An application of fractal image-set coding in facial recognition

Faces are complex patterns that often differ in only subtle ways. Face recognition algorithms have difficulty in coping with differences in lighting, cameras, pose, expression, etc. We propose a novel approach for facial recognition based on a new feature extraction method called fractal image-set encoding. This feature extraction method is a specialized fractal image coding technique that makes fractal codes more suitable for object and face recognition. A fractal code of a gray-scale image can be divided in two parts – geometrical parameters and luminance parameters. We show that fractal codes for an image are not unique and that we can change the set of fractal parameters without significant change in the quality of the reconstructed image. Fractal image-set coding keeps geometrical parameters the same for all images in the database. Differences between images are captured in the non-geometrical or luminance parameters – which are faster to compute. Results on a subset of the XM2VTS database are presented.

Adaptive optical flow for person tracking

Person tracking systems are dependent on being able to locate a person accurately across a series of frames. Optical flow can be used to segment a moving object from a scene, provided the expected velocity of the moving object is known; but successful detection also relies on being able segment the background. A problem with existing optical flow techniques is that they don’t discriminate the foreground from the background, and so often detect motion (and thus the object) in the background. To overcome this problem, we propose a new optical flow technique, that is based upon an adaptive background segmentation technique, which only determines optical flow in regions of motion. This technique has been developed with a view to being used in surveillance systems, and our testing shows that for this application it is more effective than other standard optical flow techniques.

Attention and memory bias for body image and health related information using an Emotional Stroop task in a non-clinical sample

It has been proposed that body image disturbance is a form of cognitive bias wherein schemas for self-relevant information guide the selective processing of appearancerelated information in the environment. This threatening information receives disproportionately more attention and memory, as measured by an Emotional Stroop and incidental recall task. The aim of this thesis was to expand the literature on cognitive processing biases in non-clinical males and females by incorporating a number of significant methodological refinements. To achieve this aim, three phases of research were conducted. The initial two phases of research provided preliminary data to inform the development of the main study. Phase One was a qualitative exploration of body image concerns amongst males and females recruited through the general community and from a university. Seventeen participants (eight male; nine female) provided information on their body image and what factors they saw as positively and negatively impacting on their self evaluations. The importance of self esteem, mood, health and fitness, and recognition of the social ideal were identified as key themes. These themes were incorporated as psycho-social measures and Stroop word stimuli in subsequent phases of the research. Phase Two involved the selection and testing of stimuli to be used in the Emotional Stroop task. Six experimental categories of words were developed that reflected a broad range of health and body image concerns for males and females. These categories were high and low calorie food words, positive and negative appearance words, negative emotion words, and physical activity words. Phase Three addressed the central aim of the project by examining cognitive biases for body image information in empirically defined sub-groups. A National sample of males (N = 55) and females (N = 144), recruited from the general community and universities, completed an Emotional Stroop task, incidental memory test, and a collection of psycho-social questionnaires. Sub-groups of body image disturbance were sought using a cluster analysis, which identified three sub-groups in males (Normal, Dissatisfied, and Athletic) and four sub-groups in females (Normal, Health Conscious, Dissatisfied, and Symptomatic). No differences were noted between the groups in selective attention, although time taken to colour name the words was associated with some of the psycho-social variables. Memory biases found across the whole sample for negative emotion, low calorie food, and negative appearance words were interpreted as reflecting the current focus on health and stigma against being unattractive. Collectively these results have expanded our understanding of processing biases in the general community by demonstrating that the processing biases are found within non-clinical samples and that not all processing biases are associated with negative functionality

Generation of a 3D proximal femur shape from a single projection 2D radiographic image.

Summary Generalized Procrustes analysis and thin plate splines were employed to create an average 3D shape template of the proximal femur that was warped to the size and shape of a single 2D radiographic image of a subject. Mean absolute depth errors are comparable with previous approaches utilising multiple 2D input projections. Introduction Several approaches have been adopted to derive volumetric density (g cm-3) from a conventional 2D representation of areal bone mineral density (BMD, g cm-2). Such approaches have generally aimed at deriving an average depth across the areal projection rather than creating a formal 3D shape of the bone. Methods Generalized Procrustes analysis and thin plate splines were employed to create an average 3D shape template of the proximal femur that was subsequently warped to suit the size and shape of a single 2D radiographic image of a subject. CT scans of excised human femora, 18 and 24 scanned at pixel resolutions of 1.08 mm and 0.674 mm, respectively, were equally split into training (created 3D shape template) and test cohorts. Results The mean absolute depth errors of 3.4 mm and 1.73 mm, respectively, for the two CT pixel sizes are comparable with previous approaches based upon multiple 2D input projections. Conclusions This technique has the potential to derive volumetric density from BMD and to facilitate 3D finite element analysis for prediction of the mechanical integrity of the proximal femur. It may further be applied to other anatomical bone sites such as the distal radius and lumbar spine.

