Abstract The evolution of the web in the last decades has created the need for new requirements towards intelligent information retrieval capabilities and advanced user interfaces. Nowadays, effective retrieval and usage of multimedia resources have to deal with the issues of creating efficient indexes, developing retrieval tools and improving user oriented visualization interfaces. To that end we put forward an integrated... The evolution of the web in the last decades has created the need for new requirements towards intelligent information retrieval capabilities and advanced user interfaces. Nowadays, effective retrieval and usage of multimedia resources have to deal with the issues of creating efficient indexes, developing retrieval tools and improving user oriented visualization interfaces. To that end we put forward an integrated framework named CALIMERA. The framework is based on a High-level modEL for cOnference (HELO) and aims at enhancing the information management, retrieval and visualization of recorded talks of scientific conferences. This paper presents the conference model and its uses within the framework: performing high level annotation of scientific talk recordings, offering granular search facilities and complex queries, and enhancing the knowledge visualization of the recordings. As a proof-of-concept we present the prototypes that have been implemented. Read More Read Less

Abstract The Mojette transform is a tomographic reconstruction method based on a discrete and finite interpretation of the Radon theorem. Since the Mojette acquisition follows the discrete image geometry, this method resolves the wellknown irregular sampling problem. A specific algorithm called Corner Based Inversion (CBI) is proposed to reconstruct without any error an image from its projections even if the angular... The Mojette transform is a tomographic reconstruction method based on a discrete and finite interpretation of the Radon theorem. Since the Mojette acquisition follows the discrete image geometry, this method resolves the wellknown irregular sampling problem. A specific algorithm called Corner Based Inversion (CBI) is proposed to reconstruct without any error an image from its projections even if the angular coverage is not sufficient (missing wedge). However, this reconstruction is noise sensitive and reconstruction from corrupted data fails. In this paper, we develop new noise robust CBI algorithms and we apply them both on discrete Mojette acquisitions and on usual Radon acquisitions. Reconstruction results are discussed to highlight the efficiency of these algorithms for usual tomography and perspectives are proposed to reduce the missing wedge effect. Read More Read Less

Abstract We propose in this paper an automated colorization of segmented images based on a color harmony rule defined by Itten called the contrast of proportion. Artists create an image drawing a sketch and filling its regions following harmony rules. The most significant regions are generally filled first because of their meaning. Then the other regions are filled depending on the... We propose in this paper an automated colorization of segmented images based on a color harmony rule defined by Itten called the contrast of proportion. Artists create an image drawing a sketch and filling its regions following harmony rules. The most significant regions are generally filled first because of their meaning. Then the other regions are filled depending on the previous colors. Our model is able to process images composed of totally blank or partially filled regions. The user defines sectors representing colors on the chromatic hue wheel and may redefine each color proportion. Then a set of colors is selected to compute the desired harmony. To proportionally colorize an image, already existing colors can be taken into account or the harmony can be applied only to blank regions. Each region is filled with only one color and cannot be divided. Thus, exact proportion contrast colorization of segmented images is a difficult algorithmic problem. In order to solve this problem we use different strategies and propose different methods to fill the regions. If they exist, exact solutions are proposed, otherwise three different approximation methods are used to determine combinations of colors-regions close to the defined proportions. Once the image is processed, the user can adapt hue (in the chosen sector), saturation and value of each region to enhance the result. Our results show that our model is flexible and well designed to help artists, illustrators, comics creators or any other user to automatically colorize (partially or totally) their images. Read More Read Less

Abstract This paper is an extension of a previous work by the same authors [1] that proposed and evaluated an automatic method to guide automatic portrait cropping for different aspect ratios. The development of automatic methods for image cropping in general are motivated by the large variety of aspect ratios used for both image rendering (e.g. print media, TV, cinema screens... This paper is an extension of a previous work by the same authors [1] that proposed and evaluated an automatic method to guide automatic portrait cropping for different aspect ratios. The development of automatic methods for image cropping in general are motivated by the large variety of aspect ratios used for both image rendering (e.g. print media, TV, cinema screens etc.) and image acquisition devices (e.g. still and video cameras, scanners etc.). In order to maintain the image’s original aspect ratio when adjusting for a different media, some level of cropping may be required, but the Automatic Zoom & Crop method (AZ&C) may not produce satisfactory results regarding image contents. Our method analyses images and estimates the relevant content areas, avoiding distortions and main subject chopping. The analysis is performed by four feature extractors, each producing a grayscale image which indicates relevant image areas. The outputs of these extractors are then combined by means of a Genetic Algorithm (GA) optimization. Experiments involving a subjective evaluation of a set of automatically cropped images have shown that 77% of the 35 participants considered images adjusted by the Multi Saliency Cropping Method (MSCM) better or similar than the outputs of the AZ&C method. In order to further investigate the combination of the feature extractors in the MSCM method, an extended evaluation has been performed, which involved the use of a database of 100 images for ranking method variations using combined and isolated features in addition to the AZ&C method. The results have shown that in 80% of the participants opinions the MSCM method is considered equal or superior to the variations using isolated features and the AZ&C method. Read More Read Less

Abstract In this paper, we describe a new optimization method which we call Multiple Birth and Cut (MBC). It combines the recently developed Multiple Birth and Death (MBD) algorithm and the Graph-Cut algorithm. MBD and MBC optimization methods are applied to energy minimization of an object based model, the marked point process. We compare the MBC to the MBD showing their... In this paper, we describe a new optimization method which we call Multiple Birth and Cut (MBC). It combines the recently developed Multiple Birth and Death (MBD) algorithm and the Graph-Cut algorithm. MBD and MBC optimization methods are applied to energy minimization of an object based model, the marked point process. We compare the MBC to the MBD showing their respective advantages and drawbacks, where the most important advantage of the MBC is the reduction of number of parameters. We demonstrate that by proposing good candidates throughout the selection phase in the birth step, the speed of convergence is increased. In this selection phase, the best candidates are chosen from object sets by a belief propagation algorithm. We validate our algorithm on the flamingo counting problem in a colony and demonstrate that our algorithm outperforms the MBD algorithm. Read More Read Less

Abstract This paper firstly introduces a wavelet-based segmentation for three-dimensional (3D) Semi-Regular (SR) meshes, as a pre-processing step, in a region-independent progressive coding algorithm. The proposed segmentation process aims at producing homogeneous regions with respect to their frequency amplitudes on the mesh surface, in other words: patches with different degrees of roughness. We have then studied the behavior of the wavelets,... This paper firstly introduces a wavelet-based segmentation for three-dimensional (3D) Semi-Regular (SR) meshes, as a pre-processing step, in a region-independent progressive coding algorithm. The proposed segmentation process aims at producing homogeneous regions with respect to their frequency amplitudes on the mesh surface, in other words: patches with different degrees of roughness. We have then studied the behavior of the wavelets, obtained during the independent coding of each region, especially close to the patch boundaries. The main contribution of this paper consists in considering three different possible wavelet decompositions, close to the region borders, and to study their influence during the patch-independent decoding and more particularly during the view-dependent reconstruction process. To our knowledge, no previous work has ever considered the influence of the non-refined parts of a mesh on the more detailed ones, in a view-dependent context. Among the three decompositions we have considered, we defined a new scheme and finally expose various experimentations to demonstrate that it behaves better than the other classical considerations. Read More Read Less