• Home
  • Search
  • A Unified Video Text Detection Method with Network Flow
  • Cite Icon17
  • https://doi.org/10.1109/icdar.2017.62Copy DOI Icon

A Unified Video Text Detection Method with Network Flow

  • Nov 1, 2017
  • Xue-Hang Yang +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Scene text detection in videos has many application needs but has drawn less attention than that in images. Existing methods for video text detection perform unsatisfactorily because of the insufficient utilization of spatial and temporal information. In this paper, we propose a novel video text detection method with network flow based tracking. The system first applies a newly proposed Fully Convolutional Neural Network (FCN) based scene text detection method to detect texts in individual frames and then track proposals in adjacent frames with a motion-based method. Next, the text association problem is formulated into a cost-flow network and text trajectories are derived from the network with a min-cost flow algorithm. At last, the trajectories are post-processed to improve the precision accuracy. The method can detect multi-oriented scene text in videos and incorporate spatial and temporal information efficiently. Experimental results show that the method improves the detection performance remarkably on benchmark datasets, e.g., by a 15.66% increase of ATA Average Tracking Accuracy) on ICDAR video scene text dataset.

Similar Papers
  • Book Chapter
  • Citations23

A Robust Approach for Scene Text Detection and Tracking in Video

  • Jan 01, 2018
  • Yang Wang +2
  • Conference Article
  • Citations29

Automatic Detection and Localization of Natural Scene Text in Video

  • Aug 01, 2010
  • Xiaodong Huang +1
  • Research Article
  • Citations117

Scene text detection and recognition with advances in deep learning: a survey

  • Mar 27, 2019
  • International Journal on Document Analysis and Recognition (IJDAR)
  • Xiyan Liu +2
  • Conference Article
  • Citations8

A New Method for Handwritten Scene Text Detection in Video

  • Nov 01, 2010
  • Palaiahnakote Shivakumara +3
  • Conference Article
  • Citations29

End-to-End Scene Text Recognition in Videos Based on Multi Frame Tracking

  • Nov 01, 2017
  • Xiaobing Wang +7
  • Conference Article
  • Citations41

Scene Text Detection and Tracking in Video with Background Cues

  • Jun 05, 2018
  • Lan Wang +3
  • Conference Article
  • Citations6

Data, protocol and algorithms for performance evaluation of text detection in Arabic news video

  • Mar 01, 2016
  • Oussama Zayene +4
  • Research Article
  • Citations54

Tracking Based Multi-Orientation Scene Text Detection: A Unified Framework With Dynamic Programming

  • Apr 18, 2017
  • IEEE Transactions on Image Processing
  • Chun Yang +6
  • Conference Article
  • Citations30

Text Detection in Arabic News Video Based on SWT Operator and Convolutional Auto-Encoders

  • Apr 01, 2016
  • Oussama Zayene +5
  • Conference Article
  • Citations3

Improving text recognition by distinguishing scene and overlay text

  • Feb 12, 2015
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Bernhard Quehl +2
  • Research Article
  • Citations30

Multi-oriented scene text detection in video based on wavelet and angle projection boundary growing

  • Feb 17, 2013
  • Multimedia Tools and Applications
  • Palaiahnakote Shivakumara +3
  • Book Chapter
  • Citations5

Introduction to Video Text Detection

  • Jan 01, 2014
  • Tong Lu +3
  • Research Article
  • Citations42

Fractals based multi-oriented text detection system for recognition in mobile video images

  • Mar 14, 2017
  • Pattern Recognition
  • Palaiahnakote Shivakumara +5
  • Conference Article
  • Citations12

Occluded Text Detection and Recognition in the Wild

  • May 01, 2022
  • Zobeir Raisi +1
  • Conference Article
  • Citations78

Video text detection and recognition: Dataset and benchmark

  • Mar 01, 2014
  • Phuc Xuan Nguyen +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.