Iris Localization Research Articles

Study of Iris Pattern Matching and Detection of the Persons having Squint

Objectives: The present paper has attempted a quantitative study to measure the amount of off centricity of the iris from its normal position. Methods/Statistical Analysis: The eye image having squint has been taken from real life image (CASIA DATABASE). First of all the central position of the eye opening between the eyelids are detected by Matlab code. Then the distance between the locations of the squint eye are taken by using 3X3 spatial filter with a local searching method. Findings: Squint is the off centre location of iris and pupils and may occur either in one eye or both of the eyes and both male and female persons may have squint. The local searching method terminates when the centre of the filter coincides with the centre of the pupil of the squint eye. The filters are moved from the centre of the eye by coinciding the centre of the spatial filter with the centre of the eye in vertical, horizontal and angular directions. Application/Improvement: By this process noises will be reduced which are prevalent in squint eye. The number of pixels responsible for the exact locations may be compensated by making the successive position of the filters bit overlapping which will in turn reduce the possibility of having checker board appearance in the output of the image.

Webcam‐based system for video‐oculography

Video‐oculography (VOG) is a tool providing diagnostic information about the progress of the diseases that cause regression of the vergence eye movements, such as Parkinson's disease (PD). The majority of the existing systems are based on sophisticated infra‐red (IR) devices. In this study, the authors show that a webcam‐based VOG system can provide similar accuracy to that of a head‐mounted IR‐based VOG system. They also prove that the authors’ iris localisation algorithm outperforms current state‐of‐the‐art methods on the popular BioID dataset in terms of accuracy. The proposed system consists of a set of image processing algorithms: face detection, facial features localisation and iris localisation. They have performed examinations on patients suffering from PD using their system and a JAZZ‐novo head‐mounted device with IR sensor as reference. In the experiments, they have obtained a mean correlation of 0.841 between the results from their method and those from the JAZZ‐novo. They have shown that the accuracy of their visual system is similar to the accuracy of IR head‐mounted devices. In the future, they plan to extend their experiments to inexpensive high frame rate cameras which can potentially provide more diagnostic parameters.

Hardware implementation of a novel edge-map generation technique for pupil detection in NIR images

This paper proposes an edge-map generation technique for pupil detection in near infrared (NIR) images and its hardware implementation. The proposed edge-map generation technique is based on generating two different edge-maps of same eye image using Gaussian filtering, image binarization and Sobel edge detection operations and then combining them to a single edge-map using intersection operation on binary images. This technique reduces the false edges drastically in the edge-map of eye image, which is desirable for accurate and fast pupil detection. Field programmable logic array (FPGA) based hardware implementation of the proposed technique is presented, which can be used in iris localization system on FPGA based platforms for iris recognition application. The proposed edge-map generation hardware is a parallel-pipelined implementation.

Quality-based iris segmentation-level fusion

Iris localisation and segmentation are challenging and critical tasks in iris biometric recognition. Especially in non-cooperative and less ideal environments, their impact on overall system performance has been identified as a major issue. In order to avoid a propagation of system errors along the processing chain, this paper investigates iris fusion at segmentation-level prior to feature extraction and presents a framework for this task. A novel intelligent reference method for iris segmentation-level fusion is presented, which uses a learning-based approach predicting ground truth segmentation performance from quality indicators and model-based fusion to create combined boundaries. The new technique is analysed with regard to its capability to combine segmentation results (pupillary and limbic boundaries) of multiple segmentation algorithms. Results are validated on pairwise combinations of four open source iris segmentation algorithms with regard to the public CASIA and IITD iris databases illustrating the high versatility of the proposed method.

Retina Recognition Using Support Vector Machine

This paper presents an efficient algorithm for iris recognition using support vector machine, and genetic and evolutionary feature extraction techniques. The novelty of this research effort is that we deploy a preprocessing method in an effort to localize the non-ideal iris images accurately. The SVM method incorporates the spatial information into the level set-based curve evolution approach and regularizes the level set propagation locally. The proposed iris localization scheme based on SVM avoids the oversegmentation and performs well against blurred iris/sclera boundary. Furthermore, we apply a genetic and evolutionary feature extraction (GEFE) technique, which uses genetic and evolutionary computation to evolve modified local binary pattern (MLBP) feature extractor to elicit the distinctive features from the unwrapped iris images. The MLBP algorithm combines the sign and magnitude features for the improvement of iris texture classification performance. The identification and verification performance of the proposed scheme is validated using the CASIA version 3 interval dataset.

