People	Publications	Research projects	Downloads

The CVC colour group focuses its research in areas related to computational colour within computer vision. Our long term objective is to create computer algorithms that simulate human perception and categorisation of colour. To achieve this aim, we study colour as a visual cue in its context. Our main research lines are colour constancy, induction, saliency, texture,segmentation and naming.

Color Feature Detection for Object Recognition Luminance edges are still the main source of information in the state-of-the-art methods for feature detection. We propose to exploit the statistical structure of luminance and color in natural images to extract the most discriminative features from the viewpoint of information theory for object recognition.

Related publications

Parametric model for Color Naming A full parametric model has been defined on the CIE lab space. Each of the 11 basic colour categories is modelled with a fuzzy set characterized by a combination of sigmoids as membership functions.

Related publications

Psychophysical Error Measure for Colour Constancy In this paper we propose a new evaluation in order to compare solutions of different colour constancy algorithms. this new approach is based on a psychophysical experiment to relate this new evaluation with human perception instead of physical properties.

Related publications

Chromatic Settings: new colour constancy paradigm In our study, we developed a new colour constancy paradigm, termed chromatic setting, which allows measuring the precise location of nine categorically-relevant points in colour space under immersive illumination. Additionally, we derived from these measurements a new colour constancy index which takes into account the magnitude and orientation of the chromatic shift, memory effects and the interrelations among colours and a model of colour naming tuned to each observer/adaptation state.

Related publications

Physics-based color image segmentation Based on an analysis of the bi-directional reflection model we propose a method which is particularly suited for segmentation in the presence of shadow and highlight edges.

Related publications