Robert Benavente

Parametric fuzzy sets for automatic color naming.

In this paper we present a parametric model for automatic color naming where each color category is modeled as a fuzzy set with a parametric membership function. The parameters of the functions are estimated in a fitting process using data derived from psychophysical experiments. The name assignments obtained by the model agree with previous psychophysical experiments, and therefore the high-level color-naming information provided can be useful for different computer vision applications where the use of a parametric model will introduce interesting advantages in terms of implementation costs, data representation, model analysis, and model updating.

Names and shades of color for intrinsic image estimation

In the last years, intrinsic image decomposition has gained attention. Most of the state-of-the-art methods are based on the assumption that reflectance changes come along with strong image edges. Recently, user intervention in the recovery problem has proved to be a remarkable source of improvement. In this paper, we propose a novel approach that aims to overcome the shortcomings of pure edge-based methods by introducing strong surface descriptors, such as the color-name descriptor which introduces high-level considerations resembling top-down intervention. We also use a second surface descriptor, termed color-shade, which allows us to include physical considerations derived from the image formation model capturing gradual color surface variations. Both color cues are combined by means of a Markov Random Field. The method is quantitatively tested on the MIT ground truth dataset using different error metrics, achieving state-of-the-art performance.

Induction operators for a computational colour-texture representation

The aim of this paper is to outline a perceptual approach to a computational colour-texture representation based on some colour induction phenomena. The extension of classical grey level methods for texture processing to the RGB channels of the corresponding colour texture is not the best solution to simulate human perception. Chromatic induction mechanisms of the human visual system, that has been widely studied in psychophysics, play an important role when looking at scenes where the spatial frequency is high as it occurs on texture images. Besides others, chromatic induction includes two complementary effects: chromatic assimilation and chromatic contrast. While the former has been measured by Wandell and Zhang [A spatial extension of CIELAB for digital colour image reproduction, in: SID, 1996] and extended to computer vision by Petrou et al. [Perceptual smoothing and segmentation of colour textures, in: 5th European Conference on Computer Vision, Freiburg, Germany, 1998, pp. 623] as a perceptual blurring, some aspects on the last one still remain to be measured, but it has to be a computational operator that simulates the contrast induction phenomenon performing a perceptual sharpening that preserves the structural properties of the texture. Applying both, the perceptual sharpening and the perceptual blurring, we propose to build a tower of images as an induction front-end that can be the basis of a perceptual representation of colour textures.

Quality control of safety belts by machine vision inspection for real-time production

Safety belts are specific fabrics manufactured to ensure the highest performance. Their manufacturing process not only has to assure its endurance to high tension strength, but also has to guarantee its correct visual appearance. Safety belts must not contain fiber breaks, knots, thickness variations, etc. Such defects imply the unfulfillment of rigorous safety standards. We describe the development of a computer vision inspection system, which control safety belts at a speed rate of 2 m/s. This inspection rate has been achieved by means of a parallel architecture and the use of optimized vision algorithms.

Intrinsic image evaluation on synthetic complex scenes

Scene decomposition into its illuminant, shading, and reflectance intrinsic images is an essential step for scene understanding. Collecting intrinsic image groundtruth data is a laborious task. The assumptions on which the ground-truth procedures are based limit their application to simple scenes with a single object taken in the absence of indirect lighting and interreflections. We investigate synthetic data for intrinsic image research since the extraction of ground truth is straightforward, and it allows for scenes in more realistic situations (e.g, multiple illuminants and interreflections). With this dataset we aim to motivate researchers to further explore intrinsic image decomposition in complex scenes.

Adaptation of a computer programming course to the ESHE requirements: evaluation five years later

In the academic year 2010–2011, Spain finished the process of introducing the regulatory changes derived from the Bologna Declaration and the new European Space for Higher Education (ESHE). These changes have implied the updating of university degrees’ structure as well as the inclusion of the European Credit Transfer System (ECTS). This paper describes the process of adaptation of two basic first-semester core subjects of computer engineering to one of the basic aspects of the ESHE, the adoption of the ECTS. The process described in the paper was developed in the framework of the pilot plan undertaken by the Universitat Autònoma de Barcelona between 2005 and 2010. The proposed course design implies a better coordination and integration of the contents of two different subjects that students follow simultaneously, and it is based on the combination of project-based learning and cooperative learning. After the experience finished, an extended quantitative and qualitative analysis of the academic results over the five-year period has shown an improvement in the students’ learning outcomes.

Textual Descriptors for Browsing People by Visual Appearance

This paper presents a first approach to build colour and structural descriptors for information retrieval on a people database. Queries are formulated in terms of their appearance that allows to seek people wearing specific clothes of a given colour name or texture. Descriptors are automatically computed by following three essential steps. A colour naming labelling from pixel properties. A region segmentation step based on colour properties of pixels combined with edge information. And a high level step that models the region arrangements in order to build clothes structure. Results are tested on large set of images from real scenes taken at the entrance desk of a building.

Color image enhancement based on perceptual sharpening

In this paper we present a sharpening operator for color images that is based on perceptual considerations about how human visual behaves for color scenes. Color contrast is an induction phenomenon of the visual system that varies the chromaticity of a color region depending on the color of its surround, provoking an enhanced perception of color scenes. This effect can be simulated by a sharpening operator based on a Laplacian of Gaussian filtering combined with an interpolation process. This operator presents interesting properties to remove noise in regions of similar color, to enhance edges without destroying region structures and not prevent the creation of false color edges.

Coloresia: An Interactive Colour Perception Device for the Visually Impaired

A significative percentage of the human population suffer from impairments in their capacity to distinguish or even see colours. For them, everyday tasks like navigating through a train or metro network map becomes demanding. We present a novel technique for extracting colour information from everyday natural stimuli and presenting it to visually impaired users as pleasant, non-invasive sound. This technique was implemented inside a Personal Digital Assistant (PDA) portable device. In this implementation, colour information is extracted from the input image and categorised according to how human observers segment the colour space. This information is subsequently converted into sound and sent to the user via speakers or headphones. In the original implementation, it is possible for the user to send its feedback to reconfigure the system, however several features such as these were not implemented because the current technology is limited.We are confident that the full implementation will be possible in the near future as PDA technology improves.

Enhancing spatio-chromatic representation with more-than-three color coding for image description

The extraction of spatio-chromatic features from color images is usually performed independently on each color channel. Usual 3D color spaces, such as RGB, present a high inter-channel correlation for natural images. This correlation can be reduced using color-opponent representations, but the spatial structure of regions with small color differences is not fully captured in two generic Red-Green and Blue-Yellow channels. To overcome these problems, we propose new color coding that is adapted to the specific content of each image. Our proposal is based on two steps: (a) setting the number of channels to the number of distinctive colors we find in each image (avoiding the problem of channel correlation), and (b) building a channel representation that maximizes contrast differences within each color channel (avoiding the problem of low local contrast). We call this approach more-than-three color coding (MTT) to emphasize the fact that the number of channels is adapted to the image content. The higher the color complexity of an image, the more channels can be used to represent it. Here we select distinctive colors as the most predominant in the image, which we call color pivots, and we build the new color coding strategy using these color pivots as a basis. To evaluate the proposed approach, we measure the efficiency in an image categorization task. We show how a generic descriptor improves performance at the description level when applied to the MTT coding.