Pattern recognition using invariants defined from higher order spectra : 2-D image inputs

A new algorithm for extracting features from images for object recognition is described. The algorithm uses higher order spectra to provide desirable invariance properties, to provide noise immunity, and to incorporate nonlinearity into the feature extraction procedure thereby allowing the use of simple classifiers. An image can be reduced to a set of 1D functions via the Radon transform, or alternatively, the Fourier transform of each 1D projection can be obtained from a radial slice of the 2D Fourier transform of the image according to the Fourier slice theorem. A triple product of Fourier coefficients, referred to as the deterministic bispectrum, is computed for each 1D function and is integrated along radial lines in bifrequency space. Phases of the integrated bispectra are shown to be translation- and scale-invariant. Rotation invariance is achieved by a regrouping of these invariants at a constant radius followed by a second stage of invariant extraction. Rotation invariance is thus converted to translation invariance in the second step. Results using synthetic and actual images show that isolated, compact clusters are formed in feature space. These clusters are linearly separable, indicating that the nonlinearity required in the mapping from the input space to the classification space is incorporated well into the feature extraction stage. The use of higher order spectra results in good noise immunity, as verified with synthetic and real images. Classification of images using the higher order spectra-based algorithm compares favorably to classification using the method of moment invariants

Asphalt concrete surfaces macrotexture determination from still images

Road surface macrotexture is identified as one of the factors contributing to the surface's skid resistance. Existing methods of quantifying the surface macrotexture, such as the sand patch test and the laser profilometer test, are either expensive or intrusive, requiring traffic control. High-resolution cameras have made it possible to acquire good quality images from roads for the automated analysis of texture depth. In this paper, a granulometric method based on image processing is proposed to estimate road surface texture coarseness distribution from their edge profiles. More than 1300 images were acquired from two different sites, extending to a total of 2.96 km. The images were acquired using camera orientations of 60 and 90 degrees. The road surface is modeled as a texture of particles, and the size distribution of these particles is obtained from chord lengths across edge boundaries. The mean size from each distribution is compared with the sensor measured texture depth obtained using a laser profilometer. By tuning the edge detector parameters, a coefficient of determination of up to R2 = 0.94 between the proposed method and the laser profilometer method was obtained. The high correlation is also confirmed by robust calibration parameters that enable the method to be used for unseen data after the method has been calibrated over road surface data with similar surface characteristics and under similar imaging conditions.

Accurately simulating the production of radiotherapy portal images using non-zero beam angles

In this study, the delivery and portal imaging of one square-field and one conformal radiotherapy treatment was simulated using the Monte Carlo codes BEAMnrc and DOSXYZnrc. The treatment fields were delivered to a humanoid phantom from different angles by a 6 MV photon beam linear accelerator, with an amorphous-silicon electronic portal imaging device (a-Si EPID) used to provide images of the phantom generated by each field. The virtual phantom preparation code CTCombine was used to combine a computed-tomography-derived model of the irradiated phantom with a simple, rectilinear model of the a-Si EPID, at each beam angle used in the treatment. Comparison of the resulting experimental and simulated a-Si EPID images showed good agreement, within \[gamma](3%, 3 mm), indicating that this method may be useful in providing accurate Monte Carlo predictions of clinical a-Si EPID images, for use in the verification of complex radiotherapy treatments.

Least-squares congealing for large numbers of images

In this paper we pursue the task of aligning an ensemble of images in an unsupervised manner. This task has been commonly referred to as “congealing” in literature. A form of congealing, using a least-squares criteria, has been recently demonstrated to have desirable properties over conventional congealing. Least-squares congealing can be viewed as an extension of the Lucas & Kanade (LK)image alignment algorithm. It is well understood that the alignment performance for the LK algorithm, when aligning a single image with another, is theoretically and empirically equivalent for additive and compositional warps. In this paper we: (i) demonstrate that this equivalence does not hold for the extended case of congealing, (ii) characterize the inherent drawbacks associated with least-squares congealing when dealing with large numbers of images, and (iii) propose a novel method for circumventing these limitations through the application of an inverse-compositional strategy that maintains the attractive properties of the original method while being able to handle very large numbers of images.

Gait energy volumes and frontal gait recognition using depth images

Gait energy images (GEIs) and its variants form the basis of many recent appearance-based gait recognition systems. The GEI combines good recognition performance with a simple implementation, though it suffers problems inherent to appearance-based approaches, such as being highly view dependent. In this paper, we extend the concept of the GEI to 3D, to create what we call the gait energy volume, or GEV. A basic GEV implementation is tested on the CMU MoBo database, showing improvements over both the GEI baseline and a fused multi-view GEI approach. We also demonstrate the efficacy of this approach on partial volume reconstructions created from frontal depth images, which can be more practically acquired, for example, in biometric portals implemented with stereo cameras, or other depth acquisition systems. Experiments on frontal depth images are evaluated on an in-house developed database captured using the Microsoft Kinect, and demonstrate the validity of the proposed approach.

