Object Classification with Multi-Scale Autoconvolution

This paper assesses the recently proposed affine invariant image transform called Multi-Scale Autoconvolution (MSA) in some practical object classification problems. A classification framework based on the MSA and Support Vector Machines is introduced. As shown by the comparison with another affine invariant technique it appears that this new technique provides a good basis for problems where the disturbances in classified objects can be approximated with spatial affine transformation. The paper also introduces a new property clarifying the parameter selection in the Multi-Scale Autoconvolution.

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Esa Rahtu, Janne Heikkilä
• Keywords: Affine Invariant Image, Affine Invariant Technique, Computer Vision, ICPR 2004, Spatial Affine Transformation