Learning Three-Dimensional Shape Models for Sketch Recognition

Artifacts made by humans, such as items of furniture and houses, exhibit an enormous amount of variability in shape. In this paper, we concentrate on models of the shapes of objects that are made up of fixed collections of sub-parts whose dimensions and spatial arrangement exhibit variation. Our goals are: to learn these models from data and to use them for recognition. Our emphasis is on learning and recognition from three-dimensional data, to test the basic shape-modeling methodology. In this paper we also demonstrate how to use models learned in three dimensions for recognition of two-dimensional sketches of objects.

A new optimised De Bruijn coding strategy for structured light patterns

Coded structured light is an optical technique based on active stereovision that obtains the shape of objects. One shot techniques are based on projecting a unique light pattern with an LCD projector so that grabbing an image with a camera, a large number of correspondences can be obtained. Then, a 3D reconstruction of the illuminated object can be recovered by means of triangulation. The most used strategy to encode one-shot patterns is based on De Bruijn sequences. In This work a new way to design patterns using this type of sequences is presented. The new coding strategy minimises the number of required colours and maximises both the resolution and the accuracy

Image classification for a large number of object categories

L'increment de bases de dades que cada vegada contenen imatges més difícils i amb un nombre més elevat de categories, està forçant el desenvolupament de tècniques de representació d'imatges que siguin discriminatives quan es vol treballar amb múltiples classes i d'algorismes que siguin eficients en l'aprenentatge i classificació. Aquesta tesi explora el problema de classificar les imatges segons l'objecte que contenen quan es disposa d'un gran nombre de categories. Primerament s'investiga com un sistema híbrid format per un model generatiu i un model discriminatiu pot beneficiar la tasca de classificació d'imatges on el nivell d'anotació humà sigui mínim. Per aquesta tasca introduïm un nou vocabulari utilitzant una representació densa de descriptors color-SIFT, i desprès s'investiga com els diferents paràmetres afecten la classificació final. Tot seguit es proposa un mètode par tal d'incorporar informació espacial amb el sistema híbrid, mostrant que la informació de context es de gran ajuda per la classificació d'imatges. Desprès introduïm un nou descriptor de forma que representa la imatge segons la seva forma local i la seva forma espacial, tot junt amb un kernel que incorpora aquesta informació espacial en forma piramidal. La forma es representada per un vector compacte obtenint un descriptor molt adequat per ésser utilitzat amb algorismes d'aprenentatge amb kernels. Els experiments realitzats postren que aquesta informació de forma te uns resultats semblants (i a vegades millors) als descriptors basats en aparença. També s'investiga com diferents característiques es poden combinar per ésser utilitzades en la classificació d'imatges i es mostra com el descriptor de forma proposat juntament amb un descriptor d'aparença millora substancialment la classificació. Finalment es descriu un algoritme que detecta les regions d'interès automàticament durant l'entrenament i la classificació. Això proporciona un mètode per inhibir el fons de la imatge i afegeix invariança a la posició dels objectes dins les imatges. S'ensenya que la forma i l'aparença sobre aquesta regió d'interès i utilitzant els classificadors random forests millora la classificació i el temps computacional. Es comparen els postres resultats amb resultats de la literatura utilitzant les mateixes bases de dades que els autors Aixa com els mateixos protocols d'aprenentatge i classificació. Es veu com totes les innovacions introduïdes incrementen la classificació final de les imatges.

Frequency responses of hearing aids and their effects on the speech perception of eight hard-of-hearing subjects

This dissertation examines the relationship between frequency response and word-discrimination performance of hearing-impaired persons. Three questions are addressed: does the restoration of the normal field-to-eardrum transfer function improve word discrimination; is the restoration of the normal shape of the audibility curve (uniform hearing level at all frequencies) beneficial to hearing-impaired listeners; and can speech discrimination be improved by an extension of the present narrow-band response in hearing aids.

