Finding people and animals by guided assembly

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper describes a new representation for people and animals, called a body plan. The representation is an organized collection of grouping hints obtained from constraints on color, texture, shape, and geometrical relations. Body plans can be learned from image data, using established statistical learning techniques. Body plans are well adapted to segmentation and recognition in complex environments, such as the huge libraries of digitized images now becoming widely available. Two specific applications of body plans are presented: an algorithm that determines whether an image depicts a scantily clad human and an algorithm that learns and uses a body plan to find pictures of horses. Both algorithms demonstrate excellent performance on large, poorly controlled input data.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Image Processing
PublisherIEEE Comp Soc
Pages5-8
Number of pages4
Volume3
StatePublished - 1997
Externally publishedYes
EventProceedings of the 1997 International Conference on Image Processing. Part 2 (of 3) - Santa Barbara, CA, USA
Duration: Oct 26 1997Oct 29 1997

Other

OtherProceedings of the 1997 International Conference on Image Processing. Part 2 (of 3)
CitySanta Barbara, CA, USA
Period10/26/9710/29/97

Fingerprint

Animals
Textures
Color

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Forsyth, D. A., & Fleck, M. M. (1997). Finding people and animals by guided assembly. In IEEE International Conference on Image Processing (Vol. 3, pp. 5-8). IEEE Comp Soc.

Finding people and animals by guided assembly. / Forsyth, David Alexander; Fleck, Margaret M.

IEEE International Conference on Image Processing. Vol. 3 IEEE Comp Soc, 1997. p. 5-8.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Forsyth, DA & Fleck, MM 1997, Finding people and animals by guided assembly. in IEEE International Conference on Image Processing. vol. 3, IEEE Comp Soc, pp. 5-8, Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3), Santa Barbara, CA, USA, 10/26/97.
Forsyth DA, Fleck MM. Finding people and animals by guided assembly. In IEEE International Conference on Image Processing. Vol. 3. IEEE Comp Soc. 1997. p. 5-8
Forsyth, David Alexander ; Fleck, Margaret M. / Finding people and animals by guided assembly. IEEE International Conference on Image Processing. Vol. 3 IEEE Comp Soc, 1997. pp. 5-8
@inproceedings{b186fafaf2064ec9950b87f71c7a3ed6,
title = "Finding people and animals by guided assembly",
abstract = "This paper describes a new representation for people and animals, called a body plan. The representation is an organized collection of grouping hints obtained from constraints on color, texture, shape, and geometrical relations. Body plans can be learned from image data, using established statistical learning techniques. Body plans are well adapted to segmentation and recognition in complex environments, such as the huge libraries of digitized images now becoming widely available. Two specific applications of body plans are presented: an algorithm that determines whether an image depicts a scantily clad human and an algorithm that learns and uses a body plan to find pictures of horses. Both algorithms demonstrate excellent performance on large, poorly controlled input data.",
author = "Forsyth, {David Alexander} and Fleck, {Margaret M}",
year = "1997",
language = "English (US)",
volume = "3",
pages = "5--8",
booktitle = "IEEE International Conference on Image Processing",
publisher = "IEEE Comp Soc",

}

TY - GEN

T1 - Finding people and animals by guided assembly

AU - Forsyth, David Alexander

AU - Fleck, Margaret M

PY - 1997

Y1 - 1997

N2 - This paper describes a new representation for people and animals, called a body plan. The representation is an organized collection of grouping hints obtained from constraints on color, texture, shape, and geometrical relations. Body plans can be learned from image data, using established statistical learning techniques. Body plans are well adapted to segmentation and recognition in complex environments, such as the huge libraries of digitized images now becoming widely available. Two specific applications of body plans are presented: an algorithm that determines whether an image depicts a scantily clad human and an algorithm that learns and uses a body plan to find pictures of horses. Both algorithms demonstrate excellent performance on large, poorly controlled input data.

AB - This paper describes a new representation for people and animals, called a body plan. The representation is an organized collection of grouping hints obtained from constraints on color, texture, shape, and geometrical relations. Body plans can be learned from image data, using established statistical learning techniques. Body plans are well adapted to segmentation and recognition in complex environments, such as the huge libraries of digitized images now becoming widely available. Two specific applications of body plans are presented: an algorithm that determines whether an image depicts a scantily clad human and an algorithm that learns and uses a body plan to find pictures of horses. Both algorithms demonstrate excellent performance on large, poorly controlled input data.

UR - http://www.scopus.com/inward/record.url?scp=0031364411&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031364411&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0031364411

VL - 3

SP - 5

EP - 8

BT - IEEE International Conference on Image Processing

PB - IEEE Comp Soc

ER -