Open AccessMulti‐scale document image rectification utilising text‐features
Author(s) -
Sun Riming,
Wang Shengfa,
Ji Lin,
Wang Zhenyu
Publication year - 2018
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2018.0470
Subject(s) - rectification , computer science , artificial intelligence , flexibility (engineering) , image (mathematics) , scale (ratio) , computer vision , pattern recognition (psychology) , image rectification , information retrieval , engineering , mathematics , physics , statistics , quantum mechanics , voltage , electrical engineering
A multi‐scale document image rectification method based on text‐features is presented. In contrast to most used text‐lines, the text‐features are more robust to depict the distortions of document images with multi‐column layouts, multi‐type fonts or non‐textural objects. Then, the rectification problem is formulated utilising a reverse strategy according to the text‐features. The experiments have demonstrated the flexibility and high performance of the approach.