On representing edge structure for model matching

T. F. Cootes; C. J. Taylor

On representing edge structure for model matching

Research output: Chapter in Book/Conference proceeding › Conference contribution

Abstract

We show how a novel, non-linear representation of edge structure can be used to improve the performance of model matching algorithms and object verification/recognition tasks. Rather than represent the image structure using intensity values or gradients, we use a measure which indicates the orientation of structures at each pixel, together with an indication of how reliable the orientation estimate is. Orientations in flat, noisy regions tend to be penalised whereas those near strong edges are favoured. We demonstrate that this representation leads to more accurate and reliable matching between models and new images, and leads to better recognition/verification of faces in an access control task.

Original language	English
Title of host publication	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition\|Proc IEEE Comput Soc Conf Comput Vision Pattern Recognit
Publisher	IEEE
Pages	I1114-I1119
Number of pages	6
Volume	1
Publication status	Published - 2001
Event	2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Kauai, HI Duration: 1 Jul 2001 → … http://<Go to ISI>://ISIP:000184694200150

Publication series

Name	Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher	IEEE

Conference

Conference	2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
City	Kauai, HI
Period	1/07/01 → …
Internet address	http://<Go to ISI>://ISIP:000184694200150

Cite this

Cootes, T. F., & Taylor, C. J. (2001). On representing edge structure for model matching. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|Proc IEEE Comput Soc Conf Comput Vision Pattern Recognit (Vol. 1, pp. I1114-I1119). (Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE.

@inproceedings{ef752e5f48544934bc05ce7883a97202,

title = "On representing edge structure for model matching",

abstract = "We show how a novel, non-linear representation of edge structure can be used to improve the performance of model matching algorithms and object verification/recognition tasks. Rather than represent the image structure using intensity values or gradients, we use a measure which indicates the orientation of structures at each pixel, together with an indication of how reliable the orientation estimate is. Orientations in flat, noisy regions tend to be penalised whereas those near strong edges are favoured. We demonstrate that this representation leads to more accurate and reliable matching between models and new images, and leads to better recognition/verification of faces in an access control task.",

author = "Cootes, \{T. F.\} and Taylor, \{C. J.\}",

note = "Conference on Computer Vision and Pattern Recognition DEC 08-14, 2001 KAUAI, HAWAII; 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition ; Conference date: 01-07-2001",

year = "2001",

language = "English",

volume = "1",

series = "Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE",

pages = "I1114--I1119",

booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|Proc IEEE Comput Soc Conf Comput Vision Pattern Recognit",

address = "United States",

url = "http://<Go to ISI>://ISIP:000184694200150",

}

Cootes, TF & Taylor, CJ 2001, On representing edge structure for model matching. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|Proc IEEE Comput Soc Conf Comput Vision Pattern Recognit. vol. 1, Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, pp. I1114-I1119, 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, HI, 1/07/01.

On representing edge structure for model matching. / Cootes, T. F.; Taylor, C. J.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|Proc IEEE Comput Soc Conf Comput Vision Pattern Recognit. Vol. 1 IEEE, 2001. p. I1114-I1119 (Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Conference proceeding › Conference contribution

TY - GEN

T1 - On representing edge structure for model matching

AU - Cootes, T. F.

AU - Taylor, C. J.

N1 - Conference on Computer Vision and Pattern Recognition DEC 08-14, 2001 KAUAI, HAWAII

PY - 2001

Y1 - 2001

N2 - We show how a novel, non-linear representation of edge structure can be used to improve the performance of model matching algorithms and object verification/recognition tasks. Rather than represent the image structure using intensity values or gradients, we use a measure which indicates the orientation of structures at each pixel, together with an indication of how reliable the orientation estimate is. Orientations in flat, noisy regions tend to be penalised whereas those near strong edges are favoured. We demonstrate that this representation leads to more accurate and reliable matching between models and new images, and leads to better recognition/verification of faces in an access control task.

AB - We show how a novel, non-linear representation of edge structure can be used to improve the performance of model matching algorithms and object verification/recognition tasks. Rather than represent the image structure using intensity values or gradients, we use a measure which indicates the orientation of structures at each pixel, together with an indication of how reliable the orientation estimate is. Orientations in flat, noisy regions tend to be penalised whereas those near strong edges are favoured. We demonstrate that this representation leads to more accurate and reliable matching between models and new images, and leads to better recognition/verification of faces in an access control task.

M3 - Conference contribution

VL - 1

T3 - Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - I1114-I1119

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|Proc IEEE Comput Soc Conf Comput Vision Pattern Recognit

PB - IEEE

T2 - 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Y2 - 1 July 2001

ER -

On representing edge structure for model matching

Abstract

Publication series

Conference

Fingerprint

Cite this