Advanced

Robustness and specificity in object detection

Eriksson, Anders P LU and Åström, Karl LU (2004) 17th International Conference on Pattern Recognition, 2004 In Proceedings of the 17th International Conference on Pattern Recognition p.87-90
Abstract
In this paper, we discuss the role of robustness to geometric conformity versus specificity in machine learning. The key observation made here is that object variation due to appearance and due to geometric deformation are often, for good reasons, intermixed in typical object detection applications. In the paper, we consider a whole range of differently specific object detectors. It is shown that such detectors vary in their robustness to geometric deformation and also their specificity. Such detectors can then be used in a cascade, where coarse detectors operate on a less-specific and more robust scale. This makes it possible to use coarse sampling of the space of geometric transformations. Further on more-specific and less robust... (More)
In this paper, we discuss the role of robustness to geometric conformity versus specificity in machine learning. The key observation made here is that object variation due to appearance and due to geometric deformation are often, for good reasons, intermixed in typical object detection applications. In the paper, we consider a whole range of differently specific object detectors. It is shown that such detectors vary in their robustness to geometric deformation and also their specificity. Such detectors can then be used in a cascade, where coarse detectors operate on a less-specific and more robust scale. This makes it possible to use coarse sampling of the space of geometric transformations. Further on more-specific and less robust detectors are used. This requires as input the detections at a coarser scale combined with an optimization search step. In the paper, it is also discussed how such detectors can automatically be obtained from a coarsely defined database of ground truth (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
optimization search, geometric transformations, coarse detectors, geometric deformation, machine learning, robustness, object detection
in
Proceedings of the 17th International Conference on Pattern Recognition
pages
87 - 90
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
17th International Conference on Pattern Recognition, 2004
external identifiers
  • WOS:000223879500022
  • Scopus:10044295822
ISBN
0-7695-2128-2
DOI
10.1109/ICPR.2004.1334475
language
English
LU publication?
yes
id
d98a7b7d-7385-44fb-b527-b733ce1b2c82 (old id 615002)
date added to LUP
2007-11-26 18:19:19
date last changed
2016-10-13 04:40:22
@misc{d98a7b7d-7385-44fb-b527-b733ce1b2c82,
  abstract     = {In this paper, we discuss the role of robustness to geometric conformity versus specificity in machine learning. The key observation made here is that object variation due to appearance and due to geometric deformation are often, for good reasons, intermixed in typical object detection applications. In the paper, we consider a whole range of differently specific object detectors. It is shown that such detectors vary in their robustness to geometric deformation and also their specificity. Such detectors can then be used in a cascade, where coarse detectors operate on a less-specific and more robust scale. This makes it possible to use coarse sampling of the space of geometric transformations. Further on more-specific and less robust detectors are used. This requires as input the detections at a coarser scale combined with an optimization search step. In the paper, it is also discussed how such detectors can automatically be obtained from a coarsely defined database of ground truth},
  author       = {Eriksson, Anders P and Åström, Karl},
  isbn         = {0-7695-2128-2},
  keyword      = {optimization search,geometric transformations,coarse detectors,geometric deformation,machine learning,robustness,object detection},
  language     = {eng},
  pages        = {87--90},
  publisher    = {ARRAY(0x9524720)},
  series       = {Proceedings of the 17th International Conference on Pattern Recognition},
  title        = {Robustness and specificity in object detection},
  url          = {http://dx.doi.org/10.1109/ICPR.2004.1334475},
  year         = {2004},
}