Hierarchical density estimation for image classification

Zhen Li, Xi Zhou, Thomas S. Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This paper presents a novel hierarchical density estimation approach for image classification. We first build a collection of randomized decision trees in a discriminative way to split the feature space into small regions. Then for each region, class-conditional Gaussians are learnt to characterize the "local" distribution of feature vectors falling into that region. The parameters of the Gaussians are reliably estimated through hierarchical maximum a posteriori (MAP) estimation and smoothed across multiple randomized trees in the forest. Compared with the widely-used Gaussian Mixture Models (GMM), our new approach not only yields more reliable parameter estimation, but also greatly reduces the computational cost at the testing stage. Experiments on scene classification demonstrate the effectiveness and efficiency of our new approach.

Original languageEnglish (US)
Title of host publication2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings
Number of pages4
StatePublished - 2010
Event2010 17th IEEE International Conference on Image Processing, ICIP 2010 - Hong Kong, Hong Kong
Duration: Sep 26 2010Sep 29 2010

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880


Other2010 17th IEEE International Conference on Image Processing, ICIP 2010
Country/TerritoryHong Kong
CityHong Kong


  • Decision tree
  • Hierarchical MAP estimation
  • Image classification
  • Random forest

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing


Dive into the research topics of 'Hierarchical density estimation for image classification'. Together they form a unique fingerprint.

Cite this