu 数据集上高 23.4%。并且获得的结果仅归因于识别过程。已经创建了四个基准测试数据库,其中包含来自卡纳达语、梵语、孔卡尼语和图卢语书籍的扫描页面,但它们都以卡纳达语脚本打印。Lipi Gnani 在 Kannada 数据集上的单词级识别准确率比 Google 的 Tesseract OCR 高 5.3%,在梵语数据集上高 8.5%,在 Konkani 和 Tulu 数据集上高 23.4%。并且获得的结果仅归因于识别过程。已经创建了四个基准测试数据库,其中包含来自卡纳达语、梵语、孔卡尼语和图卢语书籍的扫描页面,但它们都以卡纳达语脚本打印。Lipi Gnani 在 Kannada 数据集上的单词级识别准确率比 Google 的 Tesseract OCR 高 5.3%,在梵语数据集上高 8.5%,在 Konkani 和 Tulu 数据集上高 23.4%。
更新日期:2020-05-22
down
wechat
bug