SciELO - Scientific Electronic Library Online

vol.11 issue1Adapting a Reinforcement Learning Approach for the Flow Shop Environment with sequence-dependent setup timeSmoothing of cellular microscopy images using morphological filtering techniques author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand




  • Have no cited articlesCited by SciELO

Related links

  • Have no similar articlesSimilars in SciELO


Revista Cubana de Ciencias Informáticas

On-line version ISSN 2227-1899


OSORIO ROIG, Dailé; CHACON CABRERA, Yasser  and  GAREA LLANO, Eduardo. Consensus segmentation and ordinal co-occurrence matrix in iris recognition. Rev cuba cienc informat [online]. 2017, vol.11, n.1, pp.58-72. ISSN 2227-1899.

ABSTRACT In recent years, the biometric identification of people has gained great importance in the world from its applications in multiple scenarios, especially those applications aimed at border security, access controls and forensics. In this article, a brief introduction to the systems of recognition of people by the iris is made and two of their subjects are addressed, which are currently under research. The process of segmentation of the iris, in an image taken from the eye of a person, is approached from the description of the investigations that the authors have developed in the subject of the fusion of segmentations and their improvement. In this theme the concept of consensus segmentation is used to improve the robustness of the iris recognition with respect to the simple segmentation. The process of iris feature extraction is addressed by describing a representation proposed by the authors based on the ordinal features of the co-occurrence matrix, for an iris recognition system, which raises accuracy in recognition. The experimental results described and performed on international databases of references, show the relevance and robustness of these proposals.

Keywords : Fusion of segmentations; iris segmentation; consensus segmentation; trait extraction; ordinal measures; ordinal co-occurrence matrix.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )


Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License