Deformable Object Matching Based on Multi-scale Local Histograms

This paper presents a technique to enable deformable objects to be matched throughout video sequences based on the information provided by the multi-scale local histograms of the images. We shall show that this technique is robust enough for viewpoint changes, lighting changes, large motions of the matched object and small changes in rotation and scale. Unlike other wellknown color-based techniques, this technique only uses the gray level values of the image. The proposed algorithm is mainly based on the definition of a particular multi-scale template model and a similarity measure for histogram matching.

• Type: Conference
• Year: 2004
• Where: AMDO
• Authors: Nicolas Pérez de la Blanca, José M. Fuertes, Manuel J. Lucena
• Keywords: AMDO 2004, Computer Graphics, Multi-scale Local Histograms, Particular Multi-scale Template, Wellknown Color-based Techniques