| A New Method to Extract Text from Natural Scenes |
| |
| 作者姓名： | 郝峻晟 戚飞虎 朱凯华 蒋人杰 |
| |
| 作者单位： | Computer Vision Lab, Computer Science Department, Shanghai Jiaotong University 200030 |
| |
| 摘 要： | This paper presents a new method for text detection, location and binarization from natural scenes. Several morphological steps are used to detect the general position of the text, including English, Chinese and Japanese characters. Next bonnding boxes are processed by a new “Expand, Break and Merge” （EBM） method to get the precise text areas. Finally, text is binarized by a hybrid method based on Otsu and Niblack. This new approach can extract different kinds of text from complicated natural scenes. It is insensitive to noise, distortedness, and text orientation. It also has good performance on extracting texts in various sizes.
|
| 关 键 词： | 机器翻译 文本提取 数学形态学 边界框 二值化 |
| 收稿时间： | 2004-10-09 |
A New Method to Extract Text from Natural Scenes |
| |
| HAO Jun-sheng,QI Fei-hu,ZHU Kai-hua,JIANG Ren-jie.A New Method to Extract Text from Natural Scenes[J].Journal of Donghua University,2005,22(4):52-57. |
| |
| Authors: | HAO Jun-sheng QI Fei-hu ZHU Kai-hua JIANG Ren-jie |
| |
| Abstract: | This paper presents a new method for text detection, location and binarization fron natural scenes. Several morphological steps are used to detect the general positian of the text, including English, Chinese and Japanese characters. Next bounding boxes are processed by a new "Expand, Break and Merge" (EBM) method to get the precise text areas. Finally, text is binarized by a hybrid method based on Otsu and Niblack. This new approach can extract different kinds of text from complicated natural scenes. It is insensitive to noise, distortedness, and text orientation. It also has good performance on extracting texts in various sizes. |
| |
| Keywords: | Text Extraction mathematical morphology boundingboxes binrization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