The Bovine Iris Location Method Based on Dynamic Contour Tracking and Least Square Principle

The Bovine Iris Location Method Based on Dynamic Contour Tracking and Least Square Principle

An Efficient Approach for Simple Iris Localization and Normalization Technique

An Efficient Approach for Simple Iris Localization and Normalization Technique

Iris Recognition using Gray Level Co-occurrence Matrix and Hausdorff Dimension

Biometrics authentication is the only accurate solution for personal identification and security problems. Password incorrect use and misapplication, intentional and inadvertent is a gaping hole in security. These results are mainly occurs due to Poor human judgment, carelessness and due to tactlessness. Biometric removes all these types of security mistakes. In iris recognition system identification and verification is one of the efficient method. The objective of this proposed system is to analyze the performance of iris. The segmentation of the iris utilizes shape, intensity, and location information for pupil or iris localization and performs normalization of the iris region by unwrapping the circular region into a rectangular region. The feature extraction of iris was done by biometrics GLCM (Gray Scale Co-occurrence Matrix) and HD (Hausdorff Dimension. The BGM (Biometric Graph Matching) algorithm is used, which is used to match the graph between the training image and test image of the iris biometric. The BGM algorithm uses graph topology to define different feature values of the iris templates. A SVM (Support Vector Machine) classifier is used to distinguish between genuine and imposter. The results give better performance and authentication than the existing method.

Human Iris Recognition for Clean Electoral Process in India by Creating a Fraud Free Voter Registration List

Human Iris pattern matching and recognition system is considered to be the best biometric identification found so far because of the unique features found in the iris and moreover the textured patterns of iris remain stable, invariant and distinct throughout the whole life. Iris recognition techniques involve a mathematical analysis of the unique stable patterns that are structured within the iris and then the comparison is being done with an already existing database. In this paper the implementation of creating a fraud free voter ID list is being done as to make a clean Electoral environment. For this localization of Iris and Pupils are done by canny edge detection algorithm, Normalization is done by Dougman's Normalization method and feature extraction is being done using Log Gabor Filter and lastly method of matching is accomplished by Euclidian distance1,2. MATLAB 2011 version is used for developing the present study, and much of the emphasis is given on software for Recognition of Irises in an efficient manner.

Recognition of Non Circular Iris Pattern of the Goat by Structural, Statistical and Fourier Descriptors

The present paper has described a comparative study to find the iris pattern of the goat which has nearly rectangular or square type appearance. For detecting the structural descriptors, the deviation of the iris pattern shape and size from a standard circular (annular) shaped have been thoroughly studied. Statistical feature extraction has mainly dealt with the various types of moments e.g. – mean variance skewness and kurtosis1,2. Fourier descriptors have been extracted by 2D Fourier Transformation of the entire data set comprising patterns. It has been found that Fourier Descriptors are not directly insensitive to possible geometrical changes of the iris location like translation, rotation and scale change occurring due to eye ball movement and blinking of the eye lids. The result shows that the structural descriptors based pattern recognition rate produce a recognition rate of 97.85% with 4.5% of false acceptance rate and 2.2% false rejection rate. The images during the study were acquired from real life with 16 megapixel camera resolution.

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%.

Frame detection using gradients fuzzy logic and morphological processing for distant color eye images in an intelligent iris recognition system

The capture of an eye image with the occlusion of spectacles in a non-cooperative environment compromises the accuracy in identifying a person in an iris recognition system. This is due to the obstruction of the iris by the frame which tends to produce an incorrect estimation of the initial center of the iris and the pupil during the iris segmentation process. In addition, it also causes incorrect localization of the upper eyelid during the process of iris segmentation and sometimes, the edges of the frame are wrongly identified as the edges of the upper eyelid. A frame detection method which involves the combination of two gradients, namely the Sobel operator and high pass filter, followed by fuzzy logic and the dilation operation of morphological processing is proposed to identify the frame on the basis of different frame factors in the capture of a distant eye image. In addition, a different color space is applied and only a single channel is used for the process of frame detection. The proposed frame detection method provides the highest frame detection rate compared to the other methods, with a detection rate of more than 80.0%. For the accuracy of the iris localization, upper eyelid localization and iris recognition system, the proposed method gives more than 96.5% accuracy compared to the other methods. The index of decidability showed that the proposed method gives more than 2.35 index compared to the existing methods.

