Abstract
In this paper, we introduce KAZE features, a novel multiscale 2D fea- ture detection and description algorithm in nonlinear scale spaces. Previous ap- proaches detect and describe features at different scale levels by building or ap- proximating the Gaussian scale space of an image. However, Gaussian blurring does not respect the natural boundaries of objects and smoothes to the same de- gree both details and noise, reducing localization accuracy and distinctiveness. In contrast, we detect and describe 2D features in a nonlinear scale space by means of nonlinear diffusion filtering. In this way, we can make blurring locally adaptive to the image data, reducing noise but retaining object boundaries, obtaining su- perior localization accuracy and distinctiviness. The nonlinear scale space is built using efficient Additive Operator Splitting (AOS) techniques and variable con- ductance diffusion. We present an extensive evaluation on benchmark datasets and a practical matching application on deformable surfaces. Even though our features are somewhat more expensive to compute than SURF due to the con- struction of the nonlinear scale space, but comparable to SIFT, our results reveal a step forward in performance both in detection and description against previous state-of-the-art methods.