Abstract: A method for training a system for automatically detecting a defect of a blade of a turbomachine including a platform intended to receive a blade, at least one image-acquiring device, at least one light source the luminous intensity of which may vary, at least one moving device configured to move the platform with respect to the at least one image-acquiring device or to move the at least one image-acquiring device with respect to the platform, and a processing unit configured to receive acquired images and associate them with the items of information relating to the luminous intensity of the at least one light source and to the relative position of the platform with respect to the at least one image-acquiring device during the image acquisition.

Abstract: A method for automatic quality inspection of an aeronautical part, includes detecting faults on an image of the aeronautical part using a trained artificial neural network; training an auto-encoder on a database, by projecting each image of the database onto a small mathematical space in which the images follow a predefined probability law; for each image of the database, calculating a plurality of metrics; supervised training of a classifier from the calculated metrics; detecting faults or anomalies in the image of the aeronautical part using the auto-encoder and the classifier.

Abstract: An x-ray tomographic method for reconstructing an object, includes, on the basis of a plurality of images, each image in the plurality of images corresponding to a projection of the object, reconstructing the object using an iterative reconstruction method so as to produce a plurality of reconstructions x(m) of the object.

Abstract: A method for training a system for automatically detecting a defect of a blade of a turbomachine including a platform intended to receive a blade, at least one image-acquiring device, at least one light source the luminous intensity of which may vary, at least one moving device configured to move the platform with respect to the at least one image-acquiring device or to move the at least one image-acquiring device with respect to the platform, and a processing unit configured to receive acquired images and associate them with the items of information relating to the luminous intensity of the at least one light source and to the relative position of the platform with respect to the at least one image-acquiring device during the image acquisition.

Abstract: A riveting method that includes riveting a first aircraft part to a second aircraft part. The method includes capturing a plenoptic image of the rivet and at least one of the first part and the second part in the vicinity of the rivet, by a plenoptic imaging device secured to a riveting head, after riveting the first part to the second part. The method includes detecting the positioning and the surface condition of the rivet, from the plenoptic image captured by the imaging device.

Abstract: The invention relates to a method for the non-destructive inspection of an aeronautical part, by means of acquiring stereoscopic images and determining a three-dimensional model of the part, characterised in that it is used to extinguish one or more portions of the lighting of the part, and subsequently acquire a stereoscopic image of the surface by each of the sensors, these steps being performed by projecting a light on the surface by means of at least two projectors positioned in different locations.

Abstract: The invention relates to a method for the non-destructive inspection of an aeronautical part, by means of acquiring stereoscopic images and determining a three-dimensional model of the part, characterised in that it is used to extinguish one or more portions of the lighting of the part, and subsequently acquire a stereoscopic image of the surface by each of the sensors, these steps being performed by projecting a light on the surface by means of at least two projectors positioned in different locations.

Abstract: A riveting method that includes riveting a first aircraft part to a second aircraft part. The method includes capturing a plenoptic image of the rivet and at least one of the first part and the second part in the vicinity of the rivet, by a plenoptic imaging device secured to a riveting head, after riveting the first part to the second part. The method includes detecting the positioning and the surface condition of the rivet, from the plenoptic image captured by the imaging device.

Abstract: A plenoptic camera including an optical system receiving light issuing from an object field in which there is an object space intended to be processed via the camera. A matrix photosensitive sensor is composed of pixels arranged in rows and columