Shape-based recognition of wiry objects

Owen Carmichael, Martial Hebert

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

We present an approach to the recognition of complex-shaped objects in cluttered environments based on edge information. We first use example images of a target object in typical environments to train a classifier cascade that determines whether edge pixels in an image belong to an instance of the desired object or the clutter. Presented with a novel image, we use the cascade to discard clutter edge pixels and group the object edge pixels into overall detections of the object. The features used for the edge pixel classification are localized, sparse edge density operations. Experiments validate the effectiveness of the technique for recognition of a set of complex objects in a variety of cluttered indoor scenes under arbitrary out-of-image-plane rotation. Furthermore, our experiments suggest that the technique is robust to variations between training and testing environments and is efficient at runtime.

Original languageEnglish (US)
Pages (from-to)1537-1552
Number of pages16
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume26
Issue number12
DOIs
StatePublished - Dec 2004
Externally publishedYes

Fingerprint

Pixels
Pixel
Clutter
Cascade
Classifiers
Experiments
Experiment
Object
Testing
Classifier
Target
Arbitrary

Keywords

  • Classifier design and evaluation
  • Edge and feature detection
  • Object recognition
  • Shape

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Cite this

Shape-based recognition of wiry objects. / Carmichael, Owen; Hebert, Martial.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 12, 12.2004, p. 1537-1552.

Research output: Contribution to journalArticle

Carmichael, Owen ; Hebert, Martial. / Shape-based recognition of wiry objects. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 2004 ; Vol. 26, No. 12. pp. 1537-1552.
@article{ecc86ee904594d2a9ed9600e9e345486,
title = "Shape-based recognition of wiry objects",
abstract = "We present an approach to the recognition of complex-shaped objects in cluttered environments based on edge information. We first use example images of a target object in typical environments to train a classifier cascade that determines whether edge pixels in an image belong to an instance of the desired object or the clutter. Presented with a novel image, we use the cascade to discard clutter edge pixels and group the object edge pixels into overall detections of the object. The features used for the edge pixel classification are localized, sparse edge density operations. Experiments validate the effectiveness of the technique for recognition of a set of complex objects in a variety of cluttered indoor scenes under arbitrary out-of-image-plane rotation. Furthermore, our experiments suggest that the technique is robust to variations between training and testing environments and is efficient at runtime.",
keywords = "Classifier design and evaluation, Edge and feature detection, Object recognition, Shape",
author = "Owen Carmichael and Martial Hebert",
year = "2004",
month = "12",
doi = "10.1109/TPAMI.2004.128",
language = "English (US)",
volume = "26",
pages = "1537--1552",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "12",

}

TY - JOUR

T1 - Shape-based recognition of wiry objects

AU - Carmichael, Owen

AU - Hebert, Martial

PY - 2004/12

Y1 - 2004/12

N2 - We present an approach to the recognition of complex-shaped objects in cluttered environments based on edge information. We first use example images of a target object in typical environments to train a classifier cascade that determines whether edge pixels in an image belong to an instance of the desired object or the clutter. Presented with a novel image, we use the cascade to discard clutter edge pixels and group the object edge pixels into overall detections of the object. The features used for the edge pixel classification are localized, sparse edge density operations. Experiments validate the effectiveness of the technique for recognition of a set of complex objects in a variety of cluttered indoor scenes under arbitrary out-of-image-plane rotation. Furthermore, our experiments suggest that the technique is robust to variations between training and testing environments and is efficient at runtime.

AB - We present an approach to the recognition of complex-shaped objects in cluttered environments based on edge information. We first use example images of a target object in typical environments to train a classifier cascade that determines whether edge pixels in an image belong to an instance of the desired object or the clutter. Presented with a novel image, we use the cascade to discard clutter edge pixels and group the object edge pixels into overall detections of the object. The features used for the edge pixel classification are localized, sparse edge density operations. Experiments validate the effectiveness of the technique for recognition of a set of complex objects in a variety of cluttered indoor scenes under arbitrary out-of-image-plane rotation. Furthermore, our experiments suggest that the technique is robust to variations between training and testing environments and is efficient at runtime.

KW - Classifier design and evaluation

KW - Edge and feature detection

KW - Object recognition

KW - Shape

UR - http://www.scopus.com/inward/record.url?scp=9244248154&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=9244248154&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2004.128

DO - 10.1109/TPAMI.2004.128

M3 - Article

VL - 26

SP - 1537

EP - 1552

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 12

ER -