Mahmut Karakaya

Collaborative localization in visual sensor networks

Collaboration in visual sensor networks is essential not only to compensate for the limitations of each sensor node but also to tolerate inaccurate information generated by faulty sensors. This article focuses on the design of a collaborative target localization algorithm that is resilient to sensor faults. We first develop a distributed solution to fault-tolerant target localization based on a so-called certainty map. To tolerate potential sensor faults, a voting mechanism is adopted and a threshold value needs to be specified which is the key to the realization of the distributed solution. Analytical study is conducted to derive the lower and upper bounds for the threshold such that the probability of faulty sensors negatively impacts the localization performance is less than a small value. Second, we focus on the detection and correction of one type of sensor faults, error in camera orientation. We construct a generative image model in each camera based on the detected target location to estimate cameras orientation, detect inaccuracies in camera orientations and correct them before they cascade. Based on results obtained from both simulation and real experiments, we show that the proposed method is effective in localization accuracy as well as fault detection and correction performance.

Limbus impact on off-angle iris degradation

The accuracy of iris recognition depends on the quality of data capture and is negatively affected by several factors such as angle, occlusion, and dilation. Off-angle iris recognition is a new research focus in biometrics that tries to address several issues including corneal refraction, complex 3D iris texture, and blur. In this paper, we present an additional significant challenge that degrades the performance of the off-angle iris recognition systems, called the “limbus effect”. The limbus is the region at the border of the cornea where the cornea joins the sclera. The limbus is a semitransparent tissue that occludes a side portion of the iris plane. The amount of occluded iris texture on the side nearest the camera increases as the image acquisition angle increases. Without considering the role of the limbus effect, it is difficult to design an accurate off-angle iris recognition system. To the best of our knowledge, this is the first work that investigates the limbus effect in detail from a biometrics perspective. Based on results from real images and simulated experiments with real iris texture, the limbus effect increases the hamming distance score between frontal and off-angle iris images ranging from 0.05 to 0.2 depending upon the limbus height.

Gaze estimation for off-angle iris recognition based on the biometric eye model

Iris recognition is among the highest accuracy biometrics. However, its accuracy relies on controlled high quality capture data and is negatively affected by several factors such as angle, occlusion, and dilation. Non-ideal iris recognition is a new research focus in biometrics. In this paper, we present a gaze estimation method designed for use in an off-angle iris recognition framework based on the ORNL biometric eye model. Gaze estimation is an important prerequisite step to correct an off-angle iris images. To achieve the accurate frontal reconstruction of an off-angle iris image, we first need to estimate the eye gaze direction from elliptical features of an iris image. Typically additional information such as well-controlled light sources, head mounted equipment, and multiple cameras are not available. Our approach utilizes only the iris and pupil boundary segmentation allowing it to be applicable to all iris capture hardware. We compare the boundaries with a look-up-table generated by using our biologically inspired biometric eye model and find the closest feature point in the look-up-table to estimate the gaze. Based on the results from real images, the proposed method shows effectiveness in gaze estimation accuracy for our biometric eye model with an average error of approximately 3.5 degrees over a 50 degree range.

Leading-process actomyosin coordinates organelle positioning and adhesion receptor dynamics in radially migrating cerebellar granule neurons

BackgroundDuring brain development, neurons migrate from germinal zones to their final positions to assemble neural circuits. A unique saltatory cadence involving cyclical organelle movement (e.g., centrosome motility) and leading-process actomyosin enrichment prior to nucleokinesis organizes neuronal migration. While functional evidence suggests that leading-process actomyosin is essential for centrosome motility, the role of the actin-enriched leading process in globally organizing organelle transport or traction forces remains unexplored.ResultsWe show that myosin ii motors and F-actin dynamics are required for Golgi apparatus positioning before nucleokinesis in cerebellar granule neurons (CGNs) migrating along glial fibers. Moreover, we show that primary cilia are motile organelles, localized to the leading-process F-actin-rich domain and immobilized by pharmacological inhibition of myosin ii and F-actin dynamics. Finally, leading process adhesion dynamics are dependent on myosin ii and F-actin.ConclusionsWe propose that actomyosin coordinates the overall polarity of migrating CGNs by controlling asymmetric organelle positioning and cell-cell contacts as these cells move along their glial guides.

Off-angle iris correction using a biological model

This work implements an eye model to simulate corneal refraction effects. Using this model, ray tracing is performed to calculate transforms to remove refractive effects in off-angle iris images when reprojected to a frontal view. The correction process is used as a preprocessing step for off-angle iris images for input to a commercial matcher. With this method, a match score distribution mean improvement of 11.65% for 30 degree images, 44.94% for 40 degree images, and 146.1% improvement for 50 degree images is observed versus match score distributions with unmodified images.

