Correlation of iris biometrics and DNA
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Correlation of iris biometrics and DNA. / Harder, Stine; Clemmensen, Line H.; Dahl, Anders L.; Andersen, Jeppe D.; Johansen, Peter; Christoffersen, Susanne R.; Morling, Niels; Borsting, Claus; Paulsen, Rasmus R.
2013 International Workshop on Biometrics and Forensics, IWBF 2013. 2013. 6547325 (2013 International Workshop on Biometrics and Forensics, IWBF 2013).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Correlation of iris biometrics and DNA
AU - Harder, Stine
AU - Clemmensen, Line H.
AU - Dahl, Anders L.
AU - Andersen, Jeppe D.
AU - Johansen, Peter
AU - Christoffersen, Susanne R.
AU - Morling, Niels
AU - Borsting, Claus
AU - Paulsen, Rasmus R.
PY - 2013
Y1 - 2013
N2 - The presented work concerns prediction of complex human phenotypes from genotypes. We were interested in correlating iris color and texture with DNA. Our data consist of 212 eye images along with DNA: 32 single-nucleotide polymorphisms (SNPs). We used two types of biometrics to describe the eye images: One for iris color and one for iris texture. Both biometrics were high dimensional and a sparse principle component analysis (SPCA) reduced the dimensions and resulted in a representation of data with good interpretability. The correlations between the sparse principal components (SPCs) and the 32 SNPs were found using a canonical correlation analysis (CCA). The result was a single significant canonical correlation (CC) for both biometrics. Each CC comprised two correlated canonical variables, consisting of a linear combination of SPCs and a linear combination of SNPs, respectively. The significant canonical variables for color and texture were primarily explained by the first SPC (SPC1). Therefore, we made a visual inspection of the first SPCs. The color based SPC1 explained a blue to brown variation in iris color and the texture based SPC1 gave a general explanation of iris texture. The SNPs (rs12896399, rs3733542, rs6475555, rs12913832) and (rs12896399, rs3733542, rs12913832) had the highest correlation to the canonical variable for color and texture, respectively. Three of the most contributing SNPs were the same for both biometrics, revealing a covariance between iris color and texture.
AB - The presented work concerns prediction of complex human phenotypes from genotypes. We were interested in correlating iris color and texture with DNA. Our data consist of 212 eye images along with DNA: 32 single-nucleotide polymorphisms (SNPs). We used two types of biometrics to describe the eye images: One for iris color and one for iris texture. Both biometrics were high dimensional and a sparse principle component analysis (SPCA) reduced the dimensions and resulted in a representation of data with good interpretability. The correlations between the sparse principal components (SPCs) and the 32 SNPs were found using a canonical correlation analysis (CCA). The result was a single significant canonical correlation (CC) for both biometrics. Each CC comprised two correlated canonical variables, consisting of a linear combination of SPCs and a linear combination of SNPs, respectively. The significant canonical variables for color and texture were primarily explained by the first SPC (SPC1). Therefore, we made a visual inspection of the first SPCs. The color based SPC1 explained a blue to brown variation in iris color and the texture based SPC1 gave a general explanation of iris texture. The SNPs (rs12896399, rs3733542, rs6475555, rs12913832) and (rs12896399, rs3733542, rs12913832) had the highest correlation to the canonical variable for color and texture, respectively. Three of the most contributing SNPs were the same for both biometrics, revealing a covariance between iris color and texture.
KW - biometrics
KW - canonical correlation analysis
KW - DNA
KW - iris color
KW - iris texture
UR - http://www.scopus.com/inward/record.url?scp=84881324457&partnerID=8YFLogxK
U2 - 10.1109/IWBF.2013.6547325
DO - 10.1109/IWBF.2013.6547325
M3 - Article in proceedings
AN - SCOPUS:84881324457
SN - 9781467349895
T3 - 2013 International Workshop on Biometrics and Forensics, IWBF 2013
BT - 2013 International Workshop on Biometrics and Forensics, IWBF 2013
T2 - 1st International Workshop on Biometrics and Forensics, IWBF 2013
Y2 - 4 April 2013 through 5 April 2013
ER -
ID: 276217146