Dense statistic versus sparse feature-based approach for 3D object recognition
- 115 Downloads
In this article we introduce and compare two approaches towards automatic classification of 3D objects in 2D images. The first one is based on statistical modeling of wavelet features. It estimates probability density functions for all possible object classes considered in a particular recognition task. The second one uses sparse local features. For training, SURF features are extracted from the training images. During the recognition phase, features from the image are matched geometrically, providing the best fitting object for the query image. Experiments were performed for different training sets using more than 40 000 images with different backgrounds. Results show very good classification rates for both systems and point out special characteristics for each approach, which make them more suitable for different applications.
KeywordsFeature Vector Training Image Object Class Object Area Hough Space
Unable to display preview. Download preview PDF.
- 2.H. Bay, T. Tuytelaars, and L. van Gool, “Surf: Speeded up Robust Features,” in Proc. European Conf. on Computer Vision (ECCV) (Graz, 2006), pp. 404–417.Google Scholar
- 3.T. Lindeberg, Scale-Space Theory in Computer Vision (Kluwer Acad. Publ., Dordrecht, 1994).Google Scholar
- 4.M. Muja, Flann, Fast Library for Approximate Nearest Neighbors (2009), Available from: http://mloss.org/software/view/143/
- 6.M. Grzegorzek and H. Niemann, “Statistical Object Recognition Including Color Modeling,” in Proc. 2nd Int. Conf. on Image Analysis and Recognition (Toronto, Canada, Sept. 2005), Ed. by M. Kamel and A. Campilho (Springer-Verlag, Berlin, Heidelberg, 2005), pp. 481–489.Google Scholar