This paper presents a generative model based approach to man-made structure detection in 2D (two-dimensional) natural images. The proposed approach uses a causal multiscale random field suggested by Bouman and Shapiro (1994) 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 multi-scale 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.
Man-made structure detection in natural images using a causal multiscale random field
2003-01-01
528950 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Man-Made Structure Detection in Natural Images Using a Causal Multiscale Random Field
British Library Conference Proceedings | 2003
|Segmentation of Range and Intensity Images Using Multiscale Markov Random Field Representations
British Library Conference Proceedings | 1994
|Efficient Random Field Uncertainty Propagation in Design Using Multiscale Analysis
Online Contents | 2009
|Results Using Random Field Models for the Segmentation of Color Images of Natural Scenes
British Library Conference Proceedings | 1995
|A Multiscale Design Methodology for Hierarchical Systems With Random Field Uncertainty
Online Contents | 2010
|