The aim of this paper is to present different algorithms, based on a combination of two structures of graph and of two color image processing methods, in order to segment color images. The structures used in this study are the region adjacency graph and the line graph associated.We will see how these structures can enhance segmentation processes such as region growing or watershed transformation. The principal advantage of these structures is that they give more weight to adjacency relationships between regions than usual methods. Let us note nevertheless that this advantage leads in return to adjust more parameters than other methods to best refine the result of the segmentation.We will show that this adjustment is necessarily image dependent and observer dependent.

Observation suggests that the chromatic changes which elicit an impression of transparency include translations and convergences in color space. Neither rotations nor shears in color space lead to perceived transparency. Results of matching experiments show that equiluminous translations, which cannot be generated by episcotister or filter models, give rise to the perception of transparency. This implies that systematic luminance change is not needed for transparency to be perceived. These results were used for the development of a method for detecting a transparent overlay within a color image and for separating the overlay from the underlying surfaces. The method tests for the coherence of chromatic change along contours through X-junctions to help detect the contour of a transparent region. The algorithm tests locally for translation and convergence to detect a transparent region. It estimates globally the chromatic parameters of the transparent overlay in order to separate the overlay from the underlying surfaces.

Abstract. In recent years, there has been renewed interest in bilateral symmetry detection in images. It consists in detecting the main bilateral symmetry axis inside artificial or natural images. State-of-the-art methods combine feature point detection, pairwise comparison and voting in Hough-like space. In spite of their good performance, they fail to give reliable results over challenging real-world and artistic images. In this paper, we propose a novel symmetry detection method using multi-scale edge features combined with local orientation histograms. An experimental evaluation is conducted on public datasets plus a new aesthetic-oriented dataset. The results show that our approach outperforms all other concurrent methods.

International audienceA new, accurate, and technology-independent display color-characterization model, and its application to the colorimetric rendering of multispectral images, is introduced. It is based on polyharmonic spline interpolation and on an optimized adaptive training data set. The establishment of this model is fully automatic and requires only a few minutes,making it efficient in a practical situation. The experimental results are very good for both the forward and inverse models. Typically, the proposed model yields an average model prediction error of about 1 ΔEab* unit or below for several displays. The maximum error is shown to be low as well

Symmetry is one of the significant visual properties inside an image plane, to identify the geometrically balanced structures through real-world objects. Existing symmetry detection methods rely on descriptors of the local image features and their neighborhood behavior, resulting incomplete symmetrical axis candidates to discover the mirror similarities on a global scale. In this paper, we propose a new reflection symmetry detection scheme, based on a reliable edge-based feature extraction using Log-Gabor filters, plus an efficient voting scheme parameterized by their corresponding textural and color neighborhood information. Experimental evaluation on four single-case and three multiple-case symmetry detection datasets validates the superior achievement of the proposed work to find global symmetries inside an image.

No abstract

We have defined an inverse model for colorimetric characterization of additive displays. It is based on an optimized three-dimensional tetrahedral structure. In order to minimize the number of measurements, the structure is defined using a forward characterization model. Defining a regular grid in the device-dependent destination color space leads to heterogeneous interpolation errors in the device-independent source color space. The parameters of the function used to define the grid are optimized using a globalized Nelder-Mead simplex downhill algorithm. Several cost functions are tested on several devices. We have performed experiments with a forward model which assumes variation in chromaticities (PLVC), based on one-dimensional interpolations for each primary ramp along X, Y and Z (3 × 3 × 1 − D). Results on 4 devices (2 LCD and a DLP projection devices, one LCD monitor) are shown and discussed.

We describe methods for displaying complex, texturemapped environments with four or more spatial dimensions that allow for real-time interaction. At any one moment in time, a three-dimensional cross section of the high-dimensional environment is rendered using techniques that have been implemented in OpenGL. The position and orientation of the user within the environment determine the 3-D cross section. A variety of interfaces can be used to control position and orientation in 4-D, including a mouse “freelook” interface for use with a computer monitor display, and an interface that uses a head-tracking system with three degrees of freedom and PINCH gloves in combination with a head-mounted display. The methods avoid the use of projections that require depth buffering in greater than three dimensions and can be used in conjunction with either 2-D or 3-D texture mapping. A computer graphic engine that displays 4-D virtual environments interactively uses these methods, as does a level editor and modeling program that can be used to create 4-D environments.