Dataset Of Iris Images Research Articles

Classification of data on stacked autoencoder using modified sigmoid activation function

A Neural Network is one of the techniques by which we classify data. In this paper, we have proposed an effectively stacked autoencoder with the help of a modified sigmoid activation function. We have made a two-layer stacked autoencoder with a modified sigmoid activation function. We have compared our autoencoder to the existing autoencoder technique. In the existing autoencoder technique, we generally use the logsigmoid activation function. But in multiple cases using this technique, we cannot achieve better results. In that case, we may use our technique for achieving better results. Our proposed autoencoder may achieve better results compared to this existing autoencoder technique. The reason behind this is that our modified sigmoid activation function gives more variations for different input values. We have tested our proposed autoencoder on the iris, glass, wine, ovarian, and digit image datasets for comparison propose. The existing autoencoder technique has achieved 96% accuracy on the iris, 91% accuracy on wine, 95.4% accuracy on ovarian, 96.3% accuracy on glass, and 98.7% accuracy on digit (image) dataset. Our proposed autoencoder has achieved 100% accuracy on the iris, wine, ovarian, and glass, and 99.4% accuracy on digit (image) datasets. For more verification of the effeteness of our proposed autoencoder, we have taken three more datasets. They are abalone, thyroid, and chemical datasets. Our proposed autoencoder has achieved 100% accuracy on the abalone and chemical, and 96% accuracy on thyroid datasets.

Deep Learning-Based Iris Segmentation Algorithm for Effective Iris Recognition System

In this study, a 19-layer convolutional neural network model is developed for accurate iris segmentation and is trained and validated using five publicly available iris image datasets. An integrodifferential operator is used to create labeled images for CASIA v1.0, CASIA v2.0, and PolyU Iris image datasets. The performance of the proposed model is evaluated based on accuracy, sensitivity, selectivity, precision, and F-score. The accuracy obtained for CASIA v1.0, CASIA v2.0, CASIA Iris Interval, IITD, and PolyU Iris are 0.82, 0.97, 0.9923, 0.9942, and 0.98, respectively. The result shows that the proposed model can accurately predict iris and non-iris regions and thus can be an effective tool for iris segmentation.

A Novel Approach for Gaussian Mixture Model Clustering Based on Soft Computing Method

Determining the number of clusters in a data set is a significant and difficult problem in cluster analysis. In this study, a new model-based clustering approach is proposed for the estimation of the number of clusters. In the proposed method, the number of components in each variable is determined by using univariate Gaussian mixture models. The number of alternative cluster centres and mixture models was determined according to the number of components in heterogeneous variables. In this study, appropriate Gaussian mixture models were determined with the help of "mixture model soft computing method" for the first time. Vector arrays showing the number and addresses of clusters in appropriate Gaussian mixture models were created, and according to the parameter estimations of these models that fit the arrays, the best model was obtained through information criteria. The clustering success achieved with the proposed mixture model soft computing method was compared with the results of Gaussian mixture model clustering methods namely, mclust, clustvarsel, varselLCM, selvarMix and vscc model selection methods in R package. All respective methods analyse and determine the number of clustering for the data sets, synthetic-1, synthetic-2, Iris, and Landsat Satellite Image data sets, respectively and evaluate the correct classification rate. The results revealed that the proposed method shows better results for the determination of number of clustering as well as correct classification rate. The novelty of the study is that a new model-based dimension reduction method is proposed for the estimation of the number of clusters. A deterministic clustering approach is proposed for clustering and classification success on reduced data.

Iris Recognition Performance in Children: A Longitudinal Study

There is uncertainty around the effect of aging of children on biometric characteristics impacting applications relying on biometric recognition, particularly as the time between enrollment and query increases. Though there have been studies of such effects for iris recognition in adults, there have been few studies evaluating impact in children. This paper presents longitudinal analysis from 209 subjects aged 4 to 11 years at enrollment and six additional sessions over a period of 3 years. The influence of time, dilation and enrollment age on iris recognition have been analyzed and their statistical importance has been evaluated. A minor aging effect is noted which is statistically significant, but practically insignificant and is comparatively less important than other variability factors. Practical biometric applications of iris recognition in children are feasible for a time frame of at least 3 years between samples, for ages 4 to 11 years, even in presence of aging, though we note practical difficulties in enrolling young children with cameras not designed for the purpose. To the best of our knowledge, the database used in this study is the only dataset of longitudinal iris images from children for this age group and time period that is available for research.

