Rotation and Scale Invariant Shape Representation and Recognition Using Matching Pursuit

Using a low-level representation of images, like matching pursuit, we introduce a new way of describing objects through a general description using a translation, rotation, and isotropic scale invariant dictionary of basis functions. This description is then used as a predefined dictionary of the object to conduct a shape recognition task. We show some promising results for both parts of description and detection with simple shapes.

• Type: Conference
• Year: 2002
• Where: ICPR
• Authors: François Mendels, Pierre Vandergheynst, Jean-Philippe Thiran
• Keywords: Computer Vision, ICPR 2002, Low-level Representation, Scale Invariant Dictionary, Shape Recognition Task