Method for identifying multi-font multi-character size print form Tibetan character |
Title: |
Method for identifying multi-font multi-character size print form Tibetan character |
|
Application Number: |
200410034107 |
Application Date: |
2004/04/23 |
Announcement Date: |
2005/01/26 |
Pub. Date: |
2006/04/12 |
Publication Number: |
1570958 |
Announcement Number: |
1251130 |
Grant Date: |
2006-4-12 |
Granted Pub. Date: |
2006-4-12 |
ApplicationType: |
Invention |
State/Country: |
11[China|beijing] |
IPC: |
G06K 9/72, G06K 9/54, G06K 9/46 |
Applicant(s): |
Tsinghua University |
Inventor(s): |
Ding Xiaoqing, Wang Hua, Liu Changsong |
Key Words: |
identifying method, multi-font, multi-character size, print, Tibetan character |
Abstract: |
It is multi-font and multi-size block letter Tibet character identifying method. It¡¯s characteristic is: providing the normalization scheme that arming at the feature that the block letter Tibet character is non-Chinese characters. It separates the character to two sub-images that non-overlap based on the baseline, namely the upper-even line. Then normalizing every sub-image by location normalization that combining the barycenter and frame and size normalization that based on cubic B spline function interpolation. It abstracts the four-direction line-element feature that can reflect the combining information of Tibet character. Then it uses the linear distinguishing analyze LDA compress to reduce dimensions and obtain the compact character feature vector. It judges the character type by thick-thin two level sorting strategies that based on confidence analysis. The thick-thin sorter adopted the Euler¡¯s distance EDD that with deviation and modified quadratic authentication function MQDF. |
Claim: |
|
Priority: |
|
PCT: |
|
LegalStatus: |
|