• Home
  • Search
  • Layout and Perspective Distortion Independent Recognition of Captured Chinese Document Image
  • Cite Icon3
  • https://doi.org/10.1109/icdar.2017.102Copy DOI Icon

Layout and Perspective Distortion Independent Recognition of Captured Chinese Document Image

  • Nov 1, 2017
  • Yanwei Wang +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This paper introduced a layout and perspective distortion independent recognition framework for captured Chinese document image. Under the framework, 1) Conditional random field (CRF) is employed for text line extraction from a global point of view. As the text line extraction is layout independent it could be widely used in different type of document images 2) A text line image based perspective distortion correction method is detailed and used in three different ways. 3) The text line extraction and perspective distortion correction are combined with character recognition to construct a recognition system. On three captured document image datasets, the proposed framework improves the accuracies from 94.03% to 95.20%, 13.01% to 93.71% and 10.63% to 92.68% respectively for different distortion degrees. The experimental results demonstrate that the introduced recognition framework is promising for solving layout and perspective distortion problems in captured document image recognition.

Similar Papers
  • Book Chapter
  • Citations35

State Estimation in a Document Image and Its Application in Text Block Identification and Text Line Extraction

  • Jan 01, 2010
  • Hyung Il Koo +1
  • Book Chapter
  • Citations3

Segmentation of Handwritten Document Images into Text Lines

  • Apr 19, 2011
  • Vassilis Katsouros +1
  • Conference Article
  • Citations7

A Hybrid Method for Text Line Extraction in Handwritten Document Images

  • Aug 01, 2018
  • Ehsan Kiumarsi +1
  • Research Article
  • Citations10

A Combined Algorithm for Layout Analysis of Arabic Document Images and Text Lines Extraction

  • Jul 31, 2012
  • International Journal of Computer Applications
  • Abdulrahman Alshameri +2
  • Research Article
  • Citations7

Human Reading Knowledge Inspired Text Line Extraction

  • Aug 02, 2017
  • Cognitive Computation
  • Liuan Wang +3
  • Conference Article
  • Citations9

Towards Document Image Quality Assessment: A Text Line Based Framework and a Synthetic Text Line Image Dataset

  • Sep 01, 2019
  • Hongyu Li +2
  • Conference Article
  • Citations6

Warped Document Image Mosaicing Method Based on Inflection Point Detection and Registration

  • Nov 01, 2012
  • Lijing Tong +4
  • Book Chapter
  • Citations1

Distorted Document Image Rectification Based on Inflection Detection and Heterogeneous Registration

  • Nov 06, 2012
  • Lijing Tong +3
  • Book Chapter
  • Citations10

Text Line Extraction Using Fully Convolutional Network and Energy Minimization

  • Jan 01, 2021
  • Berat Kurar Barakat +5
  • Conference Article
  • Citations23

High Performance Layout Analysis of Arabic and Urdu Document Images

  • Sep 01, 2011
  • Syed Saqib Bukhari +2
  • Conference Article
  • Citations4

Text Line Detection in Document Images: Towards a Support System for the Blind

  • Aug 01, 2013
  • Bogdan Tomoyuki Nassu +2
  • Research Article

Using Orientation Voting to Extract Text Lines with Various Mixed Directions from a Document Image

  • Jul 25, 2017
  • Journal of the Institute of Industrial Applications Engineers
  • Xiaohua Zhang +3
  • Conference Article
  • Citations35

A Robust and Binarization-Free Approach for Text Line Detection in Historical Documents

  • Nov 01, 2017
  • Tobias Gruuening +3
  • Research Article
  • Citations75

Goal-Oriented Rectification of Camera-Based Document Images

  • Sep 27, 2010
  • IEEE Transactions on Image Processing
  • Nikolaos Stamatopoulos +3
  • Conference Article
  • Citations9

Text line extraction in document images

  • Aug 01, 2015
  • Liuan Wang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.