Abstract: A method for assessing the quality of a distorted version of a frame sequence includes the steps of determining a last spatial distortion by comparing a block of a last frame (I6) of the sequence with a corresponding block of the distorted version of the last frame, determining, in a last-but-one frame, a best-matching block matching said block of the last frame best, determining a last-but-one spatial distortion by comparing the determined best-matching block of the last-but-one frame with a corresponding block of the distorted version of the last-but-one frame, determining a spatio-temporal perceptual distortion value associated with said block using said determined distortions and using the determined spatio-temporal perceptual distortion value for assessing the quality.

Abstract: Detection of the salient points in an image enable the improvement of further steps such as coding or image indexing, watermarking, video quality estimation. The methods rely on the fact that a model is fully based on the human visual system (HVS) such as the computation of early visual features, and the methods compute a saliency map for video images taking into account motion and the velocity of the eye.

Abstract: A method of obtaining a saliency map from a plurality of saliency maps created from different visual quantities. Initially the saliency maps are normalized based on a theoretical maximum of each visual quantity. An intra-competition step selects the main saliency areas in each saliency map. An inter-competition step is then performed based on a sum of the intra-map competition with an inter-map redundancy term that is a function of the product of the intra-map competitions and of the probability of a site appearing on the saliency maps.

Abstract: A method for assessing image quality between a reference image and an impaired image is disclosed. The method comprises the steps of subband decomposition of the luminance component of the reference image into N subbands, called reference subbands and of the luminance component of the impaired image into N subbands, called impaired subbands; errors computation from the reference subbands and from the impaired subbands; and pooling the computed the errors. The subband decomposition is based on a wavelet transform adapted to decompose each of the luminance components into L levels of decomposition, with L a positive integer determined as a function of the image height and of the distance of visualization.

Abstract: The invention is a method for assessing image quality value of a distorted image with respect to a reference image. The method comprises the following steps: computing, for each pixel of the distorted image, at least one quality level with respect to the reference image; adding, for the distorted image, the quality levels associated to each pixel by weighting them by a weight depending on a perceptual interest of the pixel in order to get the image quality value, the weight being lower for a pixel of high perceptual interest.

Abstract: The invention concerns a device and a method for creating a saliency map of an image. It comprises the steps of: Projection of said image according to the luminance component and if said image is a color image, according to the luminance component and according to the chrominance components, Perceptual sub-bands decomposition of said components according to the visibility threshold of a human eye, Extraction of the salient elements of the sub-bands related to the luminance component, Contour enhancement of said salient elements in each sub-band related to the luminance component, Calculation of a saliency map from the contour enhancement, for each sub-band related to the luminance component. Creation of the saliency map as a function of the saliency maps obtained for each sub-band.

Abstract: A method for assessing image quality between a reference image and an impaired image is disclosed. The method comprises the steps of: subband decomposition of the luminance component of the reference image into N subbands, called reference subbands and of the luminance component of the impaired image into N subbands, called impaired subbands; errors computation from the reference subbands and from the impaired subbands; and pooling the computed the errors. According to the invention, the subband decomposition is based on a wavelet transform adapted to decompose each of the luminance components into L levels of decomposition, with L a positive integer determined as a function of the image height and of the distance of visualization.

Abstract: The invention is related to a method for video quality assessment. Said method comprises the steps of determining a last spatial distortion by comparing a block of a last frame (I6) of the sequence with a corresponding block of the distorted version of the last frame, determining, in a last-but-one frame, a best-matching block matching said block of the last frame best, determining a last-but-one spatial distortion by comparing the determined best-matching block of the last-but-one frame with a corresponding block of the distorted version of the last-but-one frame, determining a spatio-temporal perceptual distortion value associated with said block using said determined distortions and using the determined spatio-temporal perceptual distortion value for assessing the quality. The spatial distortion's temporal evolution improves video quality assessment.

Abstract: The invention relates to a method of obtaining a saliency map from a plurality of saliency maps created from different visual quantities, comprising - a step for normalizing said saliency maps based on the theoretical maximum of each visual quantity, -an intra-map competition step selecting the main saliency areas in each saliency map, -an inter-map competition step based on the sum of the intra-map competitions with an inter-map redundancy term that is a function of the product of the intra-map competitions and of the probability of a site appearing on said saliency maps.

Abstract: The invention is a method for assessing image quality value of a distorted image with respect to a reference image. The method comprises the following steps: computing, for each pixel of the distorted image, at least one quality level with respect to the reference image; adding, for the distorted image, the quality levels associated to each pixel by weighting them by a weight depending on a perceptual interest of the pixel in order to get the image quality value, the weight being lower for a pixel of high perceptual interest.

Abstract: The invention concerns a method for creating a saliency map of an image. It comprises the steps of an image comprising the step of hierarchical decomposition of the image into frequential sub-bands, According to the invention, the method comprises the steps of i. movement estimation between the current image and a preceding image calculated from the decomposition into frequential sub-bands, estimating a dominant movement for the image and a local movement for each pixel of the current image, ii. creation of a temporal saliency map obtained from the global and local movement estimation.

Abstract: The invention concerns a device and a method for creating a saliency map of an image. It comprises the steps of: Projection of said image according to the luminance component and if said image is a color image, according to the luminance component and according to the chrominance components, Perceptual sub-bands decomposition of said components according to the visibility threshold of a human eye, Extraction of the salient elements of the sub-bands related to the luminance component, Contour enhancement of said salient elements in each sub-band related to the luminance component, Calculation of a saliency map from the contour enhancement, for each sub-band related to the luminance component. Creation of the saliency map as a function of the saliency maps obtained for each sub-band.

Abstract: A process for detecting defects in a textured suface, particularly on a highway. The process consists in displacing with respect to the surface a camera presenting an inclination and in processing by processing systems the successive images taken by the camera. A mathematical processing is effected on sub-images, corresponding to the same spatial portion of the surface, taken at different consecutive instants.

Abstract: Device for controlling and regulating the spacing of parcels, packages or similar objects and, more particularly, of postal parcels, mounted at the outlet of a separation apparatus that includes a truncated cone-shaped rotating drum with its axis inclined towards the horizontal and having internal helical fins designed to deliver the packages one by one to the outlet of the drum. The device further includes a conveyor belt driven at constant speed and onto which the packages are tipped at the outlet of the drum, a barrier of detection cells, the beam of which extends in perpendicular to the line of travel of the conveyor in order to identify the moment of each package's passage into this beam and to measure, between two successive interruptions of the cells, the relative spacing of two consecutive packages intersecting, each in turn, the beam of the cells.

Abstract: Control device for a flow of objects in continuous file and, more particularly, of postal parcels or packages, prior to their introduction into a separator mechanism which imposes at its oulet a suitable spacing between one object and the next, which comprises a first conveyor belt on which the objects are disposed in bulk, this conveyor travelling at a variable linear speed (V1), a second conveyor belt, disposed following the first and driven at a similarly variable linear speed (V2), a photographic camera for the acquisition in real time of an image of the second conveyor and of the packages transported by it, presenting according to the length of the conveyor a given longitudinal dimension (L), a processing circuit for the image received from the camera in order to discern within this image the number of packages (Nc) which it contains, a computer for controlling the instantaneous speeds (V1 and V2) of the two conveyors during the transfer of the packages disposed on the second conveyor according to the di