This paper describes a method for recognising and localising objects from a known class. Objects are modelled as a collection of simple geometric features and their spatial arrangement. Probability distributions on the parameters of the geometric features and their positions are used to handle the variability between members of the object class. Range images are processed to extract features (p...

The feature recognition problem is formulated as a geometric constraint satisfaction problem (GCSP), in which variables are the faces in the delta volume, the possible feature classiications determine values for the variables, and the constraints are the geometric and topological properties between the variables. A novel representation language is proposed to encode more, and somewhat redundant...

An algebra for geometric reasoning is developed that is amenable to software implementation. The features of the algebra are chosen to support geometric programming of the variety found in computer graphics and computer aided geometric design applications. The implementation of the algebra in C++ is described, and several examples illustrating the use of this software are given.

Aging progress of a person is influenced by many factors such as genetics, health, lifestyle, and even weather conditions. Therefore human age estimation from a face image is a challenging problem. Aging causes significant variations in facial shape and texture across years. In order to construct a general age classifier, shape and texture information of human face should be used together. In t...

We propose a coarse registration method of range images using both geometric and photometric features. The framework of existing methods using multiple features first defines a single similarity distance summing up each feature based evaluations, and then minimizes the distance between range images for registration. In contrast, we formulate registration as a graph-based optimization problem, w...

We present a new, procedural approach for modelling and animating the garments worn by virtual characters. Our method takes into account the properties of fabric to generate the geometry of local folds that are so crucial for visual realism. Modelling is performed by approximating an initial free-form surface roughly representing a garment by a piecewise developable mesh called the buckling mes...

Person identification and verification using biometric methods is getting more and more important in today’s information society. Hand recognition is a promising biometric because of its simplicity and fairly good performance of verification. In this work, implicit polynomials, which have proven to be very successful in object modeling and recognition, have been proposed for recognizing hand sh...

“Normal foot model” is a geometric model of a healthy human foot. As the comparison of the processed feet requires a reference ideal healthy foot parameterization it was necessary to create such a model by defining skeleton geometric features and generating the feature set on a dataset population. Manual positioning of such number of landmarks is both a complex and time consuming task for a ski...

One of the most important goals of computer vision research is object recognition. Most current object recognition algorithms assume reliable image segmentation, which in practice is often not available. This research exploits the combination of the Hough method with the geometric hashing technique for model-based object recognition in seriously degraded intensity images. We describe the analys...

Recent advances in object recognition have emphasized the integration of intensity-derived features such as affine patches with associated geometric constraints leading to impressive performance in complex scenes. Over the four previous decades, the central paradigm of recognition was based on formal geometric object descriptions with a focus on the properties of such descriptions under perspec...