Form frame line detection with directional single-connected chain

Author

Zheng, Yefeng ; Liu, Changsong ; Ding, Xiaoqing ; Pan, Shiyan

Author_Institution

Dept. of Electron. Eng., Tsinghua Univ., Beijing, China

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

699

Lastpage

703

Abstract

In this paper, a novel form frame line detection algorithm is proposed based on the directional single-connected chain (DSCC). Defined as an array of black pixel run-lengths, DSCC works very well as an image structure element or vector in our vectorization algorithm. By merging multiple DSCCs under some constraints, we are able to extract the form frame lines automatically yet fast. The speed of our algorithm is comparable with some well-known projection methods. Experiments show that our algorithm is fast, resistant to moderate serious line breaks and can detect diagonal lines with any angle

Keywords

business forms; document image processing; merging; optical character recognition; OCR; black pixel run-lengths; character size; directional single-connected chain; document image processing; experiments; form frame line detection; image structure; line breaks; merging; office forms; vectorization algorithm; Acceleration; Detection algorithms; Merging; Object detection; Pixel; Postal services; Projection algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on

Conference_Location

Seattle, WA

Print_ISBN

0-7695-1263-1

Type

conf

DOI

10.1109/ICDAR.2001.953880

Filename

953880