Object recognition algorithm using a vocabulary tree and a pre-matching array

Abstract

A vocabulary tree algorithm builds a tree structure with the off-line learning method using a large training image dataset. After constructing the tree structure, we can retrieve a query image class very quickly by searching it. This algorithm has come into the spotlight recently because of the great reduction in computation time. In this article, we suggest a method which improves the classification accuracy by searching a vocabulary tree many times for each test dataset. The information which is given by the pre-matching array determines how the tree is visited. Using our new algorithm, we can reduce the miss-classification rate considerably. On the other hand, losses in computation time and memory allocation are negligible with respect to real-time recognition. © 2010 International Symposium on Artificial Life and Robotics (ISAROB).