Successful image registration is an important step for object recognition, target detection, remote sensing, multimodal content fusion, scene blending, and disaster assessment and management. The geometric and photometric variations between images adversely affect the ability for an algorithm to estimate the transformation parameters that relate the two images. Local deformations, lighting conditions, object obstructions, and perspective differences all contribute to the challenges faced by traditional registration techniques. In this paper, a novel multistage registration approach is proposed that is resilient to view point differences, image content variations, and lighting conditions. Robust registration is realized through the utilization of a novel region descriptor which couples with the spatial and texture characteristics of invariant feature points. The proposed region descriptor is exploited in a multistage approach. A multistage process allows the utilization of the graph-based descriptor in many scenarios thus allowing the algorithm to be applied to a broader set of images. Each successive stage of the registration technique is evaluated through an effective similarity metric which determines subsequent action. The registration of aerial and street view images from pre- and post-disaster provide strong evidence that the proposed method estimates more accurate global transformation parameters than traditional feature-based methods. Experimental results show the robustness and accuracy of the proposed multistage image registration methodology.

A large portion of system breaches are caused by authentication failure, either during the login process or in the post-authentication session; these failures are themselves related to the limitations associated with existing authentication methods. Current authentication methods, whether proxy based or biometrics based, are not user-centric and/or endanger users’ (biometric) security and privacy. In this paper, we propose a biometrics based user-centric authentication approach. This method involves introducing a reference subject (RS), securely fusing the user’s biometrics with the RS, generating a BioCapsule (BC) from the fused biometrics, and employing BCs for authentication. Such an approach is user friendly, identity bearing yet privacy-preserving, resilient, and revocable once a BC is compromised. It also supports “one-click sign-on” across systems by fusing the user’s biometrics with a distinct RS on each system. Moreover, active and non-intrusive authentication can be automatically performed during post-authentication sessions. We formally prove that the secure fusion based approach is secure against various attacks. Extensive experiments and detailed comparison with existing approaches show that its performance (i.e., authentication accuracy) is comparable to existing typical biometric approaches and the new BC based approach also possesses many desirable features such as diversity and revocability.

Investigation of pedestrian step frequency is essential for analyzing walking gaits and pedestrian behaviors. However, most research about step frequency is performed in labs or manually controlled experimental environment, which greatly limits the utilization of the results to analyze and/or predict real pedestrian behaviors. This study investigates the step frequencies of pedestrian in naturalistic driving environment. The mean step frequency values and distribution are studied in all cases and separately for road crossing cases only. Furthermore, comparisons of pedestrian step frequencies are made considering three different impact factors. The results have shown that in real world, people tend to use higher step frequencies when crossing the road, especially when the vehicle is moving towards the pedestrian or when the pedestrians are crossing without right-of-way.

Pedestrian detection is a challenging task due to the high variance of pedestrians and fast changing background, especially for a single in-car camera system. Traditional HOG+SVM methods have two challenges: (1) false positives and (2) processing speed. In this paper, a new pedestrian detection method using multimodal HOG for pedestrian feature extraction and kernel based Extreme Learning Machine (ELM) for classification is presented. The experimental results using our naturalistic driving dataset show that the proposed method outperforms the traditional HOG+SVM method in both recognition accuracy and processing speed.

Successful content-based image registration relies on the accurate identification of corresponding features across images. Geometric and photometric transformations between images may hinder an algorithm's ability to precisely match features. In this work, we propose a novel region descriptor detection and matching algorithm for use with image registration. The detection process utilizes invariant feature points, as well as their spatial relationships and textural characteristics to create a connected graph whose structure represents an invariant region descriptor. With such a framework, feature matching can be accomplished by graph matching with a defined similarity metric. Subsequent image registration steps are outlined that employ the invariant region descriptors. The results provide strong evidence of the region descriptor's effectiveness in applications involving image registration. Several scenarios are presented including the registration of general objects, aerial photography, as well as scenes before and after a disaster.