Biologically motivated model for object detection and identification in real-world scenes

The classical computer vision methods can only weakly emulate some of the multi-level parallelisms in signal processing and information sharing that takes place in different parts of the primates’ visual system thus enabling it to accomplish many diverse functions of visual perception. One of the main functions of the primates’ vision is to detect and recognise objects in natural scenes despite all the linear and non-linear variations of the objects and their environment. The superior performance of the primates’ visual system compared to what machine vision systems have been able to achieve to date, motivates scientists and researchers to further explore this area in pursuit of more efficient vision systems inspired by natural models. In this paper building blocks for a hierarchical efficient object recognition model are proposed. Incorporating the attention-based processing would lead to a system that will process the visual data in a non-linear way focusing only on the regions of interest and hence reducing the time to achieve real-time performance. Further, it is suggested to modify the visual cortex model for recognizing objects by adding non-linearities in the ventral path consistent with earlier discoveries as reported by researchers in the neuro-physiology of vision.

Cue combination for 3D location judgements

Cue combination rules have often been applied to the perception of surface shape but not to judgements of object location. Here, we used immersive virtual reality to explore the relationship between different cues to distance. Participants viewed a virtual scene and judged the change in distance of an object presented in two intervals, where the scene changed in size between intervals (by a factor of between 0.25 and 4). We measured thresholds for detecting a change in object distance when there were only 'physical' (stereo and motion parallax) or 'texture-based' cues (independent of the scale of the scene) and used these to predict biases in a distance matching task. Under a range of conditions, in which the viewing distance and position of the tarte relative to other objects was varied, the ration of 'physical' to 'texture-based' thresholds was a good predictor of biases in the distance matching task. The cue combination approach, which successfully accounts for our data, relies on quite different principles from those underlying geometric reconstruction.

Perception and modification of plant flavonoid signals by rhizosphere microorganisms

Flavonoids are a diverse class of polyphenolic compounds that are produced as a result of plant secondary metabolism. They are known to play a multifunctional role in rhizospheric plant-microbe and plant-plant communication. Most familiar is their function as a signal in initiation of the legume-rhizobia symbiosis, but, flavonoids may also be signals in the establishment of arbuscular mycorrhizal symbiosis and are known agents in plant defence and in allelopathic interactions. Flavonoid perception by, and impact on, their microbial targets (e.g. rhizobia, plant pathogens) is relatively well characterized. However, potential impacts on 'non-target' rhizosphere inhabitants ('non-target' is used to distinguish those microorganisms not conventionally known as targets) have not been thoroughly investigated. Thus, this review first summarizes the conventional roles of flavonoids as nod gene inducers, phytoalexins and allelochemicals before exploring questions concerning 'non-target' impacts. We hypothesize that flavonoids act to shape rhizosphere microbial community structure because they represent a potential source of carbon and toxicity and that they impact on rhizosphere function, for example, by accelerating the biodegradation of xenobiotics. We also examine the reverse question, 'how do rhizosphere microbial communities impact on flavonoid signals?' The presence of microorganisms undoubtedly influences the quality and quantity of flavonoids present in the rhizosphere, both through modification of root exudation patterns and microbial catabolism of exudates. Microbial alteration and attenuation of flavonoid signals may have ecological consequences for below-ground plant-microbe and plant-plant interaction. We have a lack of knowledge concerning the composition, concentration and bioavailability of flavonoids actually experienced by microbes in an intact rhizosphere, but this may be addressed through advances in microspectroscopic and biosensor techniques. Through the use of plant mutants defective in flavonoid biosynthesis, we may also start to address the question of the significance of flavonoids in shaping rhizosphere community structure and function.

