Sciweavers

CVPR
2003
IEEE

Man-Made Structure Detection in Natural Images using a Causal Multiscale Random Field

14 years 5 months ago
Man-Made Structure Detection in Natural Images using a Causal Multiscale Random Field
This paper presents a generative model based approach to man-made structure detection in 2D natural images. The proposed approach uses a causal multiscale random field suggested in [3] as a prior model on the class labels on the image sites. However, instead of assuming the conditional independence of the observed data, we propose to capture the local dependencies in the data using a multiscale feature vector. The distribution of the multiscale feature vectors is modeled as mixture of Gaussians. A set of robust multiscale features is presented that captures the general statistical properties of man-made structures at multiple scales without relying on explicit edge detection. The proposed approach was validated on real-world images from the Corel data set, and a performance comparison with other techniques is presented.
Sanjiv Kumar, Martial Hebert
Added 12 Oct 2009
Updated 29 Oct 2009
Type Conference
Year 2003
Where CVPR
Authors Sanjiv Kumar, Martial Hebert
Comments (0)