Avaliação do uso de técnicas de agrupamento na busca e recuperação de imagens

Abstract

Nowadays, almost all services and daily tasks involve some computational apparatus, leading to creation and further accumulation of data. This progressive amount of data is an important opportunity of exploration for scientific and commercial branches, which started to value and to use this information more intense and objectively. Allied to this, the natural process of public and private life exposure through social networks and electronic devices tend to generate a significant amount of images that can and should be utilized with various purposes, such as in public security. In this context, facial recognition has advanced and attracted specific studies and applications, aiming at the identification of individuals through parametric features. However, some barriers are still found, making difficult the efficient performance of the operation, such as the computational cost on the search time and recovery of large proportions in image databases. Based on this, this paper proposes the use of clustering algorithms in the organization of image data, thus providing a direction and “ shortening ” in facial images searches. More specifically, an analysis related to the optimization is conducted imposed by the use of clustering techniques applied in the automated organization of images, the preparative step for performing searches. The proposed method was applied to real facial images databases and used two clustering algorithms k-means and EM with variations for the similarity measures (euclidean distance and Pearson correlation). The results show that the use of clustering in data organization has proved to be efficient, leading to a significant reduction in search time and without losses in process accuracy