Robust Iris Segmentation Algorithm in Non-Cooperative Environments Using Interleaved Residual U-Net

Self Cite

Biometrics has been shown to be an effective solution for the identity recognition problem, and iris recognition, as well as face recognition, are accurate biometric modalities, among others. The higher resolution inside the crucial region reveals details of the physiological characteristics which provides discriminative information to achieve extremely high recognition rate. Due to the growing needs for the IoT device in various applications, the image sensor is gradually integrated in the IoT device to decrease the cost, and low-cost image sensors may be preferable than high-cost ones. However, low-cost image sensors may not satisfy the minimum requirement of the resolution, which definitely leads to the decrease of the recognition accuracy. Therefore, how to maintain high accuracy for biometric systems without using expensive high-cost image sensors in mobile sensing networks becomes an interesting and important issue. In this paper, we proposed MA-SRGAN, a single image super-resolution (SISR) algorithm, based on the mask-attention mechanism used in Generative Adversarial Network (GAN). We modified the latest state-of-the-art (nESRGAN+) in the GAN-based SR model by adding an extra part of a discriminator with an additional loss term to force the GAN to pay more attention within the region of interest (ROI). The experiments were performed on the CASIA-Thousand-v4 dataset and the Celeb Attribute dataset. The experimental results show that the proposed method successfully learns the details of features inside the crucial region by enhancing the recognition accuracies after image super-resolution (SR).

Section: Methodsmentioning

confidence: 99%

Mask Attention-SRGAN for Mobile Sensing Networks

Huang

Chang

2021

Self Cite

“…Later, researchers utilized existing [ 55 , 56 , 57 , 58 ], customized [ 18 , 59 ], and fully connected networks (FCN) models for iris segmentation and gained the best segmentation accuracy on several iris datasets. Li et al [ 1 ], Lian et al [ 58 ], Lozej et al [ 60 ], Wu and Zhao [ 61 ], and Zhang et al [ 62 ], scholars employed alternatives of U-Net [ 24 ] for iris segmentation.…”

Section: Related Workmentioning

confidence: 99%

“…Over the past few years, iris recognition has emerged as one of the most suitable and trustworthy biometric modalities among those currently available in the private sector [ 1 , 2 , 3 , 4 ]. Automated iris recognition systems, therefore, have been extensively installed in several biometrics applications, including [ 5 ], border-crossing control [ 6 , 7 ], citizenship verification [ 8 ], digital forensic, and industrial products.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, the accuracy of the iris segmentation is enormously significant [ 15 ]. Over the past decades, with the rapid development of deep learning, a vast number of investigations employing CNNs have been introduced for iris segmentation [ 1 , 16 , 17 , 18 , 19 , 20 ], iris bounding box identification [ 19 ], and pupil center identification [ 21 , 22 , 23 ]. The latest image segmentation models are variants of encoder-decoder architectures such as U-Net [ 24 ] and fully convolutional networks (FCN) [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Supervised Learning Framework toward State-of-the-Art Iris Image Segmentation

Putri

Liu

Aslam

et al. 2022

Self Cite

Iris segmentation plays a pivotal role in the iris recognition system. The deep learning technique developed in recent years has gradually been applied to iris recognition techniques. As we all know, applying deep learning techniques requires a large number of data sets with high-quality manual labels. The larger the amount of data, the better the algorithm performs. In this paper, we propose a self-supervised framework utilizing the pix2pix conditional adversarial network for generating unlimited diversified iris images. Then, the generated iris images are used to train the iris segmentation network to achieve state-of-the-art performance. We also propose an algorithm to generate iris masks based on 11 tunable parameters, which can be generated randomly. Such a framework can generate an unlimited amount of photo-realistic training data for down-stream tasks. Experimental results demonstrate that the proposed framework achieved promising results in all commonly used metrics. The proposed framework can be easily generalized to any object segmentation task with a simple fine-tuning of the mask generation algorithm.

“…In this work, the aim is to employ advanced algorithms of deep learning to automatically distinguish and classify all ionospheric layers from highly noisy ionograms. Specifically, we train and apply five artificial neural network models: DeepLab [ 9 ], fully convolutional DenseNet (FC-DenseNet) [ 1 , 10 ], deep watershed transform (DWT) [ 11 , 12 ], Mask R-CNN [ 13 , 14 ], and Spatial Attention U-Net (SA-UNet) [ 15 , 16 ]; all of these have been successfully applied to image segmentation [ 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 ]. It is important to note that all these models are available at (access on 29 March 2022) and thus can be easily applied and verified.…”

Section: Introductionmentioning

confidence: 99%

State-of-the-Art Capability of Convolutional Neural Networks to Distinguish the Signal in the Ionosphere

Chang

Lin

Дмитриев

et al. 2022

Self Cite

Recovering and distinguishing different ionospheric layers and signals usually requires slow and complicated procedures. In this work, we construct and train five convolutional neural network (CNN) models: DeepLab, fully convolutional DenseNet24 (FC-DenseNet24), deep watershed transform (DWT), Mask R-CNN, and spatial attention-UNet (SA-UNet) for the recovery of ionograms. The performance of the models is evaluated by intersection over union (IoU). We collect and manually label 6131 ionograms, which are acquired from a low-latitude ionosonde in Taiwan. These ionograms are contaminated by strong quasi-static noise, with an average signal-to-noise ratio (SNR) equal to 1.4. Applying the five models to these noisy ionograms, we show that the models can recover useful signals with IoU > 0.6. The highest accuracy is achieved by SA-UNet. For signals with less than 15% of samples in the data set, they can be recovered by Mask R-CNN to some degree (IoU > 0.2). In addition to the number of samples, we identify and examine the effects of three factors: (1) SNR, (2) shape of signal, (3) overlapping of signals on the recovery accuracy of different models. Our results indicate that FC-DenseNet24, DWT, Mask R-CNN and SA-UNet are capable of identifying signals from very noisy ionograms (SNR < 1.4), overlapping signals can be well identified by DWT, Mask R-CNN and SA-UNet, and that more elongated signals are better identified by all models.