Data-driven segmentation of post-mortem iris images

@article{Trokielewicz2018DatadrivenSO,
  title={Data-driven segmentation of post-mortem iris images},
  author={Mateusz Trokielewicz and Adam Czajka},
  journal={2018 International Workshop on Biometrics and Forensics (IWBF)},
  year={2018},
  pages={1-7}
}
This paper presents a method for segmenting iris images obtained from the deceased subjects, by training a deep convolutional neural network (DCNN) designed for the purpose of semantic segmentation. Post-mortem iris recognition has recently emerged as an alternative, or additional, method useful in forensic analysis. At the same time it poses many new challenges from the technological standpoint, one of them being the image segmentation stage, which has proven difficult to be reliably executed… Expand
Post-mortem Iris Recognition with Deep-Learning-based Image Segmentation
TLDR
This paper proposes to use deep learning-based iris segmentation models to extract highly irregular iris texture areas in post-mortem iris images, and shows 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. Expand
Perception of Image Features in Post-Mortem Iris Recognition: Humans vs Machines
TLDR
This paper offers the first known to us human-interpretable comparison of machine-based and human-based post-mortem iris recognition, and the trained models annotating salient iris image regions. Expand
DCNN-based Human-Interpretable Post-mortem Iris Recognition
TLDR
How humans perceive post-mortem irises when challenged with the task of classification is shown, and it is hypothesized that the proposed DCNN-based method can offer human-intelligible decisions backed by visual explanations which may be valuable for iris examiners in a forensic/courthouse scenario. Expand
Post-Mortem Iris Recognition—A Survey and Assessment of the State of the Art
TLDR
This paper surveys research to date on the problem of using iris images acquired after death for automated human recognition, and provides a medically informed commentary on post-mortem iris, analyze the reasons for recognition failures, and identify key directions for future research. Expand
Attack Detection for Cadaver Iris
This paper presents a deep-learning-based method for iris presentation attack detection (PAD) when iris images are obtained from deceased people. Post-mortem iris recognition, despite being aExpand
Learning-Free Iris Segmentation Revisited: A First Step Toward Fast Volumetric Operation Over Video Samples
TLDR
It is shown that by incorporating volumetric information, FLoRIN achieves a factor of 3.6 to an order of magnitude increase in throughput with only a minor drop in subject matching performance, making it suitable for embedded biometrics systems. Expand
Presentation Attack Detection for Cadaver Iris
TLDR
The first known PAD method in a postmortem setting is offered, together with an explanation of the decisions made by the convolutional neural network, and a dataset of live iris images to facilitate reproducibility and further research. Expand
Post‐mortem Iris Decomposition and its Dynamics in Morgue Conditions
TLDR
An analysis of the coarse effects of eyeball decay done from a perspective of automatic iris recognition is offered and suggestions are provided that may aid forensic examiners in successfully utilizing iris patterns in postmortem identification of deceased subjects. Expand
Robust Iris Presentation Attack Detection Fusing 2D and 3D Information
TLDR
This article proposes a method that combines two-dimensional and three-dimensional properties of the observed iris to address the problem of spoof detection in case when some properties of artifacts are unknown. Expand
Unconstrained Thermal Hand Segmentation
TLDR
This paper implements a method for segmenting hand images collected in the thermal spectrum involving a pre-trained, off-the-shelf data-driven model, fine-tuned with multiple databases of thermal hand images and corresponding, manually annotated ground truth masks, which allows superior performance for difficult samples. Expand
...
1
2
...

References

SHOWING 1-10 OF 19 REFERENCES
Iris Segmentation Using Fully Convolutional Encoder--Decoder Networks
TLDR
This chapter considers the application of Fully Convolutional Encoder–Decoder Networks (FCEDNs) for iris segmentation and proposes three types of FCEDN architectures for segmentation of the iris in the images, obtained from five different datasets, acquired under different scenarios. Expand
Human iris recognition in post-mortem subjects: Study and database
TLDR
This study shows that post-mortem iris recognition is possible and occasionally works even 17 days after death, contradict a promulgated rumor that iris is unusable shortly after decease. Expand
Post-mortem human iris recognition
TLDR
It is found that more than 90% of irises are still correctly recognized when captured a few hours after death, and that serious iris deterioration begins approximately 22 hours later, since the recognition rate drops to a range of 13.3-73.3% when the cornea starts to be cloudy. Expand
Accurate iris segmentation in non-cooperative environments using fully convolutional networks
TLDR
Experimental results show that MFCNs are more robust than HCNNs to noises, and can greatly improve the current state-of-the-arts by 25.62% and 13.24% on the UBIRIS.v2 and CASIA.v4-distance databases, respectively. Expand
Deep Learning-Based Iris Segmentation for Iris Recognition in Visible Light Environment
TLDR
A two-stage iris segmentation scheme based on convolutional neural network (CNN) is proposed, capable of accurate iris segmentsation in severely noisy environments of iris recognition by visible light camera sensor. Expand
Using artificial neural networks and feature saliency to identify iris measurements that contain the most discriminatory information for iris segmentation
  • R. Broussard, R. Ives
  • Computer Science
  • 2009 IEEE Workshop on Computational Intelligence in Biometrics: Theory, Algorithms, and Applications
  • 2009
TLDR
This research uses of a feature saliency algorithm to identify which measurements, used in common iris segmentation methods, jointly contain the most discriminatory information for identify the iris boundary. Expand
A Review on Deep Learning Techniques Applied to Semantic Segmentation
TLDR
A review on deep learning methods for semantic segmentation applied to various application areas as well as mandatory background concepts to help researchers decide which are the ones that best suit their needs and their targets. Expand
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
TLDR
Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
...
1
2
...