Multiscale Fields of Patterns
This work addresses image analysis challenges in computer vision, but it appears incremental as it builds on existing multiscale and pattern-based methods without claiming major breakthroughs.
The paper tackles the problem of modeling high-order image structures by introducing a multiscale framework that captures local patterns at different resolutions, resulting in expressive priors with few parameters, and demonstrates its application in contour detection and binary segmentation.
We describe a framework for defining high-order image models that can be used in a variety of applications. The approach involves modeling local patterns in a multiscale representation of an image. Local properties of a coarsened image reflect non-local properties of the original image. In the case of binary images local properties are defined by the binary patterns observed over small neighborhoods around each pixel. With the multiscale representation we capture the frequency of patterns observed at different scales of resolution. This framework leads to expressive priors that depend on a relatively small number of parameters. For inference and learning we use an MCMC method for block sampling with very large blocks. We evaluate the approach with two example applications. One involves contour detection. The other involves binary segmentation.