User authentication is critical in preventing system breaches. Existing authentication approaches usually do a onetime log-in authentication, but rarely incorporate mechanisms to differentiate the initial log-in user and the user who is currently taking control of the system, which may cause post-authentication breaches. In this paper, we study user authentication for both login session and post-authentication session and propose a biometrics based active authentication approach. Moreover, concerning the usage of biometrics, the system is biometrics-secure and privacy-preserving. Security analysis and experimental results prove that the proposed approach is secure, resilient to various attacks and effective.

Multimodal eye recognition can improve the biometric systems recognition accuracy by combining iris and sclera recognition. However, poor quality images can significantly affect the system performance. In this paper, we proposed a quality fusion based multimodal eye recognition. Our quality measure evaluated the entire eye image quality, iris area quality, and sclera area quality. The experimental results show that our overall iris and sclera quality scores are highly correlated to recognition accuracy, and our quality fusion based eye recognition can improve and predict the performance of eye recognition systems.

Linear spectral mixture analysis (LSMA) has been widely used in remote sensing community for spectral unmixing. This letter develops a promising technique, called kernel-based LSMA (KLSMA), which uses nonlinear kernels to resolve the issue of nonlinear separability arising in unmixing and further extends several commonly used LSMA techniques to their kernel-based counterparts. Interestingly, according to experiments conducted for real hyperspectral and multispectral images, KLSMA is more effective than LSMA when data samples are heavily mixed.

The blood vessel structure of the sclera is unique to each person, and it can be remotely obtained nonintrusively in the visible wavelengths. Therefore, it is well suited for human identification (ID). In this paper, we propose a new concept for human ID: sclera recognition. This is a challenging research problem because images of sclera vessel patterns are often defocused and/or saturated and, most importantly, the vessel structure in the sclera is multilayered and has complex nonlinear deformations. This paper has several contributions. First, we proposed the new approach for human ID: sclera recognition. Second, we developed a new method for sclera segmentation which works for both color and grayscale images. Third, we designed a Gabor wavelet-based sclera pattern enhancement method to emphasize and binarize the sclera vessel patterns. Finally, we proposed a line-descriptor-based feature extraction, registration, and matching method that is illumination, scale, orientation, and deformation invariant and can mitigate the multilayered deformation effects and tolerate segmentation error. The experimental results show that sclera recognition is a promising new biometrics for positive human ID.

Authentication is a fundamental issue to any trust-oriented computing system and also a critical part in many security protocols. Performing authentication is notoriously difficult. Biometrics has been widely used and adopted as a promising authentication method due to its advantages over some existing methods, particularly, its resistance to losses incurred by theft of passwords and smart cards. However, biometrics introduces its own challenges, such as being irreplaceable once compromised. Moreover, the use of biometrics introduces privacy concern. In this paper, we propose a simple yet effective biometrics-based authentication solution. The proposed approach introduces new constructs - Reference Subject and Biometric Capsule, and stores the ``difference'' (called Biometric Capsule) between the user and the Reference Subject for authentication without revealing a user's original biometric information. This approach supports replaceability and protect users' privacy. Moreover, the proposed approach creates more advantages: (a) being user-friendly without any additional burden on users and possessing one-for-all power; (b) being generic enough to be applied to various biometrics (e.g., fingerprint, face, iris) or combinations of them; and (c) being adaptive in terms of security and privacy to fit different authentication models, application requirements, available resources, and trusted or non-fully-trusted environments. The experimental results on iris validate its performance and prove it a practical mechanism.

In this paper, we proposed a robust multi-stage feature extraction and matching approach for non-cooperative iris recognition. To speed up the process, we used the SURF concept that treats the image as discrete and digital matrices. Unlike SURF method, we applied Gabor wavelets for feature extraction. More importantly, we designed a multi-scale feature point extraction method and a multi-stage matching scheme to improve the recognition accuracy and speed. The experimental results show that the proposed method can not only improve the process speed but also achieve better recognition accuracy.

