Open AccessPosted Content
Predicting Gender from Iris Texture May Be Harder Than It Seems
Andrey Kuehlkamp,Kevin W. Bowyer +1 more
TLDR
In this article, the authors used probabilistic occlusion masking to gain insight on the discriminative power of the iris texture for gender prediction, and found that the gender related information is primarily in the periocular region.Abstract:
Predicting gender from iris images has been reported by several researchers as an application of machine learning in biometrics. Recent works on this topic have suggested that the preponderance of the gender cues is located in the periocular region rather than in the iris texture itself. This paper focuses on teasing out whether the information for gender prediction is in the texture of the iris stroma, the periocular region, or both. We present a larger dataset for gender from iris, and evaluate gender prediction accuracy using linear SVM and CNN, comparing hand-crafted and deep features. We use probabilistic occlusion masking to gain insight on the problem. Results suggest the discriminative power of the iris texture for gender is weaker than previously thought, and that the gender-related information is primarily in the periocular region.read more
Citations
More filters
Proceedings ArticleDOI
Amalgamation Biometric Deep Features in Smart City-ITS Authentication
TL;DR: In this article , the authors proposed a model for having secured access to amenities in smart cities using a combination of biometric features to provide access to ITS services including the combinations of iris, periocular, and fingerprints.
Proceedings ArticleDOI
Novel approach of Using Periocular and Iris Biometric Recognition in the Authentication of ITS
TL;DR: In this paper , the authors proposed a unique approach for personal authentication based on the merging of periocular and iris sensors, which may be used in the ITS (Intelligent Transport System).
Brazilian scientific productivity from a gender perspective during the Covid-19 pandemic: classification and analysis via machine learning
Rosa Virgínia Batista do Rêgo,Gabriel da Silva Nascimento,Davi Emmanuel de Lima Rodrigues,Samara Martins Nascimento,V. M. L. Silva +4 more
TL;DR: In this article , an analysis of the impact of COVID-19 on Brazilian scientific research is made, examining the number of complete manuscripts published in the period from 2018 to 2021, considering the researcher's gender.
Proceedings ArticleDOI
Verification system based on long-range iris and Graph Siamese Neural Networks
TL;DR: A novel methodology for converting LR iris images into graphs is presented and then Graph Siamese Neural Networks (GSNN) is used to predict whether two graphs belong to the same person and demonstrate the suitability of this approach.
Proceedings ArticleDOI
Fusion Biometric Deep Features Blended in Its Authentication
TL;DR: In this paper , the authors proposed a system that considers biometric features such as periocular, iris, fingerprint, and voice modulation to secure the ITS (Intelligent Transport System).
References
More filters
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings Article
SEXNET: A Neural Network Identifies Sex From Human Faces
TL;DR: A neural network was trained to discriminate sex in human faces, and performed as well as humans on a set of 90 exemplars, and some SexNet errors mimicked those of humans.
Journal ArticleDOI
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Ramprasaath R. Selvaraju,Michael Cogswell,Abhishek Das,Ramakrishna Vedantam,Devi Parikh,Dhruv Batra +5 more
TL;DR: Grad-CAM as discussed by the authors uses the gradients of any target concept, flowing into the final convolutional layer to produce a coarse localization map highlighting important regions in the image for predicting the concept.
Journal ArticleDOI
Pupil dilation degrades iris biometric performance
TL;DR: It is found that when the degree of dilation is similar at enrollment and recognition, comparisons involving highly dilated pupils result in worse recognition performance than comparisons involving constricted pupils, and it is recommended that a measure of pupil dilation be kept as meta-data for every iris code.
Proceedings ArticleDOI
Learning to predict gender from iris images
TL;DR: Machine learning techniques are employed to develop models that predict gender based on the iris texture features to determine specific human attributes using biometrics as a means of verifying identity.
Related Papers (5)
Analyzing Covariate Influence on Gender and Race Prediction From Near-Infrared Ocular Images
Denton Bobeldyk,Arun Ross +1 more