Mid-level concept learning with visual contextual ontologies and probabilistic inference for image annotation

To date, automatic recognition of semantic information such as salient objects and mid-level concepts from images is a challenging task. Since real-world objects tend to exist in a context within their environment, the computer vision researchers have increasingly incorporated contextual information for improving object recognition. In this paper, we present a method to build a visual contextual ontology from salient objects descriptions for image annotation. The ontologies include not only partOf/kindOf relations, but also spatial and co-occurrence relations. A two-step image annotation algorithm is also proposed based on ontology relations and probabilistic inference. Different from most of the existing work, we specially exploit how to combine representation of ontology, contextual knowledge and probabilistic inference. The experiments show that image annotation results are improved in the LabelMe dataset.

Crowd Counting Using Multiple Local Features

In public venues, crowd size is a key indicator of crowd safety and stability. Crowding levels can be detected using holistic image features, however this requires a large amount of training data to capture the wide variations in crowd distribution. If a crowd counting algorithm is to be deployed across a large number of cameras, such a large and burdensome training requirement is far from ideal. In this paper we propose an approach that uses local features to count the number of people in each foreground blob segment, so that the total crowd estimate is the sum of the group sizes. This results in an approach that is scalable to crowd volumes not seen in the training data, and can be trained on a very small data set. As a local approach is used, the proposed algorithm can easily be used to estimate crowd density throughout different regions of the scene and be used in a multi-camera environment. A unique localised approach to ground truth annotation reduces the required training data is also presented, as a localised approach to crowd counting has different training requirements to a holistic one. Testing on a large pedestrian database compares the proposed technique to existing holistic techniques and demonstrates improved accuracy, and superior performance when test conditions are unseen in the training set, or a minimal training set is used.

Robot navigation in sensor space

This thesis investigates the problem of robot navigation using only landmark bearings. The proposed system allows a robot to move to a ground target location specified by the sensor values observed at this ground target posi- tion. The control actions are computed based on the difference between the current landmark bearings and the target landmark bearings. No Cartesian coordinates with respect to the ground are computed by the control system. The robot navigates using solely information from the bearing sensor space. Most existing robot navigation systems require a ground frame (2D Cartesian coordinate system) in order to navigate from a ground point A to a ground point B. The commonly used sensors such as laser range scanner, sonar, infrared, and vision do not directly provide the 2D ground coordi- nates of the robot. The existing systems use the sensor measurements to localise the robot with respect to a map, a set of 2D coordinates of the objects of interest. It is more natural to navigate between the points in the sensor space corresponding to A and B without requiring the Cartesian map and the localisation process. Research on animals has revealed how insects are able to exploit very limited computational and memory resources to successfully navigate to a desired destination without computing Cartesian positions. For example, a honeybee balances the left and right optical flows to navigate in a nar- row corridor. Unlike many other ants, Cataglyphis bicolor does not secrete pheromone trails in order to find its way home but instead uses the sun as a compass to keep track of its home direction vector. The home vector can be inaccurate, so the ant also uses landmark recognition. More precisely, it takes snapshots and compass headings of some landmarks. To return home, the ant tries to line up the landmarks exactly as they were before it started wandering. This thesis introduces a navigation method based on reflex actions in sensor space. The sensor vector is made of the bearings of some landmarks, and the reflex action is a gradient descent with respect to the distance in sensor space between the current sensor vector and the target sensor vec- tor. Our theoretical analysis shows that except for some fully characterized pathological cases, any point is reachable from any other point by reflex action in the bearing sensor space provided the environment contains three landmarks and is free of obstacles. The trajectories of a robot using reflex navigation, like other image- based visual control strategies, do not correspond necessarily to the shortest paths on the ground, because the sensor error is minimized, not the moving distance on the ground. However, we show that the use of a sequence of waypoints in sensor space can address this problem. In order to identify relevant waypoints, we train a Self Organising Map (SOM) from a set of observations uniformly distributed with respect to the ground. This SOM provides a sense of location to the robot, and allows a form of path planning in sensor space. The navigation proposed system is analysed theoretically, and evaluated both in simulation and with experiments on a real robot.