Two of the most challenging issues in the unsupervised linear spectral mixture analysis (ULSMA) are: 1) determining the number of signatures to form a linear mixing model; and 2) finding the signatures used to unmix data. These two issues do not occur in supervised LSMA since the target signatures are assumed to be known a priori. With recent advances in hyperspectral sensor technology, many unknown and subtle signal sources can now be uncovered and revealed and such signal sources generally cannot be identified by prior knowledge. Even when they can, the obtained knowledge may not be reliable, accurate, or complete. As a consequence, the resulting unmixed results may be misleading. This paper addresses these issues by introducing a new concept of inter-band spectral information (IBSI), which can be used to categorize signatures into background and target classes in terms of their sample spectral statistics. It then develops a component analysis (CA)-based ULSMA where two classes of signatures can be extracted directly from the data by two different CA-based transforms without requiring prior knowledge. In order to substantiate the utility of the proposed approach, synthetic images are used for experiments and real images are further used for validation.

In this paper, we propose a video-based noncooperative iris image segmentation scheme that incorporates a quality filter to quickly eliminate images without an eye, employs a coarse-to-fine segmentation scheme to improve the overall efficiency, uses a direct least squares fitting of ellipses method to model the deformed pupil and limbic boundaries, and develops a window gradient-based method to remove noise in the iris region. A remote iris acquisition system is set up to collect noncooperative iris video images. An objective method is used to quantitatively evaluate the accuracy of the segmentation results. The experimental results demonstrate the effectiveness of this method. The proposed method would make noncooperative iris recognition or iris surveillance possible.

Sclera recognition can be used for human identification. However, if the sclera images cannot be properly segmented by the system or the images of sclera patterns are defocused and/or saturated, it can significantly affect the accuracy of sclera recognition. In this paper, we propose a comprehensive sclera image quality measure which can quickly detect if the image has a valid eye1, assess the image quality, evaluate the segmentation accuracy, and measure if the image has sufficient feature information for recognition. In addition, it used Dempster Shafer Theory to fuse the quality score, segmentation score, and feature score together to generate the overall combination score. It is empirically verified using the UBIRIS database that the proposed quality measure is highly correlated with the performance of sclera recognition.

For positive human identification, the iris has been shown to be a stable and reliable biometric. However, it is permanently bounded with an individual and its pattern is very hard to reissue when “stolen”. Thus, cancelable biometrics is a desirable solution to ensure the revocability and alternative of an iris template when compromised. The traditional cancelable biometrics approaches often compromise the recognition accuracy. In this paper, we propose a new cancelable iris recognition method using Gabor Descriptor, which can not only achieve “cancelability”, but also increase the recognition accuracy.

Numerous monitoring applications such as traffic control systems, border patrol monitoring, and person locater services generate a large number of multimedia data streams that need to be analyzed and processed using image processing and data stream management techniques in order to detect significant events of interest or abnormal conditions. Such multimedia monitoring systems usually have high-bandwidth characteristics, stricter real-time deadlines, and high accuracy requirements. In an attempt to meet all of these requirements, we have designed Symbiote - a distributed Reconfigurable Logic Assisted multimedia Data Stream Management System (RLADSMS) at Indiana University Purdue University, Indianapolis (IUPUI) that provides hardware accelerated data stream processing using Field Programmable Gate Arrays (FPGAs).

In the above titled paper (ibid., vol. 3, no. 3, pp. 572-577, Sep. 08), equation (2-11) on page 574 contains a typo. The correct equation is presented here.

Poor quality images can significantly affect the accuracy of iris-recognition systems because they do not have enough feature information. However, existing quality measures have focused on parameters or factors other than feature information. The quality of feature available for measure is a combination of the distinctiveness of the iris region and the amount of iris region available. Some irises may only have a small area of changing patterns. Due to this, the proposed approach automatically selects the portions of the iris with the most distinguishable changing patterns to measure the feature information. The combination of occlusion and dilation determines the amount of iris region available and is considered in the proposed quality measure. The quality score is the fused result of the feature information score, the occlusion score, and the dilation score. The relationship between the quality score and recognition accuracy is evaluated using 2-D Gabor and 1-D Log-Gabor wavelet approaches and validated using a diverse data set. In addition, the proposed method is compared with the convolution matrix, spectrum energy, and Mexican hat wavelet methods. These three methods represent a variety of approaches for iris-quality measure. The experimental results show that the proposed quality score is highly correlated with the recognition accuracy and is capable of predicting the recognition results.

