This PDF file contains the front matter associated with SPIE Proceedings Volume 10221, including the Title Page, Copyright information, Table of Contents, Introduction (if any), and Conference Committee listing.

State-space (SS) based modeling for imaging electro-optical (EO) systems representing various states facilitates a method for system estimation. Traditionally linear shift-invariant (LSI) systems are modeled using Fourier analysis (FA). However, models based on FA may not have a clear insight too the instability reasons, whereas SS based models with system poles and zeros have a clear insight to the system stability information. In this paper, we introduce three methods to estimate system parameters for LSI EO imaging systems using SS based modeling. These methods include batch processing version of least squares (LS) estimation, recursive version of LS estimation, and sliding window LS estimation. The accuracy of the developed methods was tested using input and output signals of simulated LSI systems. First, LSI systems with various system parameters (poles and zeros) were simulated, which were then used to generate output signals for a set of random input signals, with each input signal value representing the average of an image. Then, these input and output signals were used to estimate systems employing SS and FA based modeling. Further, the estimated systems were used to generate output signals for a new set of input signals. For any given input signal, output signals generated by both systems were compared for similarities and signal-to-noise ratio (SNR). Results show that SS based models generate output signals that have higher SNR values. In addition, developed methods were tested against the simulated data and results show promise for development of models for estimating more complicated systems (e.g., non-linear system).

Image compression is desired for many image-related applications especially for network-based applications with bandwidth and storage constraints. The face recognition community typical reports concentrate on the maximal compression rate that would not decrease the recognition accuracy. In general, the wavelet-based face recognition methods such as EBGM (elastic bunch graph matching) and FPB (face pattern byte) are of high performance but run slowly due to their high computation demands. The PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis) algorithms run fast but perform poorly in face recognition. In this paper, we propose a novel face recognition method based on standard image compression algorithm, which is termed as compression-based (CPB) face recognition. First, all gallery images are compressed by the selected compression algorithm. Second, a mixed image is formed with the probe and gallery images and then compressed. Third, a composite compression ratio (CCR) is computed with three compression ratios calculated from: probe, gallery and mixed images. Finally, the CCR values are compared and the largest CCR corresponds to the matched face. The time cost of each face matching is about the time of compressing the mixed face image. We tested the proposed CPB method on the “ASUMSS face database” (visible and thermal images) from 105 subjects. The face recognition accuracy with visible images is 94.76% when using JPEG compression. On the same face dataset, the accuracy of FPB algorithm was reported as 91.43%. The JPEG-compressionbased (JPEG-CPB) face recognition is standard and fast, which may be integrated into a real-time imaging device.

Autonomous facial recognition system is widely used in real-life applications, such as homeland border security, law enforcement identification and authentication, and video-based surveillance analysis. Issues like low image quality, non-uniform illumination as well as variations in poses and facial expressions can impair the performance of recognition systems. To address the non-uniform illumination challenge, we present a novel robust autonomous facial recognition system inspired by the human visual system based, so called, logarithmical image visualization technique. In this paper, the proposed method, for the first time, utilizes the logarithmical image visualization technique coupled with the local binary pattern to perform discriminative feature extraction for facial recognition system. The Yale database, the Yale-B database and the ATT database are used for computer simulation accuracy and efficiency testing. The extensive computer simulation demonstrates the method’s efficiency, accuracy, and robustness of illumination invariance for facial recognition.

This study presents a remote sensing application of using time series Landsat satellite images for monitoring the solid waste disposal site (WDS). We propose a method of detecting high-rise buildings landfills, such as municipal dumps and solid waste, according to a radar image (the height of the ground level). For disposal site detection a variety steps of image processing used (calculation image average level of the earth's surface; filtering thresholds spectral brightness coefficients, the size of the connected components, the nature of reducing the level of height with the distance of the maximum level). The spatial geometric features of waste disposal facilities are analytically expressed by linear and radial characteristics from other objects of the earth surface. As a result, the proposed method demonstrates good accuracy in detection the solid waste disposal site on real satellite images.

The automatic detection and quantification of skeletal structures has a variety of different applications for biological research. Accurate segmentation of the pelvis from X-ray images of mice in a high-throughput project such as the Mouse Genomes Project not only saves time and cost but also helps achieving an unbiased quantitative analysis within the phenotyping pipeline. This paper proposes an automatic solution for pelvis segmentation based on structural and orientation properties of the pelvis in X-ray images. The solution consists of three stages including pre-processing image to extract pelvis area, initial pelvis mask preparation and final pelvis segmentation. Experimental results on a set of 100 X-ray images showed consistent performance of the algorithm. The automated solution overcomes the weaknesses of a manual annotation procedure where intra- and inter-observer variations cannot be avoided.

The brain Hippocampus component is known to be responsible for memory and spatial navigation. Its functionality depends on the status of different blood vessels within the Hippocampus and is severely impaired by Alzheimer's disease as a result blockage of increasing number of blood vessels by accumulation of amyloid-beta (Aβ) protein. Accurate counting of blood vessels within the Hippocampus of mice brain, from microscopic images, is an active research area for the understanding of Alzheimer’s disease. Here, we report our work on automatic detection of the Region of Interest, i.e. the region in which blood vessels are located. This area typically falls between the hippocampus edge and the line of neurons within the Hippocampus. This paper proposes a new method to detect and exclude the neuron line to improve the accuracy of blood vessel counting because some neurons on it might lead to false positive cases as they look like blood vessels. Our proposed solution is based on using trainable segmentation approach with morphological operations, taking into account variation in colour, intensity values, and image texture. Experiments on a sufficient number of microscopy images of mouse brain demonstrate the effectiveness of the developed solution in preparation for blood vessels counting.

Precise segmentation of three-dimensional (3D) magnetic resonance imaging (MRI) image can be a very useful computer aided diagnosis (CAD) tool in clinical routines. Accurate automatic extraction a 3D component from images obtained by magnetic resonance imaging (MRI) is a challenging segmentation problem due to the small size objects of interest (e.g., blood vessels, bones) in each 2D MRA slice and complex surrounding anatomical structures. Our objective is to develop a specific segmentation scheme for accurately extracting parts of bones from MRI images. In this paper, we use a segmentation algorithm to extract the parts of bones from Magnetic Resonance Imaging (MRI) data sets based on modified active contour method. As a result, the proposed method demonstrates good accuracy in a comparison between the existing segmentation approaches on real MRI data.

Ovarian masses are categorised into different types of malignant and benign. In order to optimize patient treatment, it is necessary to carry out pre-operational characterisation of the suspect ovarian mass to determine its category. Ultrasound imaging has been widely used in differentiating malignant from benign cases due to its safe and non-intrusive nature, and can be used for determining the number of cysts in the ovary. Presently, the gynaecologist is tasked with manually counting the number of cysts shown on the ultrasound image. This paper proposes, a new approach that automatically segments the ovarian masses and cysts from a static B-mode image. Initially, the method uses a trainable segmentation procedure and a trained neural network classifier to accurately identify the position of the masses and cysts. After that, the borders of the masses can be appraised using watershed transform. The effectiveness of the proposed method has been tested by comparing the number of cysts identified by the method against the manual examination by a gynaecologist. A total of 65 ultrasound images were used for the comparison, and the results showed that the proposed solution is a viable alternative to the manual counting method for accurately determining the number of cysts in a US ovarian image.

The ubiquity of mobile devices offers the opportunity to exploit device-generated signal data for biometric identification, health monitoring, and activity recognition. In particular, mobile devices contain an Inertial Measurement Unit (IMU) that produces acceleration and rotational rate information from the IMU accelerometers and gyros. These signals reflect motion properties of the human carrier. It is well-known that the complexity of bio-dynamical systems gives rise to chaotic dynamics. Knowledge of chaotic properties of these systems has shown utility, for example, in detecting abnormal medical conditions and neurological disorders. Chaotic dynamics has been found, in the lab, in bio-dynamical systems data such as electrocardiogram (heart), electroencephalogram (brain), and gait data. In this paper, we investigate the following question: can we detect chaotic dynamics in human gait as measured by IMU acceleration and gyro data from mobile phones? To detect chaotic dynamics, we perform recurrence analysis on real gyro and accelerometer signal data obtained from mobile devices. We apply the delay coordinate embedding approach from Takens' theorem to reconstruct the phase space trajectory of the multi-dimensional gait dynamical system. We use mutual information properties of the signal to estimate the appropriate delay value, and the false nearest neighbor approach to determine the phase space embedding dimension. We use a correlation dimension-based approach together with estimation of the largest Lyapunov exponent to make the chaotic dynamics detection decision. We investigate the ability to detect chaotic dynamics for the different one-dimensional IMU signals, across human subject and walking modes, and as a function of different phone locations on the human carrier.

A new methodology for 3D change detection which can support effective robot sensing and navigation in a reconstructed indoor environment is presented in this paper. We register the RGB-D images acquired with an untracked camera into a globally consistent and accurate point-cloud model. This paper introduces a robust system that detects camera position for multiple RGB video frames by using both photo-metric error and feature based method. It utilizes the iterative closest point (ICP) algorithm to establish geometric constraints between the point-cloud as they become aligned. For the change detection part, a bag-of-word (DBoW) model is used to match the current frame with the previous key frames based on RGB images with Oriented FAST and Rotated BRIEF (ORB) feature. Then combine the key-frame translation and ICP to align the current point-cloud with reconstructed 3D scene to localize the robot position. Meanwhile, camera position and orientation are used to aid robot navigation. After preprocessing the data, we create an Octomap Model to detect the scene change measurements. The experimental evaluations performed to evaluate the capability of our algorithm show that the robot's location and orientation are accurately determined and provide promising results for change detection indicating all the object changes with very limited false alarm rate.

Stress is a major health concern that not only compromises our quality of life, but also affects our physical health and well-being. Despite its importance, our ability to objectively detect and quantify it in a real-time, non-invasive manner is very limited. This capability would have a wide variety of medical, military, and security applications. We have developed a pipeline of image and signal processing algorithms to make such a system practical, which includes remote cardiac pulse detection based on visible spectrum videos and physiological stress detection based on the variability in the remotely detected cardiac signals. First, to determine a reliable cardiac pulse, principal component analysis (PCA) was applied for noise reduction and independent component analysis (ICA) was applied for source selection. To determine accurate cardiac timing for heart rate variability (HRV) analysis, a blind source separation method based least squares (LS) estimate was used to determine signal peaks that were closely related to R-peaks of the electrocardiogram (ECG) signal. A new metric, differential pulse transit time (dPTT), defined as the difference in arrival time of the remotely acquired cardiac signal at two separate distal locations, was derived. It was demonstrated that the remotely acquired metrics, HRV and dPTT, have potential for remote stress detection. The developed algorithms were tested against human subject data collected under two physiological conditions using the modified Trier Social Stress Test (TSST) and the Affective Stress Response Test (ASRT). This research provides evidence that the variability in remotely-acquired blood wave (BW) signals can be used for stress (high and mild) detection, and as a guide for further development of a real-time remote stress detection system based on remote HRV and dPTT.

Ovarian cysts are a common pathology in women of all age groups. It is estimated that 5-10% of women have a surgical intervention to remove an ovarian cyst in their lifetime. Given this frequency rate, characterization of ovarian masses is essential for optimal management of patients. Patients with benign ovarian masses can be managed conservatively if they are asymptomatic. Mature teratomas are common benign ovarian cysts that occur, in most cases, in premenopausal women. These ovarian cysts can contain different types of human tissue including bone, cartilage, fat, hair, or other tissue. If they are causing no symptoms, they can be harmless and may not require surgery. Subjective assessment by ultrasound examiners has a high diagnostic accuracy when characterising mature teratomas from other types of tumours. The aim of this study is to develop a computerised technique with the potential to characterise mature teratomas and distinguish them from other types of benign ovarian tumours. Local Binary Pattern (LBP) was applied to extract texture features that are specific in distinguishing teratomas. Neural Networks (NN) was then used as a classifier for recognising mature teratomas. A pilot sample set of 130 B-mode static ovarian ultrasound images (41 mature teratomas tumours and 89 other types of benign tumours) was used to test the effectiveness of the proposed technique. Test results show an average accuracy rate of 99.4% with a sensitivity of 100%, specificity of 98.8% and positive predictive value of 98.9%. This study demonstrates that the NN and LBP techniques can accurately classify static 2D B-mode ultrasound images of benign ovarian masses into mature teratomas and other types of benign tumours.