Perceptual grouping and distance estimates in typical and atypical development: comparing performance across perception, drawing and construction tasks

Perceptual grouping is a pre-attentive process which serves to group local elements into global wholes, based on shared properties. One effect of perceptual grouping is to distort the ability to estimate the distance between two elements. In this study, biases in distance estimates, caused by four types of perceptual grouping, were measured across three tasks, a perception, a drawing and a construction task in both typical development (TD: Experiment 1) and in individuals with Williams syndrome (WS: Experiment 2). In Experiment 1, perceptual grouping distorted distance estimates across all three tasks. Interestingly, the effect of grouping by luminance was in the opposite direction to the effects of the remaining grouping types. We relate this to differences in the ability to inhibit perceptual grouping effects on distance estimates. Additive distorting influences were also observed in the drawing and the construction task, which are explained in terms of the points of reference employed in each task. Experiment 2 demonstrated that the above distortion effects are also observed in WS. Given the known deficit in the ability to use perceptual grouping in WS, this suggests a dissociation between the pre-attentive influence of and the attentive deployment of perceptual grouping in WS. The typical distortion in relation to drawing and construction points towards the presence of some typical location coding strategies in WS. The performance of the WS group differed from the TD participants on two counts. First, the pattern of overall distance estimates (averaged across interior and exterior distances) across the four perceptual grouping types, differed between groups. Second, the distorting influence of perceptual grouping was strongest for grouping by shape similarity in WS, which contrasts to a strength in grouping by proximity observed in the TD participants. (c) 2008 Elsevier Inc. All rights reserved.

A novel shape feature for fast region-based pedestrian recognition

A new class of shape features for region classification and high-level recognition is introduced. The novel Randomised Region Ray (RRR) features can be used to train binary decision trees for object category classification using an abstract representation of the scene. In particular we address the problem of human detection using an over segmented input image. We therefore do not rely on pixel values for training, instead we design and train specialised classifiers on the sparse set of semantic regions which compose the image. Thanks to the abstract nature of the input, the trained classifier has the potential to be fast and applicable to extreme imagery conditions. We demonstrate and evaluate its performance in people detection using a pedestrian dataset.

Representing geometrical knowledge

This paper introduces perspex algebra which is being developed as a common representation of geometrical knowledge. A perspex can currently be interpreted in one of four ways. First, the algebraic perspex is a generalization of matrices, it provides the most general representation for all of the interpretations of a perspex. The algebraic perspex can be used to describe arbitrary sets of coordinates. The remaining three interpretations of the perspex are all related to square matrices and operate in a Euclidean model of projective space-time, called perspex space. Perspex space differs from the usual Euclidean model of projective space in that it contains the point at nullity. It is argued that the point at nullity is necessary for a consistent account of perspective in top-down vision. Second, the geometric perspex is a simplex in perspex space. It can be used as a primitive building block for shapes, or as a way of recording landmarks on shapes. Third, the transformational perspex describes linear transformations in perspex space that provide the affine and perspective transformations in space-time. It can be used to match a prototype shape to an image, even in so called 'accidental' views where the depth of an object disappears from view, or an object stays in the same place across time. Fourth, the parametric perspex describes the geometric and transformational perspexes in terms of parameters that are related to everyday English descriptions. The parametric perspex can be used to obtain both continuous and categorical perception of objects. The paper ends with a discussion of issues related to using a perspex to describe logic.

Judging size, distance and depth with an active telepresence system

A visual telepresence system has been developed at the University of Reading which utilizes eye tracing to adjust the horizontal orientation of the cameras and display system according to the convergence state of the operator's eyes. Slaving the cameras to the operator's direction of gaze enables the object of interest to be centered on the displays. The advantage of this is that the camera field of view may be decreased to maximize the achievable depth resolution. An active camera system requires an active display system if appropriate binocular cues are to be preserved. For some applications, which critically depend upon the veridical perception of the object's location and dimensions, it is imperative that the contribution of binocular cues to these judgements be ascertained because they are directly influenced by camera and display geometry. Using the active telepresence system, we investigated the contribution of ocular convergence information to judgements of size, distance and shape. Participants performed an open- loop reach and grasp of the virtual object under reduced cue conditions where the orientation of the cameras and the displays were either matched or unmatched. Inappropriate convergence information produced weak perceptual distortions and caused problems in fusing the images.

