Weak Hypotheses and Boosting for Generic Object
Detection and Recognition 1st edition by Opelt,
Fussenegger, Pinz, Auer ISBN 3540219835
9783540219835 pdf download
https://ebookball.com/product/weak-hypotheses-and-boosting-for-
generic-object-detection-and-recognition-1st-edition-by-opelt-
fussenegger-pinz-auer-isbn-3540219835-9783540219835-14506/
Explore and download more ebooks or textbooks
at ebookball.com
, Get Your Digital Files Instantly: PDF, ePub, MOBI and More
Quick Digital Downloads: PDF, ePub, MOBI and Other Formats
View Invariant Recognition Using Corresponding Object Fragments 1st
edition by Evgeniy Bart, Evgeny Byvatov, Shimon Ullman ISBN 3540219835
9783540219835
https://ebookball.com/product/view-invariant-recognition-using-
corresponding-object-fragments-1st-edition-by-evgeniy-bart-
evgeny-byvatov-shimon-ullman-isbn-3540219835-9783540219835-10540/
Texture Boundary Detection for Real Time Tracking 1st edition by Ali
Shahrokni, Tom Drummond, Pascal Fua ISBN 3540219835 9783540219835
https://ebookball.com/product/texture-boundary-detection-for-
real-time-tracking-1st-edition-by-ali-shahrokni-tom-drummond-
pascal-fua-isbn-3540219835-9783540219835-14004/
Face Recognition from Facial Surface Metric 1st edition by Alexander
Bronstein, Michael Bronstein, Alon Spira, Ron Kimmel ISBN 3540219835
9783540219835
https://ebookball.com/product/face-recognition-from-facial-
surface-metric-1st-edition-by-alexander-bronstein-michael-
bronstein-alon-spira-ron-kimmel-
isbn-3540219835-9783540219835-14040/
Matching Tensors for Automatic Correspondence and Registration 1st
edition by Ajmal Mian, Mohammed Bennamoun, Robyn Owens ISBN 35402
9783540219835
https://ebookball.com/product/matching-tensors-for-automatic-
correspondence-and-registration-1st-edition-by-ajmal-mian-
mohammed-bennamoun-robyn-owens-
isbn-3540219835-9783540219835-14176/
,A Combined PDE and Texture Synthesis Approach to Inpainting 1st
edition by Harald Grossauer ISBN 3540219835 9783540219835
https://ebookball.com/product/a-combined-pde-and-texture-
synthesis-approach-to-inpainting-1st-edition-by-harald-grossauer-
isbn-3540219835-9783540219835-9544/
Weighted Minimal Hypersurfaces and Their Applications in Computer
Vision 1st edition by Bastian Goldlucke, Marcus Magnor ISBN 3540219835
9783540219835
https://ebookball.com/product/weighted-minimal-hypersurfaces-and-
their-applications-in-computer-vision-1st-edition-by-bastian-
goldlucke-marcus-magnor-isbn-3540219835-9783540219835-13260/
Stitching and Reconstruction of Linear Pushbroom Panoramic Images for
Planar Scenes 1st edition by Chu Song Chen, Yu Ting Chen, Fay Huang
ISBN 3540219835 9783540219835
https://ebookball.com/product/stitching-and-reconstruction-of-
linear-pushbroom-panoramic-images-for-planar-scenes-1st-edition-
by-chu-song-chen-yu-ting-chen-fay-huang-
isbn-3540219835-9783540219835-11866/
A Framework for Pencil of Points Structure from Motion 1st edition by
Adrien Bartoli, Mathieu Coquerelle, Peter Sturm ISBN 3540219835
9783540219835
https://ebookball.com/product/a-framework-for-pencil-of-points-
structure-from-motion-1st-edition-by-adrien-bartoli-mathieu-
coquerelle-peter-sturm-isbn-3540219835-9783540219835-14264/
Spatially Homogeneous Dynamic Textures 1st edition by Gianfranco
Doretto, Eagle Jones, Stefano Soatto ISBN 3540219835 9783540219835
https://ebookball.com/product/spatially-homogeneous-dynamic-
textures-1st-edition-by-gianfranco-doretto-eagle-jones-stefano-
soatto-isbn-3540219835-9783540219835-9930/
, Weak Hypotheses and Boosting for Generic
Object Detection and Recognition
A. Opelt1,2 , M. Fussenegger1,2 , A. Pinz2 , and P. Auer1
1
Institute of Computer Science,
8700 Leoben, Austria
{auer,andreas.opelt}@unileoben.ac.at
2
Institute of Electrical Measurement and Measurement Signal Processing,
8010 Graz, Austria
{fussenegger,opelt,pinz}@emt.tugraz.at
Abstract. In this paper we describe the first stage of a new learning
system for object detection and recognition. For our system we propose
Boosting [5] as the underlying learning technique. This allows the use of
very diverse sets of visual features in the learning process within a com-
mon framework: Boosting — together with a weak hypotheses finder —
may choose very inhomogeneous features as most relevant for combina-
tion into a final hypothesis. As another advantage the weak hypotheses
finder may search the weak hypotheses space without explicit calculation
of all available hypotheses, reducing computation time. This contrasts
the related work of Agarwal and Roth [1] where Winnow was used as
learning algorithm and all weak hypotheses were calculated explicitly.
