Combining Statistical Measures to Find Image Text Regions

Paul Clark; A Sanfeliu; Majid Mirmehdi; J J Villanueva; M Vanrell; R Alquezar; J-O Eklundh; Y Aloimonos

Combining Statistical Measures to Find Image Text Regions

Paul Clark, A Sanfeliu, Majid Mirmehdi, J J Villanueva, M Vanrell, R Alquezar, J-O Eklundh, Y Aloimonos

Department of Computer Science

Research output: Contribution to journal › Article (Academic Journal) › peer-review

Abstract

We present a method based on statistical properties of local image pixels for focussing attention on regions of text in arbitrary scenes where the text plane is not necessarily fronto-parallel to the camera. This is particularly useful for Desktop or Wearable Computing applications. The statistical measures are cho sen to reveal charactersitic properties of text. We combine a number of localised measures using a neural network to classify each pixel as text or non-text. We demonstrate our results on typical images.

Translated title of the contribution	Combining Statistical Measures to Find Image Text Regions
Original language	English
Pages (from-to)	450-453
Journal	Proceedings of the 15th International Conference on Pattern Recognition
Publication status	Published - 2000

Bibliographical note

ISBN: 0796507506
Publisher: IEEE Computer Society
Name and Venue of Conference: Proceedings of the 15th International Conference on Pattern Recognition
Other identifier: 1000508

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=1000508

Handle.net

Persistent link

Cite this

@article{ef6398ab5b0942a6b3a881afed92927b,

title = "Combining Statistical Measures to Find Image Text Regions",

abstract = "We present a method based on statistical properties of local image pixels for focussing attention on regions of text in arbitrary scenes where the text plane is not necessarily fronto-parallel to the camera. This is particularly useful for Desktop or Wearable Computing applications. The statistical measures are cho sen to reveal charactersitic properties of text. We combine a number of localised measures using a neural network to classify each pixel as text or non-text. We demonstrate our results on typical images.",

author = "Paul Clark and A Sanfeliu and Majid Mirmehdi and Villanueva, {J J} and M Vanrell and R Alquezar and J-O Eklundh and Y Aloimonos",

note = "ISBN: 0796507506 Publisher: IEEE Computer Society Name and Venue of Conference: Proceedings of the 15th International Conference on Pattern Recognition Other identifier: 1000508",

year = "2000",

language = "English",

pages = "450--453",

journal = "Proceedings of the 15th International Conference on Pattern Recognition",

}

TY - JOUR

T1 - Combining Statistical Measures to Find Image Text Regions

AU - Clark, Paul

AU - Sanfeliu, A

AU - Mirmehdi, Majid

AU - Villanueva, J J

AU - Vanrell, M

AU - Alquezar, R

AU - Eklundh, J-O

AU - Aloimonos, Y

N1 - ISBN: 0796507506 Publisher: IEEE Computer Society Name and Venue of Conference: Proceedings of the 15th International Conference on Pattern Recognition Other identifier: 1000508

PY - 2000

Y1 - 2000

N2 - We present a method based on statistical properties of local image pixels for focussing attention on regions of text in arbitrary scenes where the text plane is not necessarily fronto-parallel to the camera. This is particularly useful for Desktop or Wearable Computing applications. The statistical measures are cho sen to reveal charactersitic properties of text. We combine a number of localised measures using a neural network to classify each pixel as text or non-text. We demonstrate our results on typical images.

AB - We present a method based on statistical properties of local image pixels for focussing attention on regions of text in arbitrary scenes where the text plane is not necessarily fronto-parallel to the camera. This is particularly useful for Desktop or Wearable Computing applications. The statistical measures are cho sen to reveal charactersitic properties of text. We combine a number of localised measures using a neural network to classify each pixel as text or non-text. We demonstrate our results on typical images.

M3 - Article (Academic Journal)

SP - 450

EP - 453

JO - Proceedings of the 15th International Conference on Pattern Recognition

JF - Proceedings of the 15th International Conference on Pattern Recognition

ER -

Combining Statistical Measures to Find Image Text Regions

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this