Generalized Hough transform for natural shapes

Ashok Samal; Jodi Edwards

doi:10.1016/S0167-8655(97)00023-8

Generalized Hough transform for natural shapes

Ashok Samal, Jodi Edwards

Research output: Contribution to journal › Article › peer-review

37 Scopus citations

Abstract

The Hough transform and their extensions can not adequately handle shapes characterized by the fact that different instances of the same shape are similar, but not identical. We present an extension to recognize natural shapes. It is based on the principle that natural shapes can be represented by two extremes: the inner extreme and the outer extreme.

Original language	English (US)
Pages (from-to)	473-480
Number of pages	8
Journal	Pattern Recognition Letters
Volume	18
Issue number	5
DOIs	https://doi.org/10.1016/S0167-8655(97)00023-8
State	Published - May 1997

Keywords

Hough transform
Local similarity
Natural shapes
Non-rigid shapes
Shape recognition
Similar shapes

ASJC Scopus subject areas

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1016/S0167-8655(97)00023-8

Cite this

@article{942d11704adf41f58fbca326bcedb94c,

title = "Generalized Hough transform for natural shapes",

abstract = "The Hough transform and their extensions can not adequately handle shapes characterized by the fact that different instances of the same shape are similar, but not identical. We present an extension to recognize natural shapes. It is based on the principle that natural shapes can be represented by two extremes: the inner extreme and the outer extreme.",

keywords = "Hough transform, Local similarity, Natural shapes, Non-rigid shapes, Shape recognition, Similar shapes",

author = "Ashok Samal and Jodi Edwards",

note = "Funding Information: The technique has been extended to detect curves (Merlin and Farber, 1975) and arbitrary 2-D shapes (Ballard, 1981). The generalized Hough transform (GHT) (Ballard, 1981) is robust for rigid shapes with fixed scale and orientation. Brute force techniques can be used to handle shapes at different scales and orientations. Several approaches have been ' Correspondinga uthor. E-mail: [email protected]. I This work is supported in part by NSF grants CDA-9022445 and USE-9152764.",

year = "1997",

month = may,

doi = "10.1016/S0167-8655(97)00023-8",

language = "English (US)",

volume = "18",

pages = "473--480",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

publisher = "Elsevier B.V.",

number = "5",

}

TY - JOUR

T1 - Generalized Hough transform for natural shapes

AU - Samal, Ashok

AU - Edwards, Jodi

N1 - Funding Information: The technique has been extended to detect curves (Merlin and Farber, 1975) and arbitrary 2-D shapes (Ballard, 1981). The generalized Hough transform (GHT) (Ballard, 1981) is robust for rigid shapes with fixed scale and orientation. Brute force techniques can be used to handle shapes at different scales and orientations. Several approaches have been ' Correspondinga uthor. E-mail: [email protected]. I This work is supported in part by NSF grants CDA-9022445 and USE-9152764.

PY - 1997/5

Y1 - 1997/5

N2 - The Hough transform and their extensions can not adequately handle shapes characterized by the fact that different instances of the same shape are similar, but not identical. We present an extension to recognize natural shapes. It is based on the principle that natural shapes can be represented by two extremes: the inner extreme and the outer extreme.

AB - The Hough transform and their extensions can not adequately handle shapes characterized by the fact that different instances of the same shape are similar, but not identical. We present an extension to recognize natural shapes. It is based on the principle that natural shapes can be represented by two extremes: the inner extreme and the outer extreme.

KW - Hough transform

KW - Local similarity

KW - Natural shapes

KW - Non-rigid shapes

KW - Shape recognition

KW - Similar shapes

UR - http://www.scopus.com/inward/record.url?scp=0031145586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031145586&partnerID=8YFLogxK

U2 - 10.1016/S0167-8655(97)00023-8

DO - 10.1016/S0167-8655(97)00023-8

M3 - Article

AN - SCOPUS:0031145586

SN - 0167-8655

VL - 18

SP - 473

EP - 480

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

IS - 5

ER -

Generalized Hough transform for natural shapes

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this