Abstract: The invention concerns a device and a method for colour correction of an input image.

Abstract: A method is disclosed for measuring similarity between images, comprising the performance of the following steps for each of the images: segmentation of the image into segments, classification of the segments as a function of their orientation to give classes, calculation of a histogram of the number of segments as a function of class, calculation of a histogram of the number of pixels belonging to the segments of one and the same class as a function of class, and comparing, for each image, the histograms calculated above to their respective histograms calculated for each of the rest of the images to give a measurement of similarity.

Abstract: The invention concerns a device and an automatic resetting method using electronic means intended for a geometric model of a scene over a picture of the scene including fixed references, the electronic means comparing the picture with model having been adjusted in perspective by homography for superimposition of the references. According to the invention, the electronic device calculates a fine homography function Hf for resetting into three phases: a first preliminary phase of determination of an average resetting homography consisting in determining an average homography function Hm applicable to the model with average adjustment over a sample of pictures of the scene taken previously, a second, rough resetting phase consisting after application of the average homography function Hm, to the model in determining a rough homography function Hg, and a third, fine resetting phase consisting after application of the rough homography function Hg to the model in determining the fine homography function Hf.

Abstract: The method is characterized in that it implements the following steps: random drawing of p candidates from the set of key images, calculation of a cost C for each candidate, selection of the candidate minimizing the cost C, determination of a subset from among the set of key images such that the key images forming the said subset have a distance from the candidate less than a threshold T, determination of a seed from among the key images of the subset such that it minimizes the cost function C for this subset, deletion of the key images of the subset to form a new set of key images for at least one new random draw and determination of a new seed according to the previous 5 steps. The field is that of the selection of shots of interest in a video sequence.

Abstract: The invention relates to a device and a method for segmenting objects in an image. The method comprises steps for: the approximate definition of a contour external to the object to be segmented, said contour including a plurality of so-called control points, the determination of a vicinity of candidate points in the vicinity of each control point, the determination of an energy associated with each candidate point in the vicinity of each control point, the convergence of each of the control points (Vi) towards the candidate point, which minimizes said energy, so providing an estimated contour of the object to be segmented. According to the invention, the energy associated with each candidate point includes a colour discrimination term.

Abstract: The method utilizing a graph-like structure is comprises the following iteration: calculation of the potential of node nm, merging of two nodes ni and nj, as a function of the distances between the attributes of the key images and as a function of the temporal distance of these key images, calculation of the potential of each edge connecting the merged node to another node of the graph previously connected to nodes ni or nj, merging of the two nodes and validation of the new graph if the energy of this graph is less than the energy of the graph before merging.

Abstract: The invention discloses a method of viewing audiovisual documents on a playback device, comprising a step for reading or receiving a document and a display step for viewing the images of this document on a screen. The method further comprises a step for reading or receiving an attribute associated with a time band of the document. A predetermined value of the attribute triggers on the device the enlargement of a part of the image on playback during said time band, because of which this image part occupies a larger area on screen.

Abstract: The method performs, for each image, the following steps: segmentation of the image, classification of the segments as a function of their orientation to give classes, calculation of a histogram of the number of segments as a function of class, calculation of a histogram of the number of pixels belonging to the segments of one and the same class as a function of class, comparison of the histograms of each image to give a measurement of similarity.

Abstract: The invention relates to a device and a process for detecting faces in a colour image. The process is such that it comprises the steps of: detection of the flesh coloured pixels in the image, segmentation of the image into regions of homogeneous colour, selection, among the regions of homogeneous colour, of the regions comprising a number of flesh coloured pixels greater than a first predetermined threshold, the regions selected being said to be flesh coloured regions. merging of the neighbouring flesh coloured regions until the merge cost attains a second predetermined threshold, the merge cost linearly weighting a merge cost relating to the shape of the regions and a merge cost relating to the colour of the regions, exclusion of false positives.

Abstract: A device and a method for measuring visual similarity between two images. One image (Q) being referred to as the model and one image (T) being referred to as the target, the method comprises a prior step (E2) of segmenting the images into regions (Qi, Ti), with each region there being associated at least one attribute (F) representative of at least one characteristic of the region. It furthermore comprises the steps of calculating (E3) the visual similarity between the pairs (Qi, Ti) of possible regions of the two images (Q, T), by taking into account the distance (D(Qi, Ti)) between the said attributes (F) of the regions (Qi, Ti) matched and the areas of the regions (Qi, Ti) matched; selecting (E4) a certain number of pairs (Qi, Ti) of regions whose similarity is greater than a first fixed threshold (?), calculating (E9) the global similarity between the two images, based on the pairs (Qi, Ti) of regions selected.