Vibrational spectroscopy of synthetic stercorite H(NH4)Na(PO4)•4H2O – a comparison with the natural cave mineral

In order to mimic the chemical reactions in cave systems, the analogue of the mineral stercorite H(NH4)Na(PO4)•4H2O has been synthesised. X-ray diffraction of the stercorite analogue matches the stercorite reference pattern. A comparison is made with the vibrational spectra of synthetic stercorite analogue and the natural Cave mineral. The mineral in nature is formed by the reaction of bat guano chemicals on calcite substrates. A single Raman band at 920 cm-1 (Cave) and 922 cm-1 (synthesised) defines the presence of hydrogen phosphate in the mineral. In the synthetic stercorite analogue, additional bands are observed and are attributed to the dihydrogen and phosphate anions. The vibrational spectra of synthetic stercorite only partly match that of the natural stercorite. It is suggested that natural stercorite is more pure than that of synthesised stercorite. Antisymmetric stretching bands are observed in the infrared spectrum at 1052, 1097, 1135 and 1173 cm-1. Raman spectroscopy shows the stercorite mineral is based upon the hydrogen phosphate anion and not the phosphate anion. Raman and infrared bands are found and assigned to PO43-, H2O, OH and NH stretching vibrations. Raman spectroscopy shows the synthetic analogue is similar to the natural mineral. A mechanism for the formation of stercorite is provided.

Towards an automatic system for road lane marking extraction in large-scale aerial images acquired over rural areas by hierarchical image analysis and Gabor filter

An automatic approach to road lane marking extraction from high-resolution aerial images is proposed, which can automatically detect the road surfaces in rural areas based on hierarchical image analysis. The procedure is facilitated by the road centrelines obtained from low-resolution images. The lane markings are further extracted on the generated road surfaces with 2D Gabor filters. The proposed method is applied on the aerial images of the Bruce Highway around Gympie, Queensland. Evaluation of the generated road surfaces and lane markings using four representative test fields has validated the proposed method.

Graph rigidity for near-coplanar structure from motion

Recent algorithms for monocular motion capture (MoCap) estimate weak-perspective camera matrices between images using a small subset of approximately-rigid points on the human body (i.e. the torso and hip). A problem with this approach, however, is that these points are often close to coplanar, causing canonical linear factorisation algorithms for rigid structure from motion (SFM) to become extremely sensitive to noise. In this paper, we propose an alternative solution to weak-perspective SFM based on a convex relaxation of graph rigidity. We demonstrate the success of our algorithm on both synthetic and real world data, allowing for much improved solutions to marker less MoCap problems on human bodies. Finally, we propose an approach to solve the two-fold ambiguity over bone direction using a k-nearest neighbour kernel density estimator.

Computational approaches to the visual validation of 3D virtual environments

Virtual environments can provide, through digital games and online social interfaces, extremely exciting forms of interactive entertainment. Because of their capability in displaying and manipulating information in natural and intuitive ways, such environments have found extensive applications in decision support, education and training in the health and science domains amongst others. Currently, the burden of validating both the interactive functionality and visual consistency of a virtual environment content is entirely carried out by developers and play-testers. While considerable research has been conducted in assisting the design of virtual world content and mechanics, to date, only limited contributions have been made regarding the automatic testing of the underpinning graphics software and hardware. The aim of this thesis is to determine whether the correctness of the images generated by a virtual environment can be quantitatively defined, and automatically measured, in order to facilitate the validation of the content. In an attempt to provide an environment-independent definition of visual consistency, a number of classification approaches were developed. First, a novel model-based object description was proposed in order to enable reasoning about the color and geometry change of virtual entities during a play-session. From such an analysis, two view-based connectionist approaches were developed to map from geometry and color spaces to a single, environment-independent, geometric transformation space; we used such a mapping to predict the correct visualization of the scene. Finally, an appearance-based aliasing detector was developed to show how incorrectness too, can be quantified for debugging purposes. Since computer games heavily rely on the use of highly complex and interactive virtual worlds, they provide an excellent test bed against which to develop, calibrate and validate our techniques. Experiments were conducted on a game engine and other virtual worlds prototypes to determine the applicability and effectiveness of our algorithms. The results show that quantifying visual correctness in virtual scenes is a feasible enterprise, and that effective automatic bug detection can be performed through the techniques we have developed. We expect these techniques to find application in large 3D games and virtual world studios that require a scalable solution to testing their virtual world software and digital content.

Vibrational spectroscopy of synthetic archerite (K,NH4)H2PO4 : and in comparison with the natural cave mineral

In order to mimic the formation of archerite in cave minerals, the mineral analogue has been synthesised. The cave mineral is formed by the reaction of the chemicals in bat guano with calcite substrates. X-ray diffraction proves that the synthesised archerite analogue was pure. The vibrational spectra of the synthesised mineral are compared with that of the natural cave mineral. Raman and infrared bands are assigned to H2PO4-, OH and NH stretching and bending vibrations. The Raman band at 917 cm-1 is assigned to the HOP stretching vibration of the H2PO4- units. Bands in the 1200 to 1800 cm-1 region are associated with NH4+ bending modes. Vibrational spectroscopy enables the molecular structure of archerite to be analysed.

