Gradient flows and geometric active contour models

Satyanad Kichenassamy; Arun Kumar; Peter Olver; Allen Tannenbaum; Anthony Yezzi

Gradient flows and geometric active contour models

Satyanad Kichenassamy
, Arun Kumar
, Peter Olver
, Allen Tannenbaum
, Anthony Yezzi

School of Mathematics

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

567 Scopus citations

Abstract

In this paper, we analyze the geometric active contour models discussed in [6, 18] from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new feature-based Riemannian metrics. This leads to a novel snake paradigm in which the feature of interest may be considered to lie at the bottom of a potential well. Thus the snake is attracted very naturally and efficiently to the desired feature. Moreover, we consider some 3-D active surface models based on these ideas.

Original language	English (US)
Title of host publication	IEEE International Conference on Computer Vision
Editors	Anon
Publisher	IEEE
Pages	810-815
Number of pages	6
State	Published - Jan 1 1995
Event	Proceedings of the 5th International Conference on Computer Vision - Cambridge, MA, USA Duration: Jun 20 1995 → Jun 23 1995

Other

Other	Proceedings of the 5th International Conference on Computer Vision
City	Cambridge, MA, USA
Period	6/20/95 → 6/23/95

Find It

Find It at U of M Libraries

Cite this

@inproceedings{6bec61662968454fa343fcd2826b8305,

title = "Gradient flows and geometric active contour models",

abstract = "In this paper, we analyze the geometric active contour models discussed in [6, 18] from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new feature-based Riemannian metrics. This leads to a novel snake paradigm in which the feature of interest may be considered to lie at the bottom of a potential well. Thus the snake is attracted very naturally and efficiently to the desired feature. Moreover, we consider some 3-D active surface models based on these ideas.",

author = "Satyanad Kichenassamy and Arun Kumar and Peter Olver and Allen Tannenbaum and Anthony Yezzi",

year = "1995",

month = jan,

day = "1",

language = "English (US)",

pages = "810--815",

editor = "Anon",

booktitle = "IEEE International Conference on Computer Vision",

publisher = "IEEE",

note = "Proceedings of the 5th International Conference on Computer Vision ; Conference date: 20-06-1995 Through 23-06-1995",

}

TY - GEN

T1 - Gradient flows and geometric active contour models

AU - Kichenassamy, Satyanad

AU - Kumar, Arun

AU - Olver, Peter

AU - Tannenbaum, Allen

AU - Yezzi, Anthony

PY - 1995/1/1

Y1 - 1995/1/1

N2 - In this paper, we analyze the geometric active contour models discussed in [6, 18] from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new feature-based Riemannian metrics. This leads to a novel snake paradigm in which the feature of interest may be considered to lie at the bottom of a potential well. Thus the snake is attracted very naturally and efficiently to the desired feature. Moreover, we consider some 3-D active surface models based on these ideas.

AB - In this paper, we analyze the geometric active contour models discussed in [6, 18] from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new feature-based Riemannian metrics. This leads to a novel snake paradigm in which the feature of interest may be considered to lie at the bottom of a potential well. Thus the snake is attracted very naturally and efficiently to the desired feature. Moreover, we consider some 3-D active surface models based on these ideas.

UR - https://www.scopus.com/pages/publications/0029215266

UR - https://www.scopus.com/pages/publications/0029215266#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:0029215266

SP - 810

EP - 815

BT - IEEE International Conference on Computer Vision

A2 - Anon, null

PB - IEEE

T2 - Proceedings of the 5th International Conference on Computer Vision

Y2 - 20 June 1995 through 23 June 1995

ER -

Gradient flows and geometric active contour models

Abstract

Other

Find It

Other files and links

Fingerprint

Cite this