Site Network: Personal | My Company | Vision Research Lab @ UCSB |

 

We introduced a curve descriptor that is based on the modes of vibration of a (possibly non uniform) membrane. To paraphrase M. Kac, can we hear the shape of an image contour?.

 

with Dr. C. Kenney, L. Bertelli, Prof. S. Chandrasekaran and Prof. B. S. Manjunath

(2003-2005) In this project we are investigating efficient methods to detect, describe and match curves, despite the geometric distortions that arise when the scene is imaged from different points of view. In this context we developed a normalization procedure that allows to extract the shape of a curve independently from an affine transformations of the curve itself. We also introduced a physically motivated descriptor based on the Helmholtz equation to label the curves for matching and retrieval purposes. Current research is focused on alleviating the computational burden for the detection and description of the curves and in combining together shape and content of image patches. We are also intrested in extending our methods for 3D surfaces.

 

Related Publications

  1. M. Zuliani, S. Bhagavathy, B. S. Manjunath, C. S. Kenney,
    "Affine-Invariant Curve Matching"
    IEEE International Conference on Image Processing, Singapore, Oct. 2004.
    VRL ID 138: [abstract] [PDF] [BibTex]

    Abstract preview: "In this paper, we propose an affine-invariant method for describing and matching curves. This is important since affine transformations are often used to model perspective distortions. More specifical..." [more]

  2. M. Zuliani, C. S. Kenney, S. Bhagavathy, B. S. Manjunath,
    "Drums and Curve Descriptors"
    British Machine Vision Conference, Kingston University, London, UK, Sep. 2004.
    VRL ID 134: [abstract] [PDF] [BibTex]

    Abstract preview: "In this paper we present a new physically motivated curve descriptor based on the solution of Helmholtz's equation. The descriptor satisfies the six principles set by MPEG-7: it has a good retrieval a..." [more]

Click here for the BMVC 2004 presentation and here to see the preprint of the corresponding article that is going to appear on the Image and Vision Computing Journal.