Abstract: In an image processing method to display a stereoscopic image on a target screen, a disparity information (200) is associated with the stereoscopic image and is adapted for the display of the stereoscopic image on an original screen, the size of the original screen being different from the size of the target screen, the stereoscopic image comprising a first image (20) and a second image (21). In order to optimise the disparity of the stereoscopic image, the method comprises selecting a part of said first image according to at least one property associated with the first image; calculating a target disparity information associated with the selected part of the image according to the viewing conditions associated with the target screen and the original disparity information associated with the selected part of the first image.

Abstract: Reframing is used to re-size an image or video content, e.g. for displaying video signals with a given aspect ratio on a display having a different aspect ratio. Window cropping parameters (position and size over time) are constrained in order to optimise the rate/distortion of the encoded output video signal. Initial reframing is improved by computing a saliency map representing a user attention map which considers the video coding context and by providing a macroblock coding efficiency cost map and then taking the saliency map or a combined saliency/coding cost map into account so that the coding cost for said reframed video signal is smaller than the coding cost for other candidate reframing windows' sizes and positions.

Abstract: A reframing application crops a sub-part of a video source, based on its content. The reframing application involves a visual attention model that produces a saliency map, and a dedicated reframing algorithm that extrapolates a cropping window based on that saliency map. After cropping, only the reframed portion of each video image remains visible. A method for processing images of a video sequence comprises steps of determining parameters of the video sequence, parameters of a previously decoded subsequence of the video sequence and user settings, determining a portion to be cropped according to the determined parameters, and cropping in a reframing step the determined portion for being displayed. An advantage of the invention is that an advanced automatic solution is provided for tuning automatically the reframing parameters, based on the content of a video.

Abstract: The invention proposes a method and a device of determining a saliency map for an image. The proposed method uses a processing device for executing the steps of: selecting one of at least two different predetermined weight sets each associated with the predetermined scene category by determining to which of the predetermined scene categories a scene depicted in the image belongs, each predetermined weight sets comprising weights for color dependent subbands, splitting the image into color dependent frequency subbands and orientation subbands by splitting the image into color components and applying wavelet transformation to each color component, determining early feature maps for the subbands by extracting visual features from the wavelet transforms by a center-surround mechanism based on a Difference of Gaussian, weighting the early feature maps using the selected weight set and fusing the weighted feature maps.

Abstract: The invention relates to an automatic detection method in a source image, of at least one area called a layout area comprising at least one layout, such as a logo and/or a score. According to the invention, the layout areas of a source image are detected using the salience of source image pixels. The detection is carried out in specific areas of the source image saliency map, usually in the areas corresponding to the corners of the image or to the bands in the upper part and lower part of the image. In these areas, two points are sought having maximum salience values and distant by at least p points from each other. These two points corresponding to the beginning and end of a layout area. The window bounding these two points then corresponds to a layout area.

Abstract: The invention proposes a method and a device of determining a saliency map for an image. The proposed method uses a processing device for executing the steps of: selecting one of at least two different predetermined weight sets each associated with the predetermined scene category by determining to which of the predetermined scene categories a scene depicted in the image belongs, each predetermined weight sets comprising weights for colour dependent subbands, splitting the image into colour dependent frequency subbands and orientation subbands by splitting the image into colour components and applying wavelet transformation to each colour component, determining early feature maps for the subbands by extracting visual features from the wavelet transforms by a center-surround mechanism based on a Difference of Gaussian, weighting the early feature maps using the selected weight set and fusing the weighted feature maps.

Abstract: The present invention relates to a method for image processing to generate, from a source image having a predefined width to height ratio, called initial ratio, and an information banner having predefined width to height ratio, called banner ratio, a final image having a width called final and a height called final and for which the width to height ratio, called final ratio, is different from the initial ratio, comprising the following steps: determine a ratio called useful according to the final ratio and the banner ratio, extract from the source image a part of the image having a width to height ratio equal to the useful ratio, and generate, from the part of the image extracted and the information banner, a final image comprising in juxtaposition an image representative of the extracted image part having a width to height ratio equal to the useful ratio and an image representative of the information banner having a width to height ratio equal to the banner ratio.

Abstract: The present invention pertains to a method for selecting a version of a document. The user inputs an identifier of a document at the level of his receiver connected to at least one communication network, and initiates a search request to receive versions of at least one part of this document. The receiver then receives a plurality of versions of the said document. Each version received is analysed by a plurality of evaluation modules so as to calculate an evaluation value for each version received according to a predetermined criterion. The receiver selects for each of the evaluation modules a version of the document having the best evaluation in respect of this criterion, and displays the identifiers of versions having the best evaluations according to each criterion. The user can then easily select the version for reproduction thereof which best meets a criterion. The invention also relates to a receiver implementing the said method.

Abstract: The present invention relates to a method for image processing to generate, from a source image having a predefined width to height ratio, called initial ratio, and an information banner having predefined width to height ratio, called banner ratio, a final image having a width called final and a height called final and for which the width to height ratio, called final ratio, is different from said initial ratio, comprising the following steps: determine a ratio called useful according to said final ratio and said banner ratio, extract from the source image a part of the image having a width to height ratio equal to the useful ratio, and generate, from the part of the image extracted and the information banner, a final image comprising in juxtaposition an image representative of said extracted image part having a width to height ratio equal to the useful ratio and an image representative of said information banner having a width to height ratio equal to the banner ratio.

Abstract: The invention relates to an automatic detection method in a source image, of at least one area called a layout area comprising at least one layout, such as a logo and/or a score. According to the invention, the layout areas of a source image are detected using the salience of source image pixels. The detection is carried out in specific areas of the source image saliency map, usually in the areas corresponding to the comers of the image or to the bands in the upper part and lower part of the image. In these areas, two points are sought having maximum salience values and distant by at least p points from each other. These two points corresponding to the beginning and end of a layout area. The window bounding these two points then corresponds to a layout area.