Direct Estimation of Appearance Models for Segmentation

Image segmentation algorithms often depend on appearance models that characterize the distribution of pixel values in different image regions. We describe a new approach for estimating appearance models directly from an image, without explicit consideration of the pixels that make up each region. Our approach is based on novel algebraic expressions that relate local image statistics to the appearance of spatially coherent regions. We describe two algorithms that can use the aforementioned algebraic expressions to estimate appearance models directly from an image. The first algorithm solves a system of linear and quadratic equations using a least squares formulation. The second algorithm is a spectral method based on an eigenvector computation. We present experimental results that demonstrate the proposed methods work well in practice and lead to effective image segmentation algorithms.

Automated summary

This paper proposes a new approach to estimate appearance models directly from images without considering individual pixels. It introduces algebraic expressions that relate local image statistics to spatially coherent regions. Two algorithms, one using a least squares formulation and the other based on eigenvector computation, are presented for estimating appearance models. Experimental results demonstrate the effectiveness of these methods for image segmentation.