Date of Original Version
Abstract or Description
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  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.
Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 119-126.