An Iris Segmentation Algorithm based on Edge Orientation for Off-angle Iris Recognition

Iris recognition is known as one of the most accurate and reliable biometrics. However, the accuracy of iris recognition systems depends on the quality of data capture and is negatively affected by several factors such as angle, occlusion, and dilation. In this paper, we present a segmentation algorithm for off-angle iris images that uses edge detection, edge elimination, edge classification, and ellipse fitting techniques. In our approach, we first detect all candidate edges in the iris image by using the canny edge detector; this collection contains edges from the iris and pupil boundaries as well as eyelash, eyelids, iris texture etc. Edge orientation is used to eliminate the edges that cannot be part of the iris or pupil. Then, we classify the remaining edge points into two sets as pupil edges and iris edges. Finally, we randomly generate subsets of iris and pupil edge points, fit ellipses for each subset, select ellipses with similar parameters, and average to form the resultant ellipses. Based on the results from real experiments, the proposed method shows effectiveness in segmentation for off-angle iris images.

Limbus impact removal for off-angle iris recognition using eye models

The traditional iris recognition algorithms segment the iris image at the cornea-sclera border as the outer boundary because they consider the visible portion of iris as the entire iris texture. However, limbus, an additional semitransparent eye structure at junction of the cornea and sclera, occludes iris textures at the sides that cannot be seen at the off-angle iris images. In the biometrics community, limbus occlusion is unnoticed due to its limited effect at frontal iris images. However, to ignore the effect of the limbus occlusion in off-angle iris images causes significant performance degradation in iris biometrics. In this paper, we first investigate the limbus impact on off-angle iris recognition. Then, we propose a new approach to remove the effect of limbus occlusion. In our approach, we segmented iris image at its actual outer iris boundary instead of the visible outer iris boundary as in traditional methods and normalize them based on the actual outer iris boundary. The invisible iris region in unwrapped image that is occluded by limbus is eliminated by including it into the mask. Based on the relation between the segmentation parameters of actual and visible iris boundaries, we generate a transfer function and estimate the actual iris boundary from the segmented visible iris boundary depending on the known limbus height and gaze angle. Moreover, based on experiments with the synthetic iris dataset from the biometric eye model, we first show that not only the acquisition angle but also the limbus height negatively affects the performance of the off-angle iris recognition and then we eliminate this negative effect with applying our proposed method.

Pupil Dilation at Synthetic Off-Angle Iris Images

With the development technology, the conventional stand-on iris recognition system is giving its place to a new biometrics research area; a stand- off iris recognition system. Previously encountered non-ideal images, which are captured from a controlled or constrained environment unintentionally, are put in the center of the new system. Thus; some degradation factors that affect the accuracy and performance of iris recognition system, such as pupil dilation, image acquisition angle, corneal refraction, focus, depth of blur, complex 3D iris texture, and limbus impact have come into prominence. In this paper, we investigate how pupil dilation variations affect the Hamming distance changes for different gaze angles. Based on the results from simulated experiments with the real iris textures, it is proven that pupil dilation effect has an influence on the Hamming distance score as the angle of iris images varies between frontal and off-angle.

Invisible data matrix detection with smart phone using geometric correction and Hough transform

Two-dimensional data matrices are used in many different areas that provide quick and automatic data entry to the computer system. Their most common usage is to automatically read labeled products (books, medicines, food, etc.) and recognize them. In Turkey, alcohol beverages and tobacco products are labeled and tracked with the invisible data matrices for public safety and tax purposes. In this application, since data matrixes are printed on a special paper with a pigmented ink, it cannot be seen under daylight. When red LEDs are utilized for illumination and reflected light is filtered, invisible data matrices become visible and decoded by special barcode readers. Owing to their physical dimensions, price and requirement of special training to use; cheap, small sized and easily carried domestic mobile invisible data matrix reader systems are required to be delivered to every inspector in the law enforcement units. In this paper, we first developed an apparatus attached to the smartphone including a red LED light and a high pass filter. Then, we promoted an algorithm to process captured images by smartphones and to decode all information stored in the invisible data matrix images. The proposed algorithm mainly involves four stages. In the first step, data matrix code is processed by Hough transform processing to find “L” shaped pattern. In the second step, borders of the data matrix are found by using the convex hull and corner detection methods. Afterwards, distortion of invisible data matrix corrected by geometric correction technique and the size of every module is fixed in rectangular shape. Finally, the invisible data matrix is scanned line by line in the horizontal axis to decode it. Based on the results obtained from the real test images of invisible data matrix captured with a smartphone, the proposed algorithm indicates high accuracy and low error rate.

Comparison and evaluation of datasets for off-angle iris recognition

In this paper, we investigated the publicly available iris recognition datasets and their data capture procedures in order to determine if they are suitable for the stand-off iris recognition research. Majority of the iris recognition datasets include only frontal iris images. Even if a few datasets include off-angle iris images, the frontal and off-angle iris images are not captured at the same time. The comparison of the frontal and off-angle iris images shows not only differences in the gaze angle but also change in pupil dilation and accommodation as well. In order to isolate the effect of the gaze angle from other challenging issues including dilation and accommodation, the frontal and off-angle iris images are supposed to be captured at the same time by using two different cameras. Therefore, we developed an iris image acquisition platform by using two cameras in this work where one camera captures frontal iris image and the other one captures iris images from off-angle. Based on the comparison of Hamming distance between frontal and off-angle iris images captured with the two-camera- setup and one-camera-setup, we observed that Hamming distance in two-camera-setup is less than one-camera-setup ranging from 0.05 to 0.001. These results show that in order to have accurate results in the off-angle iris recognition research, two-camera-setup is necessary in order to distinguish the challenging issues from each other.