It is evidenced that Ca2+plays a critical role in cell activities. Understanding and analysis of a Ca2+sparks event can provide critical information in cell communications. It is known that a Ca2+spark spatial spread in a local area can be modeled by a Gaussian distribution. There are some available methods in Ca2+spark detection, but little research has been done to quantitatively analyze and classify the Ca2+sparks into single or multiple release events. In this paper, a new method based on Gaussian-Mexican Hat Wavelet is proposed to automatically classify Ca2+sparks into single release events or multiple releases events. Then Ca2+sparks from single release events are further categorized into different energy levels. The experiment results using mouse skeletal muscle fiber cells show this method is promising.

In this paper, feature information based quality measure is proposed to measure the quality of an iris image. The proposed method automatically selects regions of the iris with most changing patterns to assess the quality based on the feature information. The Log-Gabor filter is used as a bandpass filter to extract feature information of the selected iris regions. A blurry image will be more homogenous than a clear image. In other words, the features in a blurry image will be closer to uniform distribution. Therefore, information distance between the selected feature distribution and uniform distribution can be used to generate the feature information score. This score is then fused with occlusion and pupil dilation measures to obtain a quality score. We analyzed the CASIA database ver. 2.0 images using this proposed method. The quality scores are consistent with our observations. Moreover, we evaluated the relationship between the quality score and the recognition accuracy. The experimental results show that the proposed quality score is highly correlated with the recognition accuracy. In addition, we compared our method with Daugman's quality measure; the experimental results show that this proposed quality measure can effectively measure a variety of iris images including images with a small region of changing patterns, and images heavily occluded and/or blurred. The experimental results also show that this proposed method is insensitive to residual eyelids and eyelashes from segmentation errors.

This paper proposes a fully automatic approach for Ca2+spark events detection in confocal image system. This system automatically detects the region of interest and separates it from the background, automatically finds the optimal thresholds for Ca2+sparks detection, and takes advantage of the correlation between two consecutive frames in detecting the Ca2+sparks. The experiment results show that the proposed method is very promising. Compared to the conventional system (proposed by Cheng et. al and later improved by Chun et. al), the preliminary experimental results show that the proposed system can achieve higher accuracy rate without compromising false alarm rate.

Iris recognition has been shown to be very accurate for human identification. We investigate the performance of the use of a partial iris for recognition. A partial iris identification system based on a one-dimensional approach to iris identification is developed. Experiment results show that a more distinguishable and individually unique signal is found in the inner rings of the iris. The results also show that it is possible to use only a portion of the iris for human identification.

Biometric systems verify a persons identity based on unique physical attributes. Biometric technologies are becoming the foundation of an extensive array of highly secure identification and personal verification solutions. It is a broad subject, which integrates image processing, digital signal processing, statistics, mathematics, computing, psychology and legislation. To enable the average undergraduate to understand and internalize the biometric theories and technologies, we have developed a biometric signal processing laboratory at the US Naval Academy. The paper describes the model of the lab, introduces the key biometric equipment, and overviews our lab activities.

Thresholding color video images is challenging because of the low spatial resolution and the complex backgrounds. This paper investigates the issue of thresholding these images by reducing the number of colors in order to improve automated text detection and recognition. An unsupervised thresholding approach is presented which reduces the background complexity while retaining the important text character pixels. The experiments show that our proposed thresholding approach performs significantly better than simple image histogram-based methods which generally do not produce satisfactory results.

Thresholding color video images is challenging because of the low spatial resolution and the complex backgrounds. This paper investigates the issue of thresholding these images by reducing the number of colors in order to improve automated text detection and recognition. An unsupervised thresholding approach is presented which reduces the background complexity while retaining the important text character pixels. The experiments show that our proposed thresholding approach performs significantly better than simple image histogram-based methods, which generally do not produce satisfactory results.