Mobile Iris Challenge Evaluation Research Articles

Efficient method for segmentation of noisy and non‐circular iris images using improved particle swarm optimisation‐based MRFCM

Segmentation of the iris is a crucial stage in an automated iris-based recognition system. The performance of any biometric system primarily relies on how effectively the iris is extracted from the unwanted parts of an iris image. The process of iris segmentation is mainly affected by the noise artefacts such as eyelid/eyelashes occlusions, specular reflections, intensity inhomogeneities, and non-circularity of the iris boundary. A novel and an efficient method has been proposed in this work to segment noisy and non-circular iris boundaries. The mathematical modelling of morphological reconstruct fuzzy C-means clustering (MRFCM) has been presented. The MRFCM based on improved particle swarm optimisation has been implemented before the segmentation in the recognition framework. The resultant images are then segmented by employing geodesic active contours incorporated by a new stopping function. The effect of the proposed segmentation method on iris recognition is observed through matching score distribution. The popular and publicly available datasets such as UBIRISv1, CASIA-v3-Interval, MMU1, and Mobile Iris Challenge Evaluation databases are considered for the evaluation of the proposed method. Recognition accuracy is validated and compared with the well-existing methods.

FRED-Net: Fully residual encoder–decoder network for accurate iris segmentation

Iris recognition is now developed enough to recognize a person from a distance. The process of iris segmentation plays a vital role in maintaining the accuracy of the iris-based recognition systems by limiting the errors at the current stage. However, its performance is affected by non-ideal situations created by environmental light noise and user non-cooperation. The existing local feature-based segmentation methods are unable to find the true iris boundary in these non-ideal situations, and the error created at the segmentation stage traverses to all the subsequent stages, which results in reduced accuracy and reliability. In addition, it is necessary to segment the true iris boundary without the extra cost of denoising as preprocessing. To overcome these challenging issues during iris segmentation, a deep learning-based fully residual encoder–decoder network (FRED-Net) is proposed to determine the true iris region with the flow of high-frequency information from the preceding layers via residual skip connection.The main four impacts and significances of this study are as follows. First, FRED-Net is an end-to-end semantic segmentation network that does not use conventional image processing schemes, and does not have a preprocessing overhead. It is a standalone network in which eyelid, eyelash, and glint detections are not required to obtain the true iris boundary. Second, the proposed FRED-Net is the final resultant structure of a step-by-step development, and in each step, a new complete variant network is created for semantic segmentation considering the detailed descriptions of the networks. Third, FRED-Net uses the residual connectivity between convolutional layers by the residual shortcut for both encoder and decoder, which enables a high-frequency component to flow through the network and achieve higher accuracy with few layers. Fourth, the performance of the proposed FRED-Net is tested with five different iris datasets under visible and NIR light environments, and two general road scene segmentation datasets. To achieve fair comparisons with other studies, our trained FRED-Net models, along with the algorithms, are made publicly available through our website (Dongguk FRED-Net Model with Algorithm. accessed on 16 May 2018).The experiments include two datasets: Noisy Iris Challenge Evaluation – Part II (NICE-II) selected from the UBIRIS.v2 database and Mobile Iris Challenge Evaluation (MICHE-I), for the visible light environment and three datasets: Institute of Automation, Chinese Academy of Sciences (CASIA) v4.0 interval, v4.0 distance, and IIT Delhi v1.0, for the near-infrared (NIR) light environment. Moreover, to evaluate the performance of the proposed network in general segmentation, experiments with two famous road scene segmentation datasets: Cambridge-driving Labeled Video Database (CamVid) and Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI), are included. The experimental results showed the optimum performance of the proposed FRED-Net on the above-mentioned seven datasets of iris and general road scene segmentation.

IrisDenseNet: Robust Iris Segmentation Using Densely Connected Fully Convolutional Networks in the Images by Visible Light and Near-Infrared Light Camera Sensors.

The recent advancements in computer vision have opened new horizons for deploying biometric recognition algorithms in mobile and handheld devices. Similarly, iris recognition is now much needed in unconstraint scenarios with accuracy. These environments make the acquired iris image exhibit occlusion, low resolution, blur, unusual glint, ghost effect, and off-angles. The prevailing segmentation algorithms cannot cope with these constraints. In addition, owing to the unavailability of near-infrared (NIR) light, iris recognition in visible light environment makes the iris segmentation challenging with the noise of visible light. Deep learning with convolutional neural networks (CNN) has brought a considerable breakthrough in various applications. To address the iris segmentation issues in challenging situations by visible light and near-infrared light camera sensors, this paper proposes 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. In the experiments conducted, five datasets of visible light and NIR environments were used. For visible light environment, noisy iris challenge evaluation part-II (NICE-II selected from UBIRIS.v2 database) and mobile iris challenge evaluation (MICHE-I) datasets were used. For NIR environment, the institute of automation, Chinese academy of sciences (CASIA) v4.0 interval, CASIA v4.0 distance, and IIT Delhi v1.0 iris datasets were used. Experimental results showed the optimal segmentation of the proposed IrisDenseNet and its excellent performance over existing algorithms for all five datasets.

Noncircular Iris Segmentation Based on Weighted Adaptive Hough Transform Using Smartphone Database

Iris segmentation methods work based on ideal imaging conditions which produce good output results. However, the segmentation accuracy of an iris recognition system significantly influences its performance, especially with data that captured in unconstrained environment of the Smartphone. This paper proposes a novel segmentation method for unconstrained environment of the Smartphone videos based on choose the best frames from the videos and try to enhance the contrast of this frames by applying the two fuzzy logic membership functions on the negative image which delimit between dark and bright regions in able to make the dark region darker and the bright region brighter. This pre-processing step Facilitates the work of the Weighted Adaptive Hough Transform to automatically find the diameter of the iris region to apply the osiris v4.1. The proposed method results on the video of (Mobile Iris Challenge Evaluation (MICHE))-I, iris databases indicate a high level of accuracy and more efficient computationally using the proposed technique.

