Showing papers by "Christine Fernandez-Maloigne published in 2009"

A Bandelet-Based Inpainting Technique for Clouds Removal From Remotely Sensed Images

Abstract: It is well known that removing cloud-contaminated portions of a remotely sensed image and then filling in the missing data represent an important photo editing cumbersome task. In this paper, an efficient inpainting technique for the reconstruction of areas obscured by clouds or cloud shadows in remotely sensed images is presented. This technique is based on the Bandelet transform and the multiscale geometrical grouping. It consists of two steps. In the first step, the curves of geometric flow of different zones of the image are determined by using the Bandelet transform with multiscale grouping. This step allows an efficient representation of the multiscale geometry of the image's structures. Having well represented this geometry, the information inside the cloud-contaminated zone is synthesized by propagating the geometrical flow curves inside that zone. This step is accomplished by minimizing a functional whose role is to reconstruct the missing or cloud contaminated zone independently of the size and topology of the inpainting domain. The proposed technique is illustrated with some examples on processing aerial images. The obtained results are compared with those obtained by other clouds removal techniques.

A grouplet-based reduced reference image quality assessment

Abstract: The past decades have witnessed the tremendous growth of digital image processing techniques for visual information representation and communication. Particularly, computational representation of perceived image quality has become a fundamental problem in computer vision and image processing. It is well known that the commonly used Peak Signal-to-Noise Ratio (PSNR), although analysis friendly, falls far short of this need. In this work, we propose a reduced reference (RR) perceptual image quality measure (IQM) based on the grouplet transform. Given a reference image and its “distorted” version, we first compute the grouplet transform in order to extract the information of textures and directions of both images. Then, contrast sensitivity function (CSF) filtering is performed to obtain same visual sensitivity information within both images. Thereafter, based on the properties of the human visual system (HVS), rational sensitivity thresholding is performed to obtain the sensitivity coefficients of both images. Finally, RR image quality assessment (IQA) is performed by comparing the sensitivity coefficients of both images.

Parametric and Non-parametric Models of Linear Prediction Error for Color Texture Segmentation

Abstract: This paper presents a comparison of parametric and non-parametric models of multichannel linear prediction error for supervised color texture segmentation. Information of both luminance and chrominance spatial variation feature cues are used to characterize color textures. The method presented consists of two steps. In the first step, we estimate the linear prediction errors of color textures computed on small training sub images. Multichannel complex versions of linear prediction models are used as image observation models in RGB, IHLS and L*a*b* color spaces. In the second step, overall color distribution of the image is estimated from the multichannel prediction error sequences. Both parametric and non-parametric approaches are used for this purpose. A multivariate Gaussian probability approximation is used as the parametric law defining this color distribution. For non-parametric approximation, we have used a multivariate version of k-nearest neighbor algorithm. Error rate, based on well classified pixels, for different linear prediction models using different color spaces are compared and discussed.

Comparison of subjective assessment protocols for digital cinema applications

Abstract: Quality assessment is becoming an important issue in the framework of image processing. This need is expressed by the fact that the quality threshold of end-users has been shifted up because of the large availability of high fidelity sensors at very affordable price. This observation has been made for different application domains such as printing, compression, transmission, and so on. Starting from this, it becomes very important to manufacturers and producers to provide products of high quality to attract the consumer. This high interest on quality means that tools to measure it have to be available. This work is dedicated to the comparison of subjective methodologies in the digital cinema framework. The main goal is to determine with a group of observers, which methodology is better for assessing digital cinema content and what is the annoyance level associated to each of them. Several configurations are tested side by side, Butterfly, one by one, Horizontal scroll, vertical scroll, Horizontal and vertical scroll.

A complete scheme for colour morphology with perceptual integration

Abstract: Mathematical morphology is a powerful tool for filtering, segmentation and texture analysis, extended to multivariate signal in the last years. The major limitations of applying it to colour image reside in the non-linear behavior of the Human Visual System to the perception of colour. So a direct extension of the multivariate approach to colour image is not appropriate and the existing approaches can not offer generic solutions from a perceptual point of view. To overcome this limit, we present a coherent solution for the addition/subtraction parts of the colour dilatation/erosion specification, which didn't limit the structural element to the flat ones. By combination of two perceptual colour spaces, we define a partial order, specified by a perceptual colour distance. By this way, we solve lot of problems induced by all methods based on bit mixing or lexicographical strategies. In addition, we define unic supremum and infimum in the colour space allowing classical developments for filtering or segmentation and colour texture analysis without colour artefacts. In this paper, we will discuss about the colour spaces and their specificities, then we present the possible colour ordering schemes for mathematical morphology. In a second time, we develop our specific approach, beginning by the discussion about an adapted colour space, following with the extrema extraction formulation in this adapted colour space, by distance computation. Then we propose the colour addition expression needed in the complete formulation of supremum and infimum. Finally, we show the first results in colour textured image filtering and we conclude with perspectives.

Annoyance Maximization for Digital Cinema Anti-piracy Applications

Abstract: Data security is a major issue for digital cinema industry. One common way to pirate a movie called "screening" is to use a camcorder of a good quality during the projection, to record the movie and then share it on the Internet. Different strategies have been explored for resolving the problem of securing digital cinema content, some are based on temporal effects, others on colorimetric aspects. . The main idea is to insert a mark on the projected data that is invisible to a "normal" human observer but visible on the recorded data allowing to impair the content. Starting from this concept, it is very important to find a way for maximizing annoyance in order to make the pirate copy useless. This paper deals with a strategy for defining insertion maps that increase the annoyance and determining which type of content (text, graphics) is most suitable. So, we developed a method that takes into account the specificities of images and their content to determine such a map. We then managed series of psychophysical tests with a group of normal observers in order to provide recommendations to anti-piracy technology developers to maximize the annoyance dependently on the content of images.

Still image coding using a wavelet-like transform

Abstract: In this paper, a new image coding scheme based on a wavelet-like transform derived from orthogonal polynomial basis is presented. From a set of bivariate orthogonal polynomial functions, we first obtain the 2D non-separable wavelet functions to propose a wavelet-like transform coding. The motivation behind using orthogonal polynomials is that they exhibit some properties related to the human visual system (HVS) [1]. After applying the proposed transformation, the transform coefficients are threshold coded using quantization and bit allocation as in JPEG baseline system. The performance of the proposed transform coding is reported. The proposed coding scheme is also compared with other transform coding methods such as JPEG, JPEG 2000 and JPEG-XR/HDPHOTO.

Détermination d'un espace couleur pertinent pour la caractérisation de textures couleur

Abstract: This paper presents a comparison of colour spaces including IHLS and L*a*b* for colour texture characterization. Colour information is used to build a two channel image that contains pure luminance values in one channel and complex chrominance values in the other channel. The power spectrum estimation is done using 2D multichannel linear prediction models. A spectral analysis using luminance and chrominance spectra shows that the IHLS colour space presents a more important interference between luminance and chrominance channels than the L*a*b* colour space. The spectra are used to characterize colour textures. Then classification has been carried out in each colour space. Individual as well as combined effect of information from luminance and chrominance structure cues has been used for classification. A better rate classification on the set of colour textures is obtained for L*a*b* colour space.