Image quality is a major factor influencing pattern recognition accuracy and help detect image tampering for forensics. We are concerned with investigating topological image texture analysis techniques to assess different type of degradation. We use Local Binary Pattern (LBP) as a texture feature descriptor. For any image construct simplicial complexes for selected groups of uniform LBP bins and calculate persistent homology invariants (e.g. number of connected components). We investigated image quality discriminating characteristics of these simplicial complexes by computing these models for a large dataset of face images that are affected by the presence of shadows as a result of variation in illumination conditions. Our tests demonstrate that for specific uniform LBP patterns, the number of connected component not only distinguish between different levels of shadow effects but also help detect the infected regions as well.

The main problem associated with using symmetric/ asymmetric keys is how to securely store and exchange the keys between the parties over open networks particularly in the open environment such as cloud computing. Public Key Infrastructure (PKI) have been providing a practical solution for session key exchange for loads of web services. The key limitation of PKI solution is not only the need for a trusted third partly (e.g. certificate authority) but also the absent link between data owner and the encryption keys. The latter is arguably more important where accessing data needs to be linked with identify of the owner. Currently available key exchange protocols depend on using trusted couriers or secure channels, which can be subject to man-in-the-middle attack and various other attacks. This paper proposes a new protocol for Key Exchange using Biometric Identity Based Encryption (KE-BIBE) that enables parties to securely exchange cryptographic keys even an adversary is monitoring the communication channel between the parties. The proposed protocol combines biometrics with IBE in order to provide a secure way to access symmetric keys based on the identity of the users in unsecure environment. In the KE-BIOBE protocol, the message is first encrypted by the data owner using a traditional symmetric key before migrating it to a cloud storage. The symmetric key is then encrypted using public biometrics of the users selected by data owner to decrypt the message based on Fuzzy Identity-Based Encryption. Only the selected users will be able to decrypt the message by providing a fresh sample of their biometric data. The paper argues that the proposed solution eliminates the needs for a key distribution centre in traditional cryptography. It will also give data owner the power of finegrained sharing of encrypted data by control who can access their data.

Biometric evidence plays a crucial role in criminal scene analysis. Forensic prints can be extracted from any solid surface such as firearms, doorknobs, carpets and mugs. Prints such as fingerprints, palm prints, footprints and lip-prints can be classified into patent, latent, and three-dimensional plastic prints. Traditionally, law enforcement officers capture these forensic traits using an electronic device or extract them manually, and save the data electronically using special scanners. The reliability and accuracy of the method depends on the ability of the officer or the electronic device to extract and analyze the data. Furthermore, the 2-D acquisition and processing system is laborious and cumbersome. This can lead to the increase in false positive and true negative rates in print matching. In this paper, a method and system to extract forensic prints from any surface, irrespective of its shape, is presented. First, a suitable 3-D camera is used to capture images of the forensic print, and then the 3-D image is processed and unwrapped to obtain 2-D equivalent biometric prints. Computer simulations demonstrate the effectiveness of using 3-D technology for biometric matching of fingerprints, palm prints, and lip-prints. This system can be further extended to other biometric and non-biometric modalities.

Biometrics, particularly palm print authentication has been a stimulating research area due to its abundance of features. Stable features and effective matching are the most crucial steps for an authentication system. In conventional palm print authentication systems, matching is based on flexion creases, friction ridges, and minutiae points. Currently, contactless palm print imaging is an emerging technology. However, they tend to involve fluctuations in the image quality and texture loss due to factors such as varying illumination conditions, occlusions, noise, pose, and ghosting. These variations decrease the performance of the authentication systems. Furthermore, real-time palm print authentication in large databases continue to be a challenging task. In order to effectively solve these problems, features which are invariant to these anomalies are required. This paper proposes a robust palm print matching framework by making a comparative study of different local geometric features such as Difference-of-Gaussian, Hessian, Hessian-Laplace, Harris-Laplace, and Multiscale Harris for feature detection. These detectors are coupled with Scale Invariant Feature Transformation (SIFT) descriptor to describe the identified features. Additionally, a two-stage refinement process is carried out to obtain the best stable matches. Computer simulations demonstrate that the accuracy of the system has increased effectively with an EER of 0.86% when Harris-Laplace detector is used on IITD database.

