Philip E Robinson

University of Johannesburg | uj · Department of Electrical and Electronic Engineering

Video sequences captured over a long range through the turbulent atmosphere contain some degree of atmospheric turbulence degradation (ATD). Stabilization of the geometric distortions present in video sequences containing ATD and containing objects undergoing real motion is a challenging task. This is due to the difficulty of discriminating which p...

Traditional assessment of programming ability, as well as more recent automated assessment systems, consider only the completed program submitted by the student. We present a system which automatically monitors and assesses the code-production process as well as the final product, allowing adaptive feedback and assessment of programming competency....

The modeling and quantification of digital photographic image quality has, from a psychophysics perspective, traditionally followed two paths, one of which is the discriminable small or just noticeable difference (local psychophysics) as detected in an image pair; further extended to cover a wide range of attribute artefactual quality variation. Th...

In this paper, we present and investigate the performance of an algorithm designed to identify facial features on an android mobile platform. Facial feature identification is the necessary step before many computer vision systems including emotion detection, face tracking and face recognition. The facial feature identification algorithm presented i...

Image restoration algorithms are used to reconstruct the information that is suppressed when an observed image is subjected to blurring. These algorithms generally assume that knowledge of the nature of the distortion and noise contained in an observed image is available. When this information is not available and has to be directly estimated from...

An object tracking algorithm using the Mean Shift framework is presented which is largely invariant to both partial and full occlusions, complex backgrounds and change in scale. Multiple features are used to gain a descriptive representation of the target object. Image moments are used to determine the scale of the target object. A kalman filter is...

A novel method for estimating the variance and standard deviation of the additive white Gaussian noise contained in an image will be presented. Only a single image is used to estimate the noise properties. Local image outliers are discarded, this allows us to separate the additive zero mean white Gaussian noise contained in a noisy image from the o...

This paper explores the problem of atmospheric turbulence in long range video surveillance. This turbulence causes a phenomenon called heat scintillation or heat shimmer which introduces distortions into the video being captured. The nature of these distortions is discussed and a number of possible solutions explored. Using these solutions, three a...

Long range imaging systems that capture video through the atmosphere face a major problem in the form of atmospheric turbulence. This turbulence causes a phenomenon called heat shimmer which appears as a blurring and a wavering geometric distortion of the target scene which limits the effective range of the imaging system. We explore an image proce...

In this paper two face recognition techniques, principal component analysis (PCA) and linear discriminant analysis (LDA), are considered and implemented using a nearest neighbor classifier. The performance of the two techniques is then compared in facial recognition and detection tasks. The comparisons are done using a facial recognition database c...