A multiresolution approach to iris synthesis

Databases of human iris images are created and distributed for the purposes of testing iris identification algorithms. For logistical and privacy reasons, these databases are often too small to fulfill their potential applications. In this work we develop a novel multiresolution approach to augment...

Full description

Saved in:
Bibliographic Details
Published inComputers & graphics Vol. 34; no. 4; pp. 468 - 478
Main Authors Wecker, L., Samavati, F., Gavrilova, M.
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.08.2010
Subjects
Algorithms
Approximation
Biometrics
Human
Image generation
Iris synthesis
Mathematical analysis
Multiresolution
Representations
Reverse subdivision
Subdivisions
Verification
Biometrics
Verification
Reverse subdivision
Iris synthesis
Multiresolution
Image generation
Online AccessGet full text

Cover

More Information
Summary:Databases of human iris images are created and distributed for the purposes of testing iris identification algorithms. For logistical and privacy reasons, these databases are often too small to fulfill their potential applications. In this work we develop a novel multiresolution approach to augment iris image databases. First, using a multiresolution obtained from reverse subdivision we decompose the example iris images into a set of lower resolution components. The components are a complete representation of the original image and consist of a low resolution approximation and a set of characteristics. To generate synthetic iris images we combine a set of components chosen from the original images. To ensure a unique, yet realistic, iris image each component of a synthetic image is chosen from different iris images. We quantitatively validate our approach by employing a classical iris recognition algorithm to compare our synthetic images with those that were used to create them. The results demonstrate that our approach is effective at augmenting iris image databases with iris images that are unique, yet exhibit both visually and statistically realistic characteristics. [Display omitted] ►A novel multiresolution approach to iris image database augmentation.►Realistic visual results based on components extracted from images of real irises.►Quantitative analysis of synthetic iris database have similarity to real irises.►Effectively augments existing databases with new, unique iris images.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0097-8493
1873-7684
DOI:10.1016/j.cag.2010.05.012