Bio‐PUF‐MAC authenticated encryption for iris biometrics

AbstractBiometrics is one of the ways for human authentication. Fabrication of biometrics by intruders, limits the accuracy of authentication. The user‐specific keys (ie,) pseudo‐random numbers give more security for biometric template protection and increase the accuracy of authentication also. The user‐specific token or keys can also be fabricated by intruders by any of the prediction methods. To avoid the creation of fake biometric and fake user‐specific keys, a device‐specific Physical Unclonable Function (PUF) is proposed. In this article, iris authentication is provided by unclonable PUF‐based true random numbers to enhance the unique authentication. Nonreversible Message Authentication Codes (MAC) are developed using PUF and Discrete Wavelet Transform features of iris biometrics. Systematically, MAC codes also created with, encryption algorithm. Encryption is additionally providing confidentiality in the individual iris. Experiments are done with CUHK Iris Image Dataset. Proposed Bio‐PUF system has significant functional advantages in point of view of the unclonable pseudo‐random number from PUF. Experimentally, Avalanche effect, entropy, NCPR, and UACI parameters are analyzed with PUF‐based crypt functions. For 75% of matching with the Bio‐PUF‐MAC codes with enrolment, the accuracy for correct identification is 77.73%.

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

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 Pix I SegNet 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.

Efficient iris recognition using Haralick features based extraction and fuzzy particle swarm optimization

Iris identification technology is the most versatile non-contact scanning technique, based on mathematical pattern matching. This outstanding authentication method proves its merit exceedingly well in terms of high verification speed, capability of handling large database, reliability for both 1:1 and 1:n verification mode. Iris recognition technology evaluates the unique features of iris for efficient identification or verification of identity of human beings. This biometric technique can be successfully deployed for time and attendance, surveillance, ATM, E-commerce and banking kiosks, border control mechanism, criminal identification, citizen identification, PC/network access, and so on. The distinctive and complex iris pattern has the capability for remarkably high rate of accuracy in recognition. This deployment is composed of image acquisition, image preprocessing, feature extraction, template generation, template matching and classification. Our research work applies improved techniques for optimal iris recognition. Weight sampled geodesic active contours technique efficiently segments the edges of iris. Besides Haralick feature extraction method extracts the key features of iris. Optimized feature selection is carried out by fuzzy controlled particle swarm optimization, inspired by biological evolution and swarming intelligence. Relevance vector machine, a machine learning technique superior than traditional support vector machines performs much better probabilistic supervised classification. The experiments with CASIA version 3 dataset of iris images proves the proposed methods overweigh the existing methods in terms of accuracy, processing time, specificity and sensitivity.

Multibiometric system using fuzzy level set, and genetic and evolutionary feature extraction

This study presents a multimodal system that optimises and integrates the iris and face features based on fusion at the score level. The proposed multibiometric system has two novelties as compared with the previous work. First, the authors deploy a fuzzy C-means clustering with level set (FCMLS) method in an effort to localise the non-ideal iris images accurately. The FCMLS method incorporates the spatial information into the level set (LS)-based curve evolution approach and regularises the LS propagation locally. The proposed iris localisation scheme based on FCMLS avoids over-segmentation and performs well against blurred iris/sclera boundary. Second, genetic and evolutionary feature extraction (GEFE) is applied towards multimodal biometric recognition. GEFE uses genetic and evolutionary computation to evolve local binary pattern feature extractors to elicit distinctive features from the iris and facial images. Different weights for each modality are investigated to determine the significance of each modality. By using the FCMLS method to segment an iris image accurately, as well as using GEFE on a multibiometric dataset, the authors note improved performance of identification and verification accuracies over subjects on a unimodal dataset. More specifically, on the multimodal dataset of face and iris images, GEFE had an identification accuracy of 100%.

IRIS Recognition System using Neural Network and Genetic Algorithm

this paper, the author proposes a method for personal identification based on iris recognition using Genetic algorithm and Neural Network. The process of iris recognition consists of localization of the iris region and generation of data set of iris images followed by iris pattern recognition. A Neural Network is used to reduce the low recognition rate, low accuracy and increased time of recovery. Here the genetic algorithm is used to optimize the Neural Networks parameters. The simulation results show a good identification rate and reduced training time. Keywordsalgorithm, Neural Network, Iris recognition

