Recognition of image patterns generated by a stochastic object-replacement model

JA Bangham; RW Harvey; G Tattersall

doi:10.1109/ICIP.1998.727330

Recognition of image patterns generated by a stochastic object-replacement model

JA Bangham, RW Harvey, G Tattersall

Research output: Contribution to conference › Other › peer-review

Abstract

We discuss targets in images formed from a pattern of partial occlusions. The targets vary between examples. It is shown that a new scale-space method is substantially more effective than, for example, normalised cross-correlation for distinguishing such a target from background and estimating its position. We believe such targets represent a good model of many objects.

Original language	English
Pages	576
Number of pages	1
DOIs	https://doi.org/10.1109/ICIP.1998.727330
Publication status	Published - 1998
Event	IEEE Conference on Image Processing - Chicago, United States Duration: 4 Oct 1998 → 7 Oct 1998

Conference

Conference	IEEE Conference on Image Processing
Country/Territory	United States
City	Chicago
Period	4/10/98 → 7/10/98

Access to Document

10.1109/ICIP.1998.727330

Cite this

@conference{397905d576c04d5f8b97bbf2183425dd,

title = "Recognition of image patterns generated by a stochastic object-replacement model",

abstract = "We discuss targets in images formed from a pattern of partial occlusions. The targets vary between examples. It is shown that a new scale-space method is substantially more effective than, for example, normalised cross-correlation for distinguishing such a target from background and estimating its position. We believe such targets represent a good model of many objects.",

author = "JA Bangham and RW Harvey and G Tattersall",

year = "1998",

doi = "10.1109/ICIP.1998.727330",

language = "English",

pages = "576",

note = "IEEE Conference on Image Processing ; Conference date: 04-10-1998 Through 07-10-1998",

}

TY - CONF

T1 - Recognition of image patterns generated by a stochastic object-replacement model

AU - Bangham, JA

AU - Harvey, RW

AU - Tattersall, G

PY - 1998

Y1 - 1998

N2 - We discuss targets in images formed from a pattern of partial occlusions. The targets vary between examples. It is shown that a new scale-space method is substantially more effective than, for example, normalised cross-correlation for distinguishing such a target from background and estimating its position. We believe such targets represent a good model of many objects.

AB - We discuss targets in images formed from a pattern of partial occlusions. The targets vary between examples. It is shown that a new scale-space method is substantially more effective than, for example, normalised cross-correlation for distinguishing such a target from background and estimating its position. We believe such targets represent a good model of many objects.

U2 - 10.1109/ICIP.1998.727330

DO - 10.1109/ICIP.1998.727330

M3 - Other

SP - 576

T2 - IEEE Conference on Image Processing

Y2 - 4 October 1998 through 7 October 1998

ER -