Encoder-Decoder Convolutional Neural Network Based Iris-Sclera Segmentation

Sahin, Gurkan; Susuz, Orkun

doi:10.1109/siu.2019.8806507

Cited by 3 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The researchers have previously proposed different deep learning solutions to segment and recognize the sclera for biometric applications [10], [11], [21], [22], [23]. Maheshan et al [10] proposed a CNN sclera recognition engine consisting of four convolutional units and one fully connected unit.…”

Section: A Related Work 1) Scleramentioning

confidence: 99%

“…They first used the traditional image processing techniques to segment the scleral vasculature, which is then passed on to the SLBNet to identify the person. Similarly, different neural network architectures are implemented in [22] to segment the iris and sclera using two different datasets. Furthermore, in [23], a CNN model called ScleraNET is presented to identify and recognize a person using a sclera vasculature pattern.…”

Section: A Related Work 1) Scleramentioning

confidence: 99%

See 1 more Smart Citation

SIPFormer: Segmentation of Multiocular Biometric Traits With Transformers

Hassan

Ahmed

et al. 2023

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

The advancements in machine vision have opened up new avenues for implementing multimodal biometric identification systems for real-world applications. These systems can address the shortcomings of unimodal biometric systems, which are susceptible to spoofing, noise, nonuniversality, and intraclass variations. Besides, ocular traits among various biometric traits are preferably used in these recognition systems due to their great uniqueness, permanence, and performance. However, segmenting visual biometric features under unconstrained situations remains challenging due to a variety of variables, such as Purkinje reflexes, specular reflections, eye gaze, off-angle pictures, poor resolution, and numerous occlusions. To overcome these challenges, this research presents a novel framework called SIPFormer, comprising the encoder, decoder, and transformer blocks to simultaneously segment three ocular traits (sclera, iris, and pupil) using its discriminative multihead self-attention mechanism. Besides, we used the large publicly available iris database reflecting different unconstrained acquisition settings, with inherent noise effects such as scanner artifacts, intensity and illumination variations, motion blur, and occultations caused by eyelashes, eyelids, and eyeglasses. Furthermore, the simulation results demonstrate the efficacy of the proposed SIPFormer model, where it achieved the mean Dice similarity coefficient scores of 0.9018, 0.9176, and 0.9229 for segmenting the sclera, iris, and pupil classes, respectively.

show abstract

Section: A Related Work 1) Scleramentioning

confidence: 99%

Section: A Related Work 1) Scleramentioning

confidence: 99%

SIPFormer: Segmentation of Multiocular Biometric Traits With Transformers

Hassan

Ahmed

et al. 2023

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…A computer-aided diagnosis of the retinal disease is used in the new screening method. It improves both the quality and the eff [4][5][6]iciency of the work. Glaucoma detection using a computer-aided technique is based on retinal fundus image processing and aids in screening on a wider scale.…”

Section: Introductionmentioning

confidence: 99%

Literature Review on Iris Segmentation and Classification Based on Deep Learning

2022

IRJMETS

View full text Add to dashboard Cite

Iris segmentation algorithms are a key part of full-fledged iris recognition systems and have a direct effect on the results of iris verification and recognition. But when standard iris segmentation algorithms are used on noisy iris databases that were recorded in unrestricted environments, they are not flexible enough and are not strong enough. Also, there aren't any big iris databases right now, so iris segmentation methods can't take full advantage of the benefits of convolution neural networks (CNNs). The problem of iris segmentation in handheld devices is then solved by making a deep learning scheme and coming up with a good way to improve it. Initial comparisons with iris segmentation algorithms that are available to the public show significant performance gains, especially on difficult image datasets that are meant to simulate the quality of images from a handheld device.

show abstract

Presentation Attack Detection Framework

Shahriar

Etienne

2020

Studies in Computational Intelligence

View full text Add to dashboard Cite

Encoder-Decoder Convolutional Neural Network Based Iris-Sclera Segmentation

Cited by 3 publications

References 3 publications

SIPFormer: Segmentation of Multiocular Biometric Traits With Transformers

SIPFormer: Segmentation of Multiocular Biometric Traits With Transformers

Literature Review on Iris Segmentation and Classification Based on Deep Learning

Presentation Attack Detection Framework

Contact Info

Product

Resources

About