Edge flow: A framework of boundary detection and image segmentation

W. Y. Ma; B. S. Manjunath

doi:10.1109/cvpr.1997.609409

Edge flow: A framework of boundary detection and image segmentation

W. Y. Ma, B. S. Manjunath

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

180 Citations (Scopus)

Abstract

A novel boundary detection scheme based on `edge flow' is proposed in this paper. This scheme utilizes a predictive coding model to identify the direction of change in color and texture at each image location at a given scale, and constructs an edge flow vector. By iteratively propagating the edge flow, the boundaries can be detected at image locations which encounter two opposite directions of flow in the stable state. A user defined image scale is the only significant control parameter that is needed by the algorithm. The scheme facilitates integration of color and texture into a single framework for boundary detection.

Original language	English
Pages (from-to)	744-749
Journal	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs	https://doi.org/10.1109/cvpr.1997.609409
Publication status	Published - 1997
Externally published	Yes
Event	Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - San Juan, PR, USA Duration: 17 Jun 1997 → 19 Jun 1997

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Access Output

10.1109/cvpr.1997.609409

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{d82d9cc59d014a1b852a4a206c329b41,

title = "Edge flow: A framework of boundary detection and image segmentation",

abstract = "A novel boundary detection scheme based on `edge flow' is proposed in this paper. This scheme utilizes a predictive coding model to identify the direction of change in color and texture at each image location at a given scale, and constructs an edge flow vector. By iteratively propagating the edge flow, the boundaries can be detected at image locations which encounter two opposite directions of flow in the stable state. A user defined image scale is the only significant control parameter that is needed by the algorithm. The scheme facilitates integration of color and texture into a single framework for boundary detection.",

author = "Ma, {W. Y.} and Manjunath, {B. S.}",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].; Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition ; Conference date: 17-06-1997 Through 19-06-1997",

year = "1997",

doi = "10.1109/cvpr.1997.609409",

language = "English",

pages = "744--749",

journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

issn = "1063-6919",

publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - Edge flow

T2 - Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

AU - Ma, W. Y.

AU - Manjunath, B. S.

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 1997

Y1 - 1997

N2 - A novel boundary detection scheme based on `edge flow' is proposed in this paper. This scheme utilizes a predictive coding model to identify the direction of change in color and texture at each image location at a given scale, and constructs an edge flow vector. By iteratively propagating the edge flow, the boundaries can be detected at image locations which encounter two opposite directions of flow in the stable state. A user defined image scale is the only significant control parameter that is needed by the algorithm. The scheme facilitates integration of color and texture into a single framework for boundary detection.

AB - A novel boundary detection scheme based on `edge flow' is proposed in this paper. This scheme utilizes a predictive coding model to identify the direction of change in color and texture at each image location at a given scale, and constructs an edge flow vector. By iteratively propagating the edge flow, the boundaries can be detected at image locations which encounter two opposite directions of flow in the stable state. A user defined image scale is the only significant control parameter that is needed by the algorithm. The scheme facilitates integration of color and texture into a single framework for boundary detection.

UR - http://www.scopus.com/inward/record.url?scp=0030719749&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0030719749&origin=recordpage

U2 - 10.1109/cvpr.1997.609409

DO - 10.1109/cvpr.1997.609409

M3 - RGC 21 - Publication in refereed journal

SN - 1063-6919

SP - 744

EP - 749

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Y2 - 17 June 1997 through 19 June 1997

ER -

Edge flow: A framework of boundary detection and image segmentation

Abstract

Bibliographical note

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this