Title :
The extraction of characters on dated color postcards
Author :
Yen, Shwu-Huey ; Chen, Mei-Fen ; Lin, Hwei-Jen ; Wang, Chia-Jen ; Liu, Chiu-Hsiang
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Tamkang Univ., Tamsui
Abstract :
A novel scheme is proposed to extract characters from dated postcards. The illustrations of the postcards appear in various languages and colors embedded in different backgrounds. Due to reproduction and uneven illumination, these characters suffer a severe degradation and hence extracting characters using conventional methods becomes difficult. A morphological operation is proposed to remove irrelevant backgrounds that are connecting to border edges of the postcards. As a result, characters become the most obvious objects. Followed by horizontal and vertical projections, the exact locations of the characters can be located. The proposed scheme has been executed on a set of color images of postcards and proved its efficacy
Keywords :
character recognition; feature extraction; image colour analysis; image reconstruction; RLSA; background embedded illustrations; character location; connected component analysis; dated color postcards; horizontal projections; irrelevant background removal; morphological reconstruction; postcard character extraction; reproduction; uneven illumination; vertical projections; Computer science; Data mining; Degradation; Image analysis; Image color analysis; Lighting; Low pass filters; Morphological operations; Nonlinear filters; Solids;
Conference_Titel :
Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
0-7803-8603-5
DOI :
10.1109/ICME.2004.1394499