Exploiting superior CNN-based iris segmentation for better recognition accuracy

Hofbauer, Heinz; Jalilian, Ehsaneddin; Uhl, Andreas

doi:10.1016/j.patrec.2018.12.021

Cited by 78 publications

(48 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the proposed method to serve as a drop-in replacement for the Daugman method recognition pipeline, the prediction obtained from the DCNN-based segmentation has to be correctly normalized onto a dimensionless polar-coordinate rectangle. For this stage, a method for localizing pupillary and limbic iris boundaries has been devised, which employs a Hough transform that is applied to the prediction obtained from the OSIRIS segmentation, normalized images, and normalized masks coarse CNN binary predictions with fitted Hough circles, segmented images, normalized images, and normalized masks coarse segmentation model, similarly to the methodology introduced in [21] and [22], as this model yields the smoothest prediction. These boundary parameters are then used in all subsequent experiments, including those involving the fine and fine v2highres models.…”

Section: Iris and Mask Normalizationmentioning

confidence: 99%

Post-mortem iris recognition with deep-learning-based image segmentation

Trokielewicz

Czajka

Maciejewicz

2020

Image and Vision Computing

View full text Add to dashboard Cite

This paper proposes the first known to us iris recognition methodology designed specifically for post-mortem samples. We propose to use deep learning-based iris segmentation models to extract highly irregular iris texture areas in post-mortem iris images. We show how to use segmentation masks predicted by neural networks in conventional, Gabor-based iris recognition method, which employs circular approximations of the pupillary and limbic iris boundaries. As a whole, this method allows for a significant improvement in post-mortem iris recognition accuracy over the methods designed only for ante-mortem irises, including the academic OSIRIS and commercial IriCore implementations. The proposed method reaches the EER less than 1% for samples collected up to 10 hours after death, when compared to 16.89% and 5.37% of EER observed for OSIRIS and IriCore, respectively. For samples collected up to 369 hours post-mortem, the proposed method achieves the EER 21.45%, while 33.59% and 25.38% are observed for OSIRIS and IriCore, respectively. Additionally, the method is tested on a database of iris images collected from ophthalmology clinic patients, for which it also offers an advantage over the two other algorithms. This work is the first step towards post-mortem-specific iris recognition, which increases the chances of identification of deceased subjects in forensic investigations. The new database of post-mortem iris images acquired from 42 subjects, as well as the deep learning-based segmentation models are made available along with the paper, to ensure all the results presented in this manuscript are reproducible.

show abstract

Section: Iris and Mask Normalizationmentioning

confidence: 99%

Post-mortem iris recognition with deep-learning-based image segmentation

Trokielewicz

Czajka

Maciejewicz

2020

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…CNN-based iris divisions have been demonstrated to be better than conventional iris division methods as far as division mistake measurements. [4] To appropriately use them in a conventional biometric acknowledgment frameworks requires a parameterization of the iris, in light of the created division, to get the standardized iris surface ordinarily utilized for highlight extraction. This is an unsolved issue.…”

Section: Literatre Surveymentioning

confidence: 99%

Deep Learning Iris Recognition Method Based on Capsule Network Architecture

sree*,

Divya

2020

IJRTE

View full text Add to dashboard Cite

In biometric acknowledgment, which is generally utilized in different fields. As of late, numerous profound learning strategies have been utilized in biometric acknowledgment, attributable to their points of interest. In this deep learning process we adjust the existing network structure and providing the modified routing algorithm technique which is depends on dynamic routing between two capsule layers. This layers helps to maintain and adopt a iris recognition. Various iris data sets are used for recognition. These datasets are trained and tested with the help of different pupil size of an iris. In order to show the recognition ability when the environment varies. The test of dataset achieves 96.2%. CASIA-V4 Lamp dataset gives the highest accuracy of 98.34%. It shows the apply of capsule network in iris recognition.

show abstract

“…In the paper of [27], an AlexNet pre-trained model had been tailored with a handcrafted CNN architecture to extract features from fingernail plates and finger knuckles for the purpose of biometric authentication. The works of [28] proposes the use of a pre-trained CNN model for age range classification from an unconstrained face images due to the absence of large comprehensive unconstrained face dataset. In their paper, pre-trained CNN model is used as feature extractor from face images and applied fine-tuning to train their model for age classification.…”

Section: Review Of Related Studies and Literaturesmentioning

confidence: 99%

Unconstrained Ear Recognition through Domain Adaptive Deep Learning Models of Convolutional Neural Network

Alejo¹,

Hate²

2019

IJRTE

View full text Add to dashboard Cite

Limited ear dataset yields to the adaption of domain adaptive deep learning or transfer learning in the development of ear biometric recognition. Ear recognition is a variation of biometrics that is becoming popular in various areas of research due to the advantages of ears towards human identity recognition. In this paper, handpicked CNN architectures: AlexNet, GoogLeNet, Inception-v3, Inception-ResNet-v2, ResNet-18, ResNet-50, SqueezeNet, ShuffleNet, and MobileNet-v2 are explored and compared for use in an unconstrained ear biometric recognition. 250 unconstrained ear images are collected and acquired from the web through web crawlers and are preprocessed with basic image processing methods including the use of contrast limited adaptive histogram equalization for ear image quality improvement. Each CNN architecture is analyzed structurally and are fine-tuned to satisfy the requirements of ear recognition. Earlier layers of CNN architectures are used as feature extractors. Last 2-3 layers of each CNN architectures are fine-tuned thus, are replaced with layers of the same kind for ear recognition models to classify 10 classes of ears instead of 1000. 80 percent of acquired unconstrained ear images is used for training and the remaining 20 percent is reserved for testing and validation. Results of each architectures are compared in terms of their training time, training and validation outputs as such learned features and losses, and test results in terms of above-95% accuracy confidence. Above all the used architectures, ResNet, AlexNet, and GoogleNet achieved an accuracy confidence of 97-100% and is best for use in unconstrained ear biometric recognition while ShuffleNet, despite of achieving approximately 90%, shows promising result for use in mobile version of unconstrained ear biometric recognition.

show abstract

Exploiting superior CNN-based iris segmentation for better recognition accuracy

Cited by 78 publications

References 8 publications

Post-mortem iris recognition with deep-learning-based image segmentation

Post-mortem iris recognition with deep-learning-based image segmentation

Deep Learning Iris Recognition Method Based on Capsule Network Architecture

Unconstrained Ear Recognition through Domain Adaptive Deep Learning Models of Convolutional Neural Network

Contact Info

Product

Resources

About