IPSegNet : Deep Convolutional Neural Network Based Segmentation Framework for Iris and Pupil

Patil, Shreyas Malakarjun; Jha, Ranjeet Ranjan; Nigam, Aditya

doi:10.1109/sitis.2017.40

Cited by 3 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Patil et al [185] proposed two approaches of a CNN based on architectures to the region of interest extraction of an iris, namely, IPSegNet1 and IPSegNet2, to obtain a circular region through iris and pupil segmentation together [185].…”

Section: Vgg and R-cnn Architecture-based Modelsmentioning

confidence: 99%

Iris Recognition Development Techniques: A Comprehensive Review

2021

View full text Add to dashboard Cite

Recently, iris recognition techniques have achieved great performance in identification. Among authentication techniques, iris recognition systems have received attention very much due to their rich iris texture which gives robust standards for identifying individuals. Notwithstanding this, there are several challenges in unrestricted recognition environments. In this article, the researchers present the techniques used in different phases of the recognition system of the iris image. The researchers also reviewed the methods associated with each phase. The recognition system is divided into seven phases, namely, the acquisition phase in which the iris images are acquired, the preprocessing phase in which the quality of the iris image is improved, the segmentation phase in which the iris region is separated from the background of the image, the normalization phase in which the segmented iris region is shaped into a rectangle, the feature extraction phase in which the features of the iris region are extracted, the feature selection phase in which the unique features of the iris are selected using feature selection techniques, and finally the classification phase in which the iris images are classified. This article also explains the two approaches of iris recognition which are the traditional approach and the deep learning approach. In addition, the researchers discuss the advantages and disadvantages of previous techniques as well as the limitations and benefits of both the traditional and deep learning approaches of iris recognition. This study can be considered as an initial step towards a large-scale study about iris recognition.

show abstract

Section: Vgg and R-cnn Architecture-based Modelsmentioning

confidence: 99%

Iris Recognition Development Techniques: A Comprehensive Review

2021

View full text Add to dashboard Cite

show abstract

“…Similar to E 1 , the E 2 error rate is given by the average errors (E 2 k ) on all the input test images. Jaccard index (JI)/intersection over union (IOU): It measures the IOU of the labelled segments for each class and reports the average, as given below: (18) where L(=2) is the number of classes. C ii is defined as the number of pixels in the image having ground truth label i and whose prediction is also i. G i is given as the total number of pixels in the image with ground truth label i. P i is defined as the total number of pixels in the image whose prediction is i.…”

Section: Performance Parametersmentioning

confidence: 99%

“…We propose a novel CNN model for Iris ROI segmentation. The proposed network does not use any existing pre‐trained models as proposed in [18, 28].…”

Section: Introductionmentioning

confidence: 99%

“…In [17], the authors experimented with typical fully convolutional encoder–decoder networks and tested a variant which employed Monte Carlo sampling and drop‐out technique on the convolutional weights. In [18], the authors proposed two CNN architectures IPSegNet1 and IPSegNet2 which have been modelled on the lines of object detection networks, Faster RCNN (Region‐based Convolutional Neural Network) [19] and SSD (Single Shot Multi‐Box Detector) [20]. Both the networks have been trained to output two circular region of interests for the Iris and Pupil.…”

Section: Introductionmentioning

confidence: 99%

“…The main contributions of the proposed approach are We propose a novel CNN model for Iris ROI segmentation. The proposed network does not use any existing pre‐trained models as proposed in [18, 28]. We exhibit a multi‐loss function which includes content loss along with cross‐entropy for our segmentation task facilitating in fast and better convergence of loss.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

PixISegNet: pixel‐level iris segmentation network using convolutional encoder–decoder with stacked hourglass bottleneck

et al. 2019

Self Cite

View full text Add to dashboard Cite

In this paper, we present a new iris ROI segmentation algorithm using a deep convolutional neural network (NN) to achieve the state-of-the-art segmentation performance on well-known iris image data sets. The authors' model surpasses the performance of state-of-the-art Iris DenseNet framework by applying several strategies, including multi-scale/ multi-orientation training, model training from scratch, and proper hyper-parameterisation of crucial parameters. The proposed PixISegNet consists of an autoencoder which primarily uses long and short skip connections and a stacked hourglass network between encoder and decoder. There is a continuous scale up-down in stacked hourglass networks, which helps in extracting features at multiple scales and robustly segments the iris even in an occluded environment. Furthermore, cross-entropy loss and content loss optimise the proposed model. The content loss considers the high-level features, thus operating at a different scale of abstraction, which compliments the cross-entropy loss, which considers pixel-to-pixel classification loss. Additionally, they have checked the robustness of the proposed network by rotating images to certain degrees with a change in the aspect ratio along with blurring and a change in contrast. Experimental results on the various iris characteristics demonstrate the superiority of the proposed method over state-of-the-art iris segmentation methods considered in this study. In order to demonstrate the network generalisation, they deploy a very stringent TOTA (i.e. train-once-test-all) strategy. Their proposed method achieves E 1 scores of 0.00672, 0.00916 and 0.00117 on UBIRIS-V2, IIT-D and CASIA V3.0 Interval data sets, respectively. Moreover, such a deep convolutional NN for segmentation when included in an end-to-end iris recognition system with a siamese based matching network will augment the performance of the siamese network.

show abstract