Object recognition using particle swarm optimization on geometrical descriptors

This work presents study and experimentation for object recognition when isolated objects are under discussion. For simplicity, instead of solid objects, outlines of the objects have been used for the whole process of the recognition. Simple geometrical shape descriptors (SSD) of eccentricity, compactness, convexity, retangularity, and solidity have been used as features of the objects. From the analysis and results using SSDs, the following questions arise: What is the optimum number of descriptors to be used? Are these descriptors of equal importance? To answer these questions, the problem of selecting the best descriptors has been formulated as an optimization problem. Particle Swarm Optimization technique has been mapped and used successfully to have an object recognition system using minimal number of Descriptors. The proposed method assigns, for each of these descriptors, a weighting factor that reflects the relative importance of that descriptor.