Download:
by Jordi Vitria, David Guillamet, David Guillamet, Baback Moghaddam, Baback Moghaddam, Jordi Vitrià
http://www.merl.com/papers/docs/TR2003-93.pdf
Add To MetaCart
Abstract:
We propose a novel local appearance modeling method for object detection and recognition in cluttered scenes. The approach is based on the joint distribution of local feature vectors at multiple salient points and factorization with Independent Component Analysis (ICA). The resulting densities are simple multiplicative distributions modeled through adaptative Gaussian mixture models. This leads to computationally tractable joint probability densities which can model high-order dependencies. Our techinque has been initially tested under different natural and cluttered scenes with different degrees of occlusions with promising results. With this present work, we provide a large statistical test with the MNIST digit database in order to demonstrate the improved performance obtained by explicit modeling of high-order dependencies.
Citations
|
925
|
Color indexing
– Swain, Ballard
- 1991
|
|
808
|
Independent component analysis, a new concept
– Comon
- 1994
|
|
792
|
A combined corner and edge detector
– Harris, Stephens
- 1988
|
|
427
|
Probabilistic visual learning for object representation
– Moghaddam, Pentland
- 1997
|
|
405
|
Shape matching and object recognition using shape contexts
– Belongie, Malik, et al.
- 2002
|
|
271
|
Local grayvalue invariants for image retrieval
– Schmid, Mohr
- 1997
|
|
188
|
Image indexing using color correlograms
– Huang, Kumar, et al.
- 1997
|
|
169
|
Representation of local geometry in the visual system
– Koenderink, Doorn
- 1987
|
|
124
|
Probabilistic modeling of local appearance and spatial relationships for object recognition
– Schneiderman, Kanade
- 1998
|
|
83
|
A Computational approach for corner and vertex detection
– Deriche, Giraudon
- 1993
|
|
58
|
Comparing and evaluating interest points
– Schmid, Mohr, et al.
- 1998
|
|
41
|
Blind separation of sources
– Comon, Jutten, et al.
- 1991
|
|
24
|
Object recognition with color cooccurrence histograms
– Chang, Krumm
- 1999
|
|
10
|
Mdl-based selection of the number of components in mixture models for pattern classification
– Tenmoto, Kudo, et al.
- 1998
|
|
8
|
The MNIST DataBase of Handwritten digits
– LeCun
- 1998
|
|
5
|
Regionsof-interest and spatial layout in content based image retrieval
– Moghaddam, Biermann, et al.
- 1999
|
|
1
|
Using an ICA representation of local color histograms for object recognition
– Bressan, Guillamet, et al.
- 2003
|