Raman spectroscopy of synthetic CaHPO4•2H2O– and in comparison with the cave mineral brushite

The mineral brushite has been synthesised by mixing calcium ions and hydrogen phosphate anions to mimic the reactions in a Cave. The vibrational spectra of the synthesised brushite were compared with that of the natural Cave mineral. Bands attributable to the PO43- and HPO42- anions are observed. Brushite, both synthetic and natural, is characterised by an intense sharp band at 985 cm-1 with a shoulder at 1000 cm-1. Characteristic bending modes are observed in the 300 to 600 cm-1 region. The spectra of the synthesised brushite matches very well the spectrum of brushite from the Moorba Cave, Western Australia.

Volume estimation from multiplanar 2D ultrasound images using a remote electromagnetic position and orientation sensor

A system is described for calculating volume from a sequence of multiplanar 2D ultrasound images. Ultrasound images are captured using a video digitising card (Hauppauge Win/TV card) installed in a personal computer, and regions of interest transformed into 3D space using position and orientation data obtained from an electromagnetic device (Polbemus, Fastrak). The accuracy of the system was assessed by scanning 10 water filled balloons (13-141 ml), 10 kidneys (147  200 ml) and 16 fetal livers (8  37 ml) in water using an Acuson 128XP/10 (5 MHz curvilinear probe). Volume was calculated using the ellipsoid, planimetry, tetrahedral and ray tracing methods and compared with the actual volume measured by weighing (balloons) and water displacement (kidneys and livers). The mean percentage error for the ray tracing method was 0.9 ± 2.4%, 2.7 ± 2.3%, 6.6 ± 5.4% for balloons, kidneys and livers, respectively. So far the system has been used clinically to scan fetal livers and lungs, neonate brain ventricles and adult prostate glands.

Fusion of morphological images for airborne target detection

Several track-before-detection approaches for image based aircraft detection have recently been examined in an important automated aircraft collision detection application. A particularly popular approach is a two stage processing paradigm which involves: a morphological spatial filter stage (which aims to emphasize the visual characteristics of targets) followed by a temporal or track filter stage (which aims to emphasize the temporal characteristics of targets). In this paper, we proposed new spot detection techniques for this two stage processing paradigm that fuse together raw and morphological images or fuse together various different morphological images (we call these approaches morphological reinforcement). On the basis of flight test data, the proposed morphological reinforcement operations are shown to offer superior signal to-noise characteristics when compared to standard spatial filter options (such as the close-minus-open and adaptive contour morphological operations). However, system operation characterised curves, which examine detection verses false alarm characteristics after both processing stages, illustrate that system performance is very data dependent.

PARP inhibition induces BAX/BAK-independent synthetic lethality of BRCA1-deficient non-small cell lung cancer

Evasion of apoptosis contributes to both tumourigenesis and drug resistance in non-small cell lung carcinoma (NSCLC). The pro-apoptotic BCL-2 family proteins BAX and BAK are critical regulators of mitochondrial apoptosis. New strategies for targeting NSCLC in a mitochondria-independent manner should bypass this common mechanism of apoptosis block. BRCA1 mutation frequency in lung cancer is low; however, decreased BRCA1 mRNA and protein expression levels have been reported in a significant proportion of lung adenocarcinomas. BRCA1 mutation/deficiency confers a defect in homologous recombination DNA repair that has been exploited by synthetic lethality through inhibition of PARP (PARPi) in breast and ovarian cells; however, it is not known whether this same synthetic lethal mechanism exists in NSCLC cells. Additionally, it is unknown whether the mitochondrial apoptotic pathway is required for BRCA1/PARPi-mediated synthetic lethality. Here we demonstrate that silencing of BRCA1 expression by RNA interference sensitizes NSCLC cells to PARP inhibition. Importantly, this sensitivity was not attenuated in cells harbouring mitochondrial apoptosis block induced by co-depletion of BAX and BAK. Furthermore, we demonstrate that BRCA1 inhibition cannot override platinum resistance, which is often mediated by loss of mitochondrial apoptosis signalling, but can still sensitize to PARP inhibition. Finally we demonstrate the existence of a BRCA1-deficient subgroup (11–19%) of NSCLC patients by analysing BRCA1 protein levels using immunohistochemistry in two independent primary NSCLC cohorts. Taken together, the existence of BRCA1-immunodeficient NSCLC suggests that this molecular subgroup could be effectively targeted by PARP inhibitors in the clinic and that PARP inhibitors could be used for the treatment of BRCA1-immunodeficient, platinum-resistant tumours.