Measuring student perception and actual usage of online learning management system

Online learning management systems are in use to facilitate the face to face learning process in many universities. There are many variables that shape and influence a student’s perception of an online learning management system. This study investigates whether there is a relationship between the perception of a student regarding the learning management system and their actual usage of such system. It is believed to help better understand the student usage of online learning management system. An online questionnaire was published on a course management system for a selected subject and the student participation was voluntary. Results indicate that no significant relationship between the perception students had about the learning management system and the actual use of the system. Interestingly, a significant relationship was found between having internet access away from university and the student perception about the system. Students who had internet access away from university had better perception about the learning management system even though there was no significant difference in the level of online learning management system usage between the groups.

Dissociating between object affordances and spatial compatibility effects using early response components

Perception and action are tightly linked: objects may be perceived not only in terms of visual features, but also in terms of possibilities for action. Previous studies showed that when a centrally located object has a salient graspable feature (e.g., a handle), it facilitates motor responses corresponding with the feature's position. However, such so-called affordance effects have been criticized as resulting from spatial compatibility effects, due to the visual asymmetry created by the graspable feature, irrespective of any affordances. In order to dissociate between affordance and spatial compatibility effects, we asked participants to perform a simple reaction-time task to typically graspable and non-graspable objects with similar visual features (e.g., lollipop and stop sign). Responses were measured using either electromyography (EMG) on proximal arm muscles during reaching-like movements, or with finger key-presses. In both EMG and button press measurements, participants responded faster when the object was either presented in the same location as the responding hand, or was affordable, resulting in significant and independent spatial compatibility and affordance effects, but no interaction. Furthermore, while the spatial compatibility effect was present from the earliest stages of movement preparation and throughout the different stages of movement execution, the affordance effect was restricted to the early stages of movement execution. Finally, we tested a small group of unilateral arm amputees using EMG, and found residual spatial compatibility but no affordance, suggesting that spatial compatibility effects do not necessarily rely on individuals’ available affordances. Our results show dissociation between affordance and spatial compatibility effects, and suggest that rather than evoking the specific motor action most suitable for interaction with the viewed object, graspable objects prompt the motor system in a general, body-part independent fashion

Unconscious effects of grammatical gender during object categorisation

Does language modulate perception and categorisation of everyday objects? Here, we approach this question from the perspective of grammatical gender in bilinguals. We tested Spanish–English bilinguals and control native speakers of English in a semantic categorisation task on triplets of pictures in an all-in-English context while measuring event-related brain potentials (ERPs). Participants were asked to press a button when the third picture of a triplet belonged to the same semantic category as the first two, and another button when it belonged to a different category. Unbeknownst to them, in half of the trials, the gender of the third picture name in Spanish had the same gender as that of the first two, and the opposite gender in the other half. We found no priming in behavioural results of either semantic relatedness or gender consistency. In contrast, ERPs revealed not only the expected semantic priming effect in both groups, but also a negative modulation by gender inconsistency in Spanish–English bilinguals, exclusively. These results provide evidence for spontaneous and unconscious access to grammatical gender in participants functioning in a context requiring no access to such information, thereby providing support for linguistic relativity effects in the grammatical domain.

Methods of sensory augmentation through electro-tactile stimulation of the tongue

This paper details an investigation into sensory substitution by means of direct electrical stimulation of the tongue for the purpose of information input to the human brain. In particular, a device has been constructed and a series of trials have been performed in order to demonstrate the efficacy and performance of an electro-tactile array mounted onto the tongue surface for the purpose of sensory augmentation. Tests have shown that by using a low resolution array a computer-human feedback loop can be successfully implemented by humans in order to complete tasks such as object tracking, surface shape identification and shape recognition with no training or prior experience with the device. Comparisons of this technique have been made with visual alternatives and these show that the tongue based tactile array can match such methods in convenience and accuracy in performing simple tasks.