Deep Neural Network and Data Augmentation Methodology for off-axis iris segmentation in wearable headsets

@article{Varkarakis2020DeepNN,
  title={Deep Neural Network and Data Augmentation Methodology for off-axis iris segmentation in wearable headsets},
  author={Viktor Varkarakis and Shabab Bazrafkan and Peter M. Corcoran},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={2020},
  volume={121},
  pages={
          101-121
        }
}
A data augmentation methodology is presented and applied to generate a large dataset of off-axis iris regions and train a low-complexity deep neural network. Although of low complexity the resulting network achieves a high level of accuracy in iris region segmentation for challenging off-axis eye-patches. Interestingly, this network is also shown to achieve high levels of performance for regular, frontal, segmentation of iris regions, comparing favourably with state-of-the-art techniques ofโ€ฆย 
Challenges and Recent Solutions for Image Segmentation in the Era of Deep Learning
  • E. Goceri
  • Computer Science
    2019 Ninth International Conference on Image Processing Theory, Tools and Applications (IPTA)
  • 2019
TLDR
The challenges that are mostly related to architecture and training of deep neural networks are explained and the state-of-the-art solutions applied in the literature are presented to help researchers to design proper network architectures according to their problems.
Deep Learning for Consumer Devices and Services 4โ€”A Review of Learnable Data Augmentation Strategies for Improved Training of Deep Neural Networks
TLDR
This article summarises and discusses the most signficiant of these advanced data augmentation strategies, which have inspired many variations in the last few years.
NIR Iris Challenge Evaluation in Non-cooperative Environments: Segmentation and Localization
TLDR
The 2021 NIR Iris Challenge Evaluation in Non-cooperative Environments: Segmentation and Localization (NIR-ISL 2021) at the 2021 International Joint Conference on Biometrics (IJCB 2021) was used as a public platform to assess the performance of iris segmentation and localization methods on Asian and African NIR iris images captured in non- cooperative environments.
Deep Learning for Consumer Devices and Services 2โ€”AI Gets Embedded at the Edge
TLDR
The current paradigm shift of AI from the data center into CE devicesโ€”โ€œEdge-AIโ€ is explored.
Using Convolutional Neural Network and a Single Heartbeat for ECG Biometric Recognition
TLDR
It was found that the timeโ€“frequency domain representation of a short segment of an ECG signal can be feasible for biometric recognition by achieving better accuracy and acceptability of this modality.
Resampling and Data Augmentation For Equinesโ€™ Behaviour Classification Based on Wearable Sensor Accelerometer Data Using a Convolutional Neural Network
TLDR
This work evaluates the effect of sampling rate reduction of a tri-axial accelerometer on the recognition accuracy by resampling a 50 Hz experimental dataset to four lower sampling rates and shows that sampling at 5 Hz with a 2 s window will offer advantages for activity surveillance thanks to decreased energy requirements.
Contour-Aware Polyp Segmentation in Colonoscopy Images Using Detailed Upsamling Encoder-Decoder Networks
TLDR
A new polyp segmentation method based on an architecture of multi-model deep encoder-decoder networks called MED-Net, which significantly outperforms state-of-the-art methods and presents a complementary strategy for improving the methodโ€™s segmentation performance based on a combination of a boundary-aware data augmentation method and an effective weighted loss function.
Domain adversarial networks and intensity-based data augmentation for male pelvic organ segmentation in cone beam CT
TLDR
In radiation therapy, a CT image is used to manually delineate the organs and plan the treatment, and models trained with CT data do not generalize well to CBCT images, so two strategies leveraging large databases of annotated CTs to train neural networks for segmentation on CBCT are investigated.
To recurse or not to recurse: a low-dose CT study
TLDR
A framework is presented wherein a recurrent neural network is utilized to remove the streaking artefacts from few-view CT imaging by subdividing it into small patches, which indicates that processing each image patch needs less computational power in the RNN network, while in total, the feedforward network is more efficient.
Survey of Iris Image Segmentation and Localization
TLDR
The paper aims to optimise these processes in terms of image capture distance, computation time and memory requirement, using the Dynamic Reconfigurable Processor (DRP) technology along with suitable algorithms for segmentation and localization processes as described in sections 2.2 and 2.3 respectively.
...
1
2
...

References

SHOWING 1-10 OF 113 REFERENCES
A Deep Learning Approach to Segmentation of Distorted Iris Regions in Head-Mounted Displays
TLDR
An appropriate augmentation method is presented to generate the distorted iris dataset used for training from publicly available frontal iris datasets and shows promising results in segmenting off-axis iris images in unconstrained conditions.
An End to End Deep Neural Network for Iris Segmentation in Unconstraint Scenarios
TLDR
An end to end Fully Convolutional Deep Neural Network (FCDNN) design is proposed to perform the iris segmentation task for lower-quality iris images and shows very promising performance when compared with state-of-art techniques applied to the same lower quality datasets.
Domain Adaptation for CNN Based Iris Segmentation
TLDR
Two pixel-level domain adaptation methods can effectively transfer the domains of source databases to those of the targets, producing new adapted databases and indicate that training a specific CNN for a new iris segmentation task, maintaining optimal segmentation scores, is possible using a very low number of training samples.
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.
IrisDenseNet: Robust Iris Segmentation Using Densely Connected Fully Convolutional Networks in the Images by Visible Light and Near-Infrared Light Camera Sensors
TLDR
A densely connected fully convolutional network (IrisDenseNet), which can determine the true iris boundary even with inferior-quality images by using better information gradient flow between the dense blocks is proposed.
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.
SegDenseNet: Iris Segmentation for Pre-and-Post Cataract Surgery
Cataract is one of the major ophthalmic diseases worldwide which can potentially affect the performance of iris-based biometric systems. While existing research has shown that cataract does not haveโ€ฆ
Research on data augmentation for image classification based on convolution neural networks
TLDR
Experimental results show that, under the same condition of multiple increasing, the performance evaluation on small-scale data sets is more obvious, the four individual methods perform generally better than others, and some appropriate combination methods are slightly more effective than the individuals.
An Accurate Iris Segmentation Framework Under Relaxed Imaging Constraints Using Total Variation Model
This paper proposes a novel and more accurate iris segmentation framework to automatically segment iris region from the face images acquired with relaxed imaging under visible or near-infraredโ€ฆ
Efficient segmentation for multi-frame iris acquisition on smartphones
TLDR
An iris segmentation technique, optimized for relatively low quality images acquired with smartphone visible-near infrared cameras is presented and enables multiple iris images to be extracted sequentially at native frame rates.
...
1
2
3
4
5
...