An Iris Localization Algorithm based on Geometric Features of the Circle

An Iris Localization Algorithm based on Geometric Features of the Circle

Visual quality analysis of femtosecond LASIK and iris location guided mechanical SBK for high myopia

Visual quality analysis of femtosecond LASIK and iris location guided mechanical SBK for high myopia

An improved Daugman method for iris recognition

An improved Daugman iris recognition algorithm is provided in this paper, which embodies in two aspects: ➀ Improvement for iris localization and ➁ The improvement for both iris encoding and matching algorithms. In Step 1, the localization and shape of the pupil are roughly determined in iris image, which is used as prior knowledge to quickly locate the inner and outer boundary of iris from rough to fine scale. Eyelids, eyelashes areas and the spot in the pupil are automatically detected and removed to improve the localization accuracy. In Step 2, the possible noise from residual eyelashes is further filtered by selecting a “pure” iris area as a reference and making a validation judgment pixel-wise. Furthermore, the validation flag for each pixel is introduced into the iris encoding and matching computation, as a result, the rejection rate of iris recognition is reduced. Compared with Daugman algorithm, iris recognition test on collected human eye images shows that our proposed algorithm has an obvious improvement both on boosting the speed and reducing the rejection rate.

Efficient iris localisation using a guided filter

Biometric information is widely used in user identification systems. Iris is one of the most reliable and accurate biometric information. In an iris recognition system, the iris localisation is one the most important parts because the performance of an iris recognition system is highly dependent on the accuracy of iris localisation. If unreliable iris regions are used in the iris recognition system, the recognition rate may be degraded. Therefore many researchers have studied the iris localisation methods. Especially, localising an iris region from noisy images is one of the hot topics in the iris recognition researches. In this study, the authors are concentrating on the iris localisation, where an efficient iris localisation method for noisy iris images is proposed. The proposed iris localisation method consists of two steps: pupil boundary localisation and iris boundary localisation. To localise a pupil region, an efficient block-based minimum energy detection method is used, in which specular reflection removal is performed as a preprocessing. Iris boundary is localised using a guided filter, the circular Hough transform and an ellipse fitting method. Experimental results with various test image sets show the effectiveness of the proposed method.

Iris metastasis from prostate carcinoma: A case report and review of the literature

Despite the high incidence of prostate carcinoma, metastases of the uvea are very rare and the iris localization is even more. Only a few cases worldwide have been described so far. We report here the case of a 66-year-old man diagnosed with a metastatic prostate carcinoma. Nine months later, he developed brain and skin metastases. A couple of weeks later, the metastatic lesion appeared on his left iris. He has received whole brain radiation therapy including the iris lesion in the radiation fields. Through this case report and a literature review, we discuss the incidence, the different clinical presentations and the impact on the survival prognosis of this uncommon metastatic site.

An Iris Localization Algorithm based on Morphological Processing

To improve the speed of iris localization, an iris localization algorithm based on the morphological processing is proposed with fast speed. Firstly, pupil area is segmented from eye image by thresholding, to remove eyelash noise and other noises from binaryzation pupil area by morphological open operation. Then, a series of structure element of radius increasing is used to make morphological erode operation on pupil area to localize roughly the inner boundary of the iris. Finally, calculus operator is employed to accurately localize the inner and outer iris boundary. 108 iris images from CASIA (Version 1.0) iris database are used to do iris localization experiments. The localization accurate rate of the proposed algorithm, calculus operator and hough transform is 97.2%, 90.3% and 92.1% respectively. Experiment results have showed that the proposed algorithm has a high performance on speed and precision with strong robustness to the different quality iris images.

Research on Iris Localization Algorithm based on the Active Contour Model

An automatic and robust iris segmentation algorithm will be employed when iris recognition is used to identify human efficiently. Many studies have shown that iris localization is one of the most important parts of the iris recognition system. Most current studies are based on the assumption that iris edge is round, and the gray information of eye image is used for iris segmentation, which requires very high quality of image. Based on the active contour model, an algorithm for iris location was proposed. First, a plurality of pupil edge points was located as the initial contour point set. Then, the real contour evolution of pupil was approximated by the approximation of energy function. Finally, the accurate iris edge was located by daugman’s circular gradient operator. Based on CASIA (V2.0) iris database, experiment results show that the location effect of the proposed algorithm is more superior than that of the classical calculus method and hough transform method.

Study on slot irises for tunable filters using TE 011 mode

Tunable filters using the TE011 mode have slot irises for coupling between cavities. Unless the slot iris is appropriately designed, the coupling value of the iris varies as an operating frequency changes and the filter performance deteriorates as a result. In this reported work, it was found that the frequency-dependent coupling characteristic of the slot iris can be minimised by locating the iris appropriately. Why the coupling of a slot iris changes when the operating frequency is tuned is explained and how to find the optimum location of the slot iris for minimum variation of the coupling value is presented. The proposed theory is verified by full-wave EM simulations and experiments with a Ka-band two-pole filter.