Robust Perspective Rectification of Camera-Captured Document Images - Archive ouverte HAL Access content directly
Conference Papers Year :

Robust Perspective Rectification of Camera-Captured Document Images

(1) , (1, 2) , (2)
1
2

Abstract

A correction method for perspective distortions on document images is discussed. In documents, lines and line feeds give rise to many horizontal and vertical lines, then two vanishing points generated by these lines can be computed based on the Radon transform. However, some noisy lines are unrelated to vanishing points and can be removed using RANSAC algorithm in the Radon domain. In this perspective, we propose a unique scheme on how to apply RANSAC algorithm to our method. The distortion is rectified by the perspective mapping determined with two vanishing points. Experimental results show that our method can remove line noise effectively and is competitive compared to the state-of-art especially for camera-captured inside document images where contours are not clearly defined.
Not file

Dates and versions

hal-02073407 , version 1 (19-03-2019)

Identifiers

Cite

Yusuke Takezawa, Makoto Hasegawa, Salvatore Tabbone. Robust Perspective Rectification of Camera-Captured Document Images. 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Nov 2017, Kyoto, France. pp.27-32, ⟨10.1109/ICDAR.2017.345⟩. ⟨hal-02073407⟩
47 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More