Noisy Ocular Recognition Based on Three Convolutional Neural Networks.

In recent years, the iris recognition system has been gaining increasing acceptance for applications such as access control and smartphone security. When the images of the iris are obtained under unconstrained conditions, an issue of undermined quality is caused by optical and motion blur, off-angle view (the user’s eyes looking somewhere else, not into the front of the camera), specular reflection (SR) and other factors. Such noisy iris images increase intra-individual variations and, as a result, reduce the accuracy of iris recognition. A typical iris recognition system requires a near-infrared (NIR) illuminator along with an NIR camera, which are larger and more expensive than fingerprint recognition equipment. Hence, many studies have proposed methods of using iris images captured by a visible light camera without the need for an additional illuminator. In this research, we propose a new recognition method for noisy iris and ocular images by using one iris and two periocular regions, based on three convolutional neural networks (CNNs). Experiments were conducted by using the noisy iris challenge evaluation-part II (NICE.II) training dataset (selected from the university of Beira iris (UBIRIS).v2 database), mobile iris challenge evaluation (MICHE) database, and institute of automation of Chinese academy of sciences (CASIA)-Iris-Distance database. As a result, the method proposed by this study outperformed previous methods.

Deep Learning-Based Iris Segmentation for Iris Recognition in Visible Light Environment

Existing iris recognition systems are heavily dependent on specific conditions, such as the distance of image acquisition and the stop-and-stare environment, which require significant user cooperation. In environments where user cooperation is not guaranteed, prevailing segmentation schemes of the iris region are confronted with many problems, such as heavy occlusion of eyelashes, invalid off-axis rotations, motion blurs, and non-regular reflections in the eye area. In addition, iris recognition based on visible light environment has been investigated to avoid the use of additional near-infrared (NIR) light camera and NIR illuminator, which increased the difficulty of segmenting the iris region accurately owing to the environmental noise of visible light. To address these issues; this study proposes a two-stage iris segmentation scheme based on convolutional neural network (CNN); which is capable of accurate iris segmentation in severely noisy environments of iris recognition by visible light camera sensor. In the experiment; the noisy iris challenge evaluation part-II (NICE-II) training database (selected from the UBIRIS.v2 database) and mobile iris challenge evaluation (MICHE) dataset were used. Experimental results showed that our method outperformed the existing segmentation methods.

Insights into the results of MICHE I - Mobile Iris CHallenge Evaluation

Mobile biometrics technologies are nowadays the new frontier for secure use of data and services, and are considered particularly important due to the massive use of handheld devices in the entire world. Among the biometric traits with potential to be used in mobile settings, the iris/ocular region is a natural candidate, even considering that further advances in the technology are required to meet the operational requirements of such ambitious environments. Aiming at promoting these advances, we organized the Mobile Iris Challenge Evaluation (MICHE)-I contest. This paper presents a comparison of the performance of the participant methods by various Figures of Merit (FoMs). A particular attention is devoted to the identification of the image covariates that are likely to cause a decrease in the performance levels of the compared algorithms. Among these factors, interoperability among different devices plays an important role. The methods (or parts of them) implemented by the analyzed approaches are classified into segmentation (S), which was the main target of MICHE-I, and recognition (R). The paper reports both the results observed for either S or R, and also for different recombinations (S+R) of such methods. Last but not least, we also present the results obtained by multi-classifier strategies.

FIRE: Fast Iris REcognition on mobile phones by combining colour and texture features

FIRE is a Fast Iris REcognition algorithm especially designed for iris recognition on mobile phones under visible-light. It is based on the combination of three classifiers exploiting the iris colour and texture information. Its limited computational time makes FIRE particularly suitable for fast user verification on mobile devices. The high parallelism of the code allows its use also on large databases. FIRE, in its first version, was submitted to the Mobile Iris CHallenge Evaluation part II held in 2016. In this paper, FIRE is further improved: a number of different techniques has been analyzed and the best performing ones have been selected for fusion at score level. Performance are assessed in terms of Recognition Rate (RR), Area Under Receiver Operating Characteristic Curve (AUC), and Equal Error Rate (EER).

Results from MICHE II – Mobile Iris CHallenge Evaluation II

Mobile biometrics represent the new frontier of authentication. The most appealing feature of mobile devices is the wide availability and the presence of more and more reliable sensors for capturing biometric traits, e.g., cameras and accelerometers. Moreover, they more and more often store personal and sensitive data, that need to be protected. Doing this on the same device using biometrics to enforce security seems a natural solution. This makes this research topic attracting and generally promising. However, the growing interest for related applications is counterbalanced by still present limitations, especially for some traits. Acquisition and computation resources are nowadays widely available, but they are not always sufficient to allow a reliable recognition result. Most of all, the way capture is expected to be carried out, i.e., by the user him/herself in uncontrolled conditions and without an expert assistance, can heavily affect the quality of samples and, as a consequence, the accuracy of recognition. Among the biometric traits raising the interest of researchers, iris plays an important role. Mobile Iris CHallenge Evaluation II (MICHE II) competition provided a testbed to assess the progress of mobile iris recognition, as well as its limitations still to overcome. This paper presents the results of the competition and the analysis of achieved performance, that takes into account both proposals submitted for the competition section launched at the 2016 edition of the International Conference on Pattern Recognition (ICPR), as well as proposals submitted for this special issue.