Novel Gaussianized vector representation for improved natural scene categorization

Authors:
Xi Zhou;Xiaodan Zhuang;Hao Tang;Mark Hasegawa-Johnson;Thomas S. Huang
Affiliations:
Beckman Institute of Advanced Science and Technology, Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA;Beckman Institute of Advanced Science and Technology, Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA;Beckman Institute of Advanced Science and Technology, Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA;Beckman Institute of Advanced Science and Technology, Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA;Beckman Institute of Advanced Science and Technology, Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
Venue:
Pattern Recognition Letters
Year:
2010

Citing 13
Cited 3

Color indexing

International Journal of Computer Vision
Recognition without Correspondence using MultidimensionalReceptive Field Histograms

International Journal of Computer Vision
Unsupervised learning by probabilistic latent semantic analysis

Machine Learning
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

International Journal of Computer Vision
An Improved Active Shape Model for Face Alignment

ICMI '02 Proceedings of the 4th IEEE International Conference on Multimodal Interfaces
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Recognition with Local Features: the Kernel Recipe

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Kernel Codebooks for Scene Categorization

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Face alignment using statistical models and wavelet features

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Hyperfeatures – multilevel local coding for visual recognition

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Adapted vocabularies for generic visual categorization

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV

Improved learning of I2C distance and accelerating the neighborhood search for image classification

Pattern Recognition
Building global image features for scene recognition

Pattern Recognition
Scene classification using multi-resolution low-level feature combination

Neurocomputing

Quantified Score

Hi-index	0.10

Visualization

Abstract

We present a novel Gaussianized vector representation for scene images by an unsupervised approach. Each image is first encoded as an ensemble of orderless bag of features. A global Gaussian Mixture Model (GMM) learned from all images is then used to randomly distribute each feature into one Gaussian component by a multinomial trial. The posteriors of the feature on all the Gaussian components serve as the parameters of the multinomial distribution. Finally, the normalized means of the features distributed in every Gaussian component are concatenated to form a supervector, which is a compact representation for each scene image. We prove that these supervectors observe the standard normal distribution. The Gaussianized vector representation is a more generalized form of the widely used histogram representation. Our experiments on scene categorization tasks using this vector representation show significantly improved performance compared with the histogram-of-features representation. This paper is an extended version of our work that won the IBM Best Student Paper Award at the 2008 International Conference on Pattern Recognition (ICPR 2008) (Zhou et al., 2008).