In our first empirical evaluation we use four types of local descriptors:
two basic ones consisting of a set of grayvalues and intensity moments
and two high level descriptors: moment invariants [8] and SIFTs [12].
The descriptors are calculated from local patches detected by an inter-
est point operator. The weak hypotheses finder selects one of the local
patches and one type of local descriptor and efficiently searches for the
most discriminative similarity threshold. This differs from other work on
Boosting for object recognition where simple rectangular hypotheses [22]
or complex classifiers [20] have been used. In relatively simple images,
where the objects are prominent, our approach yields results comparable
to the state-of-the-art [3]. But we also obtain very good results on more
complex images, where the objects are located in arbitrary positions,
poses, and scales in the images. These results indicate that our flexible
approach, which also allows the inclusion of features from segmented re-
gions and even spatial relationships, leads us a significant step towards
generic object recognition.
1 Introduction
We believe that a learning component is a necessary part of any generic ob-
ject recognition system. In this paper we investigate a principle approach for
learning objects in still images which allows the use of flexible and extendible
T. Pajdla and J. Matas (Eds.): ECCV 2004, LNCS 3022, pp. 71–84, 2004.
c Springer-Verlag Berlin Heidelberg 2004
Detection and Recognition 1st edition by Opelt,
Fussenegger, Pinz, Auer ISBN 3540219835
9783540219835 pdf download
https://ebookball.com/product/weak-hypotheses-and-boosting-for-
generic-object-detection-and-recognition-1st-edition-by-opelt-
fussenegger-pinz-auer-isbn-3540219835-9783540219835-14506/
Explore and download more ebooks or textbooks
at ebookball.com
, Get Your Digital Files Instantly: PDF, ePub, MOBI and More
Quick Digital Downloads: PDF, ePub, MOBI and Other Formats
View Invariant Recognition Using Corresponding Object Fragments 1st
edition by Evgeniy Bart, Evgeny Byvatov, Shimon Ullman ISBN 3540219835
9783540219835
https://ebookball.com/product/view-invariant-recognition-using-
corresponding-object-fragments-1st-edition-by-evgeniy-bart-
evgeny-byvatov-shimon-ullman-isbn-3540219835-9783540219835-10540/
Texture Boundary Detection for Real Time Tracking 1st edition by Ali
Shahrokni, Tom Drummond, Pascal Fua ISBN 3540219835 9783540219835
https://ebookball.com/product/texture-boundary-detection-for-
real-time-tracking-1st-edition-by-ali-shahrokni-tom-drummond-
pascal-fua-isbn-3540219835-9783540219835-14004/
Face Recognition from Facial Surface Metric 1st edition by Alexander
Bronstein, Michael Bronstein, Alon Spira, Ron Kimmel ISBN 3540219835
9783540219835
https://ebookball.com/product/face-recognition-from-facial-
surface-metric-1st-edition-by-alexander-bronstein-michael-
bronstein-alon-spira-ron-kimmel-
isbn-3540219835-9783540219835-14040/
Matching Tensors for Automatic Correspondence and Registration 1st
edition by Ajmal Mian, Mohammed Bennamoun, Robyn Owens ISBN 35402
9783540219835
https://ebookball.com/product/matching-tensors-for-automatic-
correspondence-and-registration-1st-edition-by-ajmal-mian-
mohammed-bennamoun-robyn-owens-
isbn-3540219835-9783540219835-14176/
,A Combined PDE and Texture Synthesis Approach to Inpainting 1st
edition by Harald Grossauer ISBN 3540219835 9783540219835
https://ebookball.com/product/a-combined-pde-and-texture-
synthesis-approach-to-inpainting-1st-edition-by-harald-grossauer-
isbn-3540219835-9783540219835-9544/
Weighted Minimal Hypersurfaces and Their Applications in Computer
Vision 1st edition by Bastian Goldlucke, Marcus Magnor ISBN 3540219835
9783540219835
https://ebookball.com/product/weighted-minimal-hypersurfaces-and-
