In this paper, we introduce KAZE features, a novel multiscale 2D feature detection and description algorithm in nonlinear scale spaces. Previous approaches detect and describe features at different scale levels by building or approximating the Gaussian scale space of an image. However, Gaussian blurring does not respect the natural boundaries of objects and smoothes to the same degree 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 superior localization accuracy and distinctiviness. The nonlinear scale space is built using efficient Additive Operator Splitting (AOS) techniques and variable conductance 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 construction 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.
KeywordsFeature Detection Scale Space Scale Level Scale Invariant Feature Transform Nonlinear Diffusion
Unable to display preview. Download preview PDF.
- 1.Liu, C., Yuen, J., Torralba, A.: Dense scene alignment using SIFT flow for object recognition. In: IEEE Conf. on Computer Vision and Pattern Recognition, CVPR (2009)Google Scholar
- 2.Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: IEEE Conf. on Computer Vision and Pattern Recognition, CVPR (2006)Google Scholar
- 3.Agarwal, S., Snavely, N., Simon, I., Seitz, S.M., Szeliski, R.: Building Rome in a Day. In: Intl. Conf. on Computer Vision, ICCV, Kyoto, Japan (2009)Google Scholar
- 5.Lindeberg, T.: Feature detection with automatic scale selection. Intl. J. of Computer Vision 30, 77–116 (1998)Google Scholar
- 9.Weickert, J., ter Haar Romeny, B., Viergever, M.A.: Efficient and reliable schemes for nonlinear diffusion filtering. IEEE Trans. Image Processing 7 (1998)Google Scholar
- 10.ter Haar Romeny, B.M.: Front-End Vision and Multi-Scale Image Analysis. Multi-Scale Computer Vision Theory and Applications, written in Mathematica. Kluwer Academic Publishers (2003)Google Scholar
- 12.Qiu, Z., Yang, L., Lu, W.: A new feature-preserving nonlinear anisotropic diffusion method for image denoising. In: British Machine Vision Conf., BMVC, Dundee, UK (2011)Google Scholar
- 15.Weickert, J., Ishikawa, S., Imiya, A.: Linear scale-space has first been proposed in Japan. Journal of Mathematical Imaging and Vision 10 (1999)Google Scholar
- 20.Brown, M., Lowe, D.: Invariant features from interest point groups. In: British Machine Vision Conf., BMVC, Cardiff, UK (2002)Google Scholar
- 22.Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008), http://www.vlfeat.org/
- 24.Salzmann, M., Hartley, R., Fua, P.: Convex optimization for deformable surface 3D tracking. In: Intl. Conf. on Computer Vision, ICCV, Rio de Janeiro, Brazil (2007)Google Scholar
- 25.Bartoli, A., Gérard, Y., Chadebecq, F., Collins, T.: On template-based reconstruction from a single view: Analytical solutions and proofs of well-posedness for developable, isometric and conformal surfaces. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, USA (2012)Google Scholar