Iris segmentation using variational level set method

Continuous efforts have been made to process degraded iris images for enhancement of the iris recognition performance in unconstrained situations. Recently, many researchers have focused on developing the iris segmentation techniques, which can deal with iris images in a non-cooperative environment where the probability of acquiring unideal iris images is very high due to gaze deviation, noise, blurring, and occlusion by eyelashes, eyelids, glasses, and hair. Although there have been many iris segmentation methods, most focus primarily on the accurate detection of iris images captured in a closely controlled environment. The novelty of this research effort is that we propose to apply a variational level set-based curve evolution scheme that uses a significantly larger time step to numerically solve the evolution partial differential equation (PDE) for segmentation of an unideal iris image accurately, and thereby, speeding up the curve evolution process drastically. The iris boundary represented by the variational level set may break and merge naturally during evolution, and thus, the topological changes are handled automatically. The proposed variational model is also robust against poor localization and weak iris/sclera boundaries. In order to solve the size irregularities occurring due to arbitrary shapes of the extracted iris/pupil regions, a simple method is applied based on connection of adjacent contour points. Furthermore, to reduce the noise effect, we apply a pixel-wise adaptive 2D Wiener filter. The verification and identification performance of the proposed scheme is validated on three challenging iris image datasets, namely, the ICE 2005, the WVU Unideal, and the UBIRIS Version 1.

IMPROVEMENT OF IRIS RECOGNITION PERFORMANCE USING REGION-BASED ACTIVE CONTOURS, GENETIC ALGORITHMS AND SVMs

Most existing iris recognition algorithms focus on the processing and recognition of the ideal iris images that are acquired in a controlled environment. In this paper, we process the nonideal iris images that are captured in an unconstrained situation and are affected severely by gaze deviation, eyelids and eyelashes occlusions, nonuniform intensity, motion blur, reflections, etc. The proposed iris recognition algorithm has three novelties as compared to the previous works; firstly, we deploy a region-based active contour model to segment a nonideal iris image with intensity inhomogeneity; secondly, genetic algorithms (GAs) are deployed to select the subset of informative texture features without compromising the recognition accuracy; Thirdly, to speed up the matching process and to control the misclassification error, we apply a combined approach called the adaptive asymmetrical support vector machines (AASVMs). The verification and identification performance of the proposed scheme is validated on three challenging iris image datasets, namely, the ICE 2005, the WVU Nonideal, and the UBIRIS Version 1.

IRIS RECOGNITION BASED ON HILBERT–HUANG TRANSFORM

As a reliable approach for human identification, iris recognition has received increasing attention in recent years. This paper proposes a new analysis method for iris recognition based on Hilbert–Huang transform (HHT). We first divide a normalized iris image into several subregions. Then the main frequency center information based on HHT of each subregion is employed to form the feature vector. The proposed iris recognition method has nice properties, such as translation invariance, scale invariance, rotation invariance, illumination invariance and robustness to high frequency noise. Moreover, the experimental results on the CASIA iris database which is the largest publicly available iris image data sets show that the performance of the proposed method is encouraging and comparable to the best iris recognition algorithm found in the current literature.

Neural network based biometric personal identification with fast iris segmentation

This paper presents the iris recognition system for biometric personal identification using neural network. Personal identification consists of localization of the iris region and generation of a data set of iris images followed by iris pattern recognition. In this paper, a fast algorithm is proposed for the localization of the inner and outer boundaries of the iris region. Located iris is extracted from an eye image, and, after normalization and enhancement, it is represented by a data set. Using this data set a Neural Network (NN) is used for the classification of iris patterns. The adaptive learning strategy is applied for training of the NN. The results of simulations illustrate the effectiveness of the neural system in personal identification.

DCT-Based Iris Recognition

This paper presents a novel iris coding method based on differences of discrete cosine transform (DCT) coefficients of overlapped angular patches from normalized iris images. The feature extraction capabilities of the DCT are optimized on the two largest publicly available iris image data sets, 2,156 images of 308 eyes from the CASIA database and 2,955 images of 150 eyes from the Bath database. On this data, we achieve 100 percent Correct Recognition Rate (CRR) and perfect Receiver-Operating Characteristic (ROC) Curves with no registered false accepts or rejects. Individual feature bit and patch position parameters are optimized for matching through a product-of-sum approach to Hamming distance calculation. For verification, a variable threshold is applied to the distance metric and the False Acceptance Rate (FAR) and False Rejection Rate (FRR) are recorded. A new worst-case metric is proposed for predicting practical system performance in the absence of matching failures, and the worst case theoretical Equal Error Rate (EER) is predicted to be as low as 2.59 x 10(-4) on the available data sets.