Although not as popular as fingerprint biometrics, palm prints have garnered interest in scientific community for the rich amount of distinctive information available on the palm. In this paper, a novel method for touchless palm print stitching to increase the effective area is presented. The method is not only rotation invariant but also able to robustly handle many distortions of touchless systems like illumination variations, pose variations etc. The proposed method also can handle partial palmprints, which have a high chance of occurrence in a scene of crime, by stitching them together to produce a much larger-to-full size palmprint for authentication purpose. Experiment results are shown for IIT-D palmprint database, from which pseudo partial palmprints were generated by cropping and randomly rotating them. Furthermore, the quality of stitching algorithm is determined by extensive computer simulations and visual analysis of the stitched image. Experimental results also show that the stitching significantly increases the area of palm image for feature point detection and hence provides a way to increase the accuracy and reliability of detection.

Currently an analog microscope has a wide distribution in the following fields: medicine, animal husbandry, monitoring technological objects, oceanography, agriculture and others. Automatic method is preferred because it will greatly reduce the work involved. Stepper motors are used to move the microscope slide and allow to adjust the focus in semi-automatic or automatic mode view with transfer images of microbiological objects from the eyepiece of the microscope to the computer screen. Scene analysis allows to locate regions with pronounced abnormalities for focusing specialist attention. This paper considers the method for stitching microbial images, obtained of semi-automatic microscope. The method allows to keep the boundaries of objects located in the area of capturing optical systems. Objects searching are based on the analysis of the data located in the area of the camera view. We propose to use a neural network for the boundaries searching. The stitching image boundary is held of the analysis borders of the objects. To auto focus, we use the criterion of the minimum thickness of the line boundaries of object. Analysis produced the object located in the focal axis of the camera. We use method of recovery of objects borders and projective transform for the boundary of objects which are based on shifted relative to the focal axis. Several examples considered in this paper show the effectiveness of the proposed approach on several test images.

In the field of vision-based systems for object detection and classification, thresholding is a key pre-processing step. Thresholding is a well-known technique for image segmentation. Segmentation of medical images, such as Computed Axial Tomography (CAT), Magnetic Resonance Imaging (MRI), X-Ray, Phase Contrast Microscopy, and Histological images, present problems like high variability in terms of the human anatomy and variation in modalities. Recent advances made in computer-aided diagnosis of histological images help facilitate detection and classification of diseases. Since most pathology diagnosis depends on the expertise and ability of the pathologist, there is clearly a need for an automated assessment system. Histological images are stained to a specific color to differentiate each component in the tissue. Segmentation and analysis of such images is problematic, as they present high variability in terms of color and cell clusters. This paper presents an adaptive thresholding technique that aims at segmenting cell structures from Haematoxylin and Eosin stained images. The thresholded result can further be used by pathologists to perform effective diagnosis. The effectiveness of the proposed method is analyzed by visually comparing the results to the state of art thresholding methods such as Otsu, Niblack, Sauvola, Bernsen, and Wolf. Computer simulations demonstrate the efficiency of the proposed method in segmenting critical information.

The goal of this paper is to (a) test the nuclei based Computer Aided Cancer Detection system using Human Visual based system on the histopathology images and (b) Compare the results of the proposed system with the Local Binary Pattern and modified Fibonacci -p pattern systems. The system performance is evaluated using different parameters such as accuracy, specificity, sensitivity, positive predictive value, and negative predictive value on 251 prostate histopathology images. The accuracy of 96.69% was observed for cancer detection using the proposed human visual based system compared to 87.42% and 94.70% observed for Local Binary patterns and the modified Fibonacci p patterns.