A framework towards real-time detection and tracking of text

Merino Carlos; Majid Mirmehdi

A framework towards real-time detection and tracking of text

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

Abstract

We present a near realtime text tracking system capable of detecting and tracking text on outdoor shop signs or indoor notices, at rates of up to 15 frames per second (for generous 640x480 images), depending on scene complexity. The method is based on extracting text regions using a novel tree-based connected component filtering approach, combined with the Eigen-Transform texture descriptor. The method can efficiently handle dark and light text on light and dark backgrounds. Particle filter tracking is then used to follow the text, including SIFT matching to maintain region identity in the face of multiple regions of interest, fast displacements, and erratic motions.

Translated title of the contribution	A framework towards real-time detection and tracking of text
Original language	English
Title of host publication	Second International Workshop on Camera-Based Document Analysis and Recognition (CBDAR 2007)
Publication status	Published - 2007

Bibliographical note

Other page information: 10-17
Conference Proceedings/Title of Journal: Second International Workshop on Camera-Based Document Analysis and Recognition (CBDAR 2007)
Other identifier: 2000721

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=2000721

Handle.net

Persistent link

Cite this

@inproceedings{a8f0e901f54d4625a705f08909c02f1e,

title = "A framework towards real-time detection and tracking of text",

abstract = "We present a near realtime text tracking system capable of detecting and tracking text on outdoor shop signs or indoor notices, at rates of up to 15 frames per second (for generous 640x480 images), depending on scene complexity. The method is based on extracting text regions using a novel tree-based connected component filtering approach, combined with the Eigen-Transform texture descriptor. The method can efficiently handle dark and light text on light and dark backgrounds. Particle filter tracking is then used to follow the text, including SIFT matching to maintain region identity in the face of multiple regions of interest, fast displacements, and erratic motions. ",

author = "Merino Carlos and Majid Mirmehdi",

note = "Other page information: 10-17 Conference Proceedings/Title of Journal: Second International Workshop on Camera-Based Document Analysis and Recognition (CBDAR 2007) Other identifier: 2000721",

year = "2007",

language = "English",

booktitle = "Second International Workshop on Camera-Based Document Analysis and Recognition (CBDAR 2007)",

}

TY - GEN

T1 - A framework towards real-time detection and tracking of text

AU - Carlos, Merino

AU - Mirmehdi, Majid

N1 - Other page information: 10-17 Conference Proceedings/Title of Journal: Second International Workshop on Camera-Based Document Analysis and Recognition (CBDAR 2007) Other identifier: 2000721

PY - 2007

Y1 - 2007

N2 - We present a near realtime text tracking system capable of detecting and tracking text on outdoor shop signs or indoor notices, at rates of up to 15 frames per second (for generous 640x480 images), depending on scene complexity. The method is based on extracting text regions using a novel tree-based connected component filtering approach, combined with the Eigen-Transform texture descriptor. The method can efficiently handle dark and light text on light and dark backgrounds. Particle filter tracking is then used to follow the text, including SIFT matching to maintain region identity in the face of multiple regions of interest, fast displacements, and erratic motions.

AB - We present a near realtime text tracking system capable of detecting and tracking text on outdoor shop signs or indoor notices, at rates of up to 15 frames per second (for generous 640x480 images), depending on scene complexity. The method is based on extracting text regions using a novel tree-based connected component filtering approach, combined with the Eigen-Transform texture descriptor. The method can efficiently handle dark and light text on light and dark backgrounds. Particle filter tracking is then used to follow the text, including SIFT matching to maintain region identity in the face of multiple regions of interest, fast displacements, and erratic motions.

M3 - Conference Contribution (Conference Proceeding)

BT - Second International Workshop on Camera-Based Document Analysis and Recognition (CBDAR 2007)

ER -

A framework towards real-time detection and tracking of text

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this