Start Submission Become a Reviewer

Reading: H-Metric: Characterizing Image Datasets via Homogenization Based on KNN-Queries

Download

A- A+
dyslexia friendly

Research Papers

H-Metric: Characterizing Image Datasets via Homogenization Based on KNN-Queries

Authors:

Welington M da Silva ,

Universidade Federal de Sao Carlos - Campus Sorocaba - Rodovia Joao Leme dos Santos, Km 110 - 18052-780 - SP-264 - Sorocaba, SP, Brazil
X close

Jose F Rodrigues Jr,

Inst. de Ciencias Matematicas e de Computacao - Universidade de Sao Paulo - CP 668 - 13560-970 Sao Carlos, SP, Brazil
X close

Agma J M Traina,

Inst. de Ciencias Matematicas e de Computacao - Universidade de Sao Paulo - CP 668 - 13560-970 Sao Carlos, SP, Brazil
X close

Sergio F da Silva

Inst. de Ciencias Matematicas e de Computacao - Universidade de Sao Paulo - CP 668 - 13560-970 Sao Carlos, SP, Brazil
X close

Abstract

Precision-Recall is one of the main metrics for evaluating content-based image retrieval techniques. However, it does not provide an ample perception of the properties of an image dataset immersed in a metric space. In this work, we describe an alternative metric named H-Metric, which is determined along a sequence of controlled modifications in the image dataset. The process is named homogenization and works by altering the homogeneity characteristics of the classes of the images. The result is a process that measures how hard it is to deal with a set of images in respect to content-based retrieval, offering support in the task of analyzing configurations of distance functions and of features extractors.
DOI: http://doi.org/10.2481/dsj.10-007
How to Cite: da Silva, W.M. et al., (2012). H-Metric: Characterizing Image Datasets via Homogenization Based on KNN-Queries. Data Science Journal. 10, pp.52–60. DOI: http://doi.org/10.2481/dsj.10-007
28
Views
10
Downloads
Published on 15 Jan 2012.
Peer Reviewed

Downloads

  • PDF (EN)

    comments powered by Disqus