EVALUACIÓN DE CONFIGURACIONES DE CLUSTERING PARA LA DETECCIÓN DE OBJETOS UTILIZANDO CARACTERÍSTICAS SIFT

Abstract

Scale-Invariant Feature Transform (SIFT) features have been widely accepted as an effective local keypoint descriptor for its robust description of digital image content. This method extracts distinctive invariant features from images that can be used to perform reliable matching between different views of an object. Object recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbour algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. Nonetheless, reasoning for the choice of this clustering approach is not provided and a lack of its theoretical insight is noticed. Here, we present and evaluate different configurations for clustering sets of keypoints according to their pose parameters: x and y coordinates location, scale and orientation based on Lowe’s approach.