their-applications-in-computer-vision-1st-edition-by-bastian-
goldlucke-marcus-magnor-isbn-3540219835-9783540219835-13260/
Stitching and Reconstruction of Linear Pushbroom Panoramic Images for
Planar Scenes 1st edition by Chu Song Chen, Yu Ting Chen, Fay Huang
ISBN 3540219835 9783540219835
https://ebookball.com/product/stitching-and-reconstruction-of-
linear-pushbroom-panoramic-images-for-planar-scenes-1st-edition-
by-chu-song-chen-yu-ting-chen-fay-huang-
isbn-3540219835-9783540219835-11866/
A Framework for Pencil of Points Structure from Motion 1st edition by
Adrien Bartoli, Mathieu Coquerelle, Peter Sturm ISBN 3540219835
9783540219835
https://ebookball.com/product/a-framework-for-pencil-of-points-
structure-from-motion-1st-edition-by-adrien-bartoli-mathieu-
coquerelle-peter-sturm-isbn-3540219835-9783540219835-14264/
Spatially Homogeneous Dynamic Textures 1st edition by Gianfranco
Doretto, Eagle Jones, Stefano Soatto ISBN 3540219835 9783540219835
https://ebookball.com/product/spatially-homogeneous-dynamic-
textures-1st-edition-by-gianfranco-doretto-eagle-jones-stefano-
soatto-isbn-3540219835-9783540219835-9930/
, Weak Hypotheses and Boosting for Generic
Object Detection and Recognition
A. Opelt1,2 , M. Fussenegger1,2 , A. Pinz2 , and P. Auer1
1
Institute of Computer Science,
8700 Leoben, Austria
{auer,andreas.opelt}@unileoben.ac.at
2
Institute of Electrical Measurement and Measurement Signal Processing,
8010 Graz, Austria
{fussenegger,opelt,pinz}@emt.tugraz.at
Abstract. In this paper we describe the first stage of a new learning
system for object detection and recognition. For our system we propose
Boosting [5] as the underlying learning technique. This allows the use of
very diverse sets of visual features in the learning process within a com-
mon framework: Boosting — together with a weak hypotheses finder —
may choose very inhomogeneous features as most relevant for combina-
tion into a final hypothesis. As another advantage the weak hypotheses
finder may search the weak hypotheses space without explicit calculation
of all available hypotheses, reducing computation time. This contrasts
the related work of Agarwal and Roth [1] where Winnow was used as
learning algorithm and all weak hypotheses were calculated explicitly.
In our first empirical evaluation we use four types of local descriptors:
two basic ones consisting of a set of grayvalues and intensity moments
and two high level descriptors: moment invariants [8] and SIFTs [12].
The descriptors are calculated from local patches detected by an inter-
est point operator. The weak hypotheses finder selects one of the local
patches and one type of local descriptor and efficiently searches for the
most discriminative similarity threshold. This differs from other work on
Boosting for object recognition where simple rectangular hypotheses [22]
or complex classifiers [20] have been used. In relatively simple images,
where the objects are prominent, our approach yields results comparable
to the state-of-the-art [3]. But we also obtain very good results on more
complex images, where the objects are located in arbitrary positions,
poses, and scales in the images. These results indicate that our flexible
approach, which also allows the inclusion of features from segmented re-
gions and even spatial relationships, leads us a significant step towards
generic object recognition.
1 Introduction
We believe that a learning component is a necessary part of any generic ob-
ject recognition system. In this paper we investigate a principle approach for
learning objects in still images which allows the use of flexible and extendible
T. Pajdla and J. Matas (Eds.): ECCV 2004, LNCS 3022, pp. 71–84, 2004.
c Springer-Verlag Berlin Heidelberg 2004
