Automatic approaches towards vehicle make and model recognition

Vehicle Make and Model Recognition (MMR) systems provide means for improving the level of identity provided by Automatic Number Plate Recognition (ANPR) systems. Although a number of vehicle MMR systems have been proposed in literature the design of a robust algorithm still remains an open research problem. The research presented in this thesis aims to resolve some of the outstanding challenges in vehicle MMR such as rotation, translation, scale and illumination variance, occlusion, computational complexity and functional limitations. Four novel algorithms for vehicle MMR are proposed. [Continues.]