Skip to main content
SpringerLink
Log in

Text-Pose Estimation in 3D Using Edge-Direction Distributions

  • Conference paper
Image Analysis and Recognition (ICIAR 2005)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 3656))

Included in the following conference series:

  • 939 Accesses

Abstract

This paper presents a method for estimating the orientation of planar text surfaces using the edge-direction distribution (EDD) extracted from the image as input to a neural network. We consider canonical rotations and we developed a mathematical model to analyze how the EDD changes with the rotation angle under orthographic projection. In order to improve performance and solve quadrant ambiguities, we adopt an active-vision approach by considering a pair of images (instead of only one) with a slight rotation difference between them. We then use the difference between the two EDDs as input to the network. Starting with camera-captured front-parallel images with text, we apply single-axis synthetic rotations to verify the validity of the EDD transform model and to train and test the network. The presented text-pose estimation method is intended to provide navigation guidance to a mobile robot capable of reading the textual content encountered in its environment.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ezaki, N., Bulacu, M., Schomaker, L.: Text detection from natural scene images: Towards a system for visually impaired persons. In: Proc. of 17th Int. Conf. on Pattern Recognition (ICPR 2004), pp. 683–686. IEEE CS, Cambridge (2004)

    Chapter  Google Scholar 

  2. Clark, P., Mirmehdi, M.: On the recovery of oriented documents from single images. In: Proc. of ACIVS 2002, Ghent, Belgium, pp. 190–197 (2002)

    Google Scholar 

  3. Myers, G.K., Bolles, R.C., Luong, Q.T., Herson, J.A.: Recognition of text in 3-d scenes. In: Proc. of 4th Symposium on Document Image Understanding Technology, Columbia, Maryland, USA (2001)

    Google Scholar 

  4. Garding, J.: Shape from texture and contour by weak isotropy. J. of Artificial Intelligence 64, 243–297 (1993)

    Article  MATH  MathSciNet  Google Scholar 

  5. Malik, J., Rosenholtz, R.: Computing local surface orientation and shape from texture for curved surfaces. Int. J. Computer Vision 23, 149–168 (1997)

    Article  Google Scholar 

  6. Clerc, M., Mallat, S.: Shape from texture and shading with wavelets. Dynamical Systems, Control, Coding, Computer Vision, Progress in Systems and Control Theory 25, 393–417 (1999)

    MathSciNet  Google Scholar 

  7. Super, B.J., Bovik, A.C.: Shape from texture using local spectral moments. IEEE Trans on PAMI 17, 333–343 (1995)

    Google Scholar 

  8. Schomaker, L., Bulacu, M.: Automatic writer identification using connected-component contours and edge-based features of uppercase western script. IEEE Trans on PAMI 26, 787–798 (2004)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. AI Institute, Groningen University, The Netherlands

    Marius Bulacu & Lambert Schomaker

Authors
  1. Marius Bulacu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lambert Schomaker
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Electrical and Computer Engineering Department, University of Waterloo,  

    Mohamed Kamel

  2. FEUP - Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, P.O. Box, 4200-465, Porto, Portugal

    Aurélio Campilho

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Bulacu, M., Schomaker, L. (2005). Text-Pose Estimation in 3D Using Edge-Direction Distributions. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2005. Lecture Notes in Computer Science, vol 3656. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11559573_77

Download citation

  • DOI: https://doi.org/10.1007/11559573_77

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-29069-8

  • Online ISBN: 978-3-540-31938-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation