Publications

@article{abateKurtosisSkewnessPixel2017,

title = {Kurtosis and Skewness at Pixel Level as Input for SOM Networks to Iris Recognition on Mobile Devices},

author = { Andrea Abate and Silvio Barra and Luigi Gallo and Fabio Narducci},

doi = {10.1016/j.patrec.2017.02.002},

issn = {0167-8655},

year  = {2017},

date = {2017-02-01},

urldate = {2017-02-21},

journal = {Pattern Recognition Letters},

abstract = {The increasing popularity of smartphones amongst the population laid the basis for a wide range of applications aimed at security and privacy protection. Very modern mobile devices have recently demonstrated the feasibility of using a camera sensor to access the system without typing any alphanumerical password. In this work, we present a method that implements iris recognition in the visible spectrum through unsupervised learning by means of Self Organizing Maps (SOM). The proposed method uses a SOM network to cluster iris features at pixel level. The discriminative feature map is obtained by using RGB data of the iris combined with the statistical descriptors of kurtosis and skewness. An experimental analysis on MICHE-I and UBIRISv1 datasets demonstrates the strengths and weaknesses of the algorithm, which has been specifically designed to require low processing power in compliance with the limited capability of common mobile devices.},

keywords = {Iris, Mobile Biometric Recognition, Statistical descriptors, Unsupervised Learning},

pubstate = {published},

tppubtype = {article}

}

@article{abate_kurtosis_2017,

title = {Kurtosis and skewness at pixel level as input for SOM networks to iris recognition on mobile devices},

author = {Andrea Abate and Silvio Barra and Luigi Gallo and Fabio Narducci},

url = {http://www.sciencedirect.com/science/article/pii/S0167865517300338},

doi = {10.1016/j.patrec.2017.02.002},

issn = {0167-8655},

year  = {2017},

date = {2017-02-01},

urldate = {2017-02-21},

journal = {Pattern Recognition Letters},

abstract = {The increasing popularity of smartphones amongst the population laid the basis for a wide range of applications aimed at security and privacy protection. Very modern mobile devices have recently demonstrated the feasibility of using a camera sensor to access the system without typing any alphanumerical password. In this work, we present a method that implements iris recognition in the visible spectrum through unsupervised learning by means of Self Organizing Maps (SOM). The proposed method uses a SOM network to cluster iris features at pixel level. The discriminative feature map is obtained by using RGB data of the iris combined with the statistical descriptors of kurtosis and skewness. An experimental analysis on MICHE-I and UBIRISv1 datasets demonstrates the strengths and weaknesses of the algorithm, which has been specifically designed to require low processing power in compliance with the limited capability of common mobile devices.},

keywords = {Iris, Mobile Biometric Recognition, Statistical descriptors, Unsupervised Learning},

pubstate = {published},

tppubtype = {article}

}