Kernel integral images: A framework for fast non-uniform filtering

TitleKernel integral images: A framework for fast non-uniform filtering
Publication TypeConference Papers
Year of Publication2008
AuthorsHussein M, Porikli F, Davis LS
Conference NameComputer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on
Date Published2008/06//
Keywordsapproximated, equations;interpolation;, filtering;bilinear, filtering;kernel, Gaussian, graphics;computer, images;approximation, integral, interpolation;computer, nonuniform, processing;integral, theory;filtering, theory;image, vision;fast, weighting

Integral images are commonly used in computer vision and computer graphics applications. Evaluation of box filters via integral images can be performed in constant time, regardless of the filter size. Although Heckbert (1986) extended the integral image approach for more complex filters, its usage has been very limited, in practice. In this paper, we present an extension to integral images that allows for application of a wide class of non-uniform filters. Our approach is superior to Heckbertpsilas in terms of precision requirements and suitability for parallelization. We explain the theoretical basis of the approach and instantiate two concrete examples: filtering with bilinear interpolation, and filtering with approximated Gaussian weighting. Our experiments show the significant speedups we achieve, and the higher accuracy of our approach compared to Heckbertpsilas.