Performance Evaluation of Raster Based Shape Vectors in Object Recognition

Abstract

Object recognition is still an impediment in the field of computer vision and multimedia retrieval.Defining an object model is a critical task. Shape information of an object play a critical role in the process of object recognition. Extraction of boundary information of an object from the multimedia data and classifying this information with associated objects is the primary step towards object recognition. Rasters play an important role while computing object boundary. The trade-off lies with the dimensionality of the object versus computational cost while achieving maximum efficiency. In this treatise an attempt is made to evaluate the performance of circular and spiral raster models in terms of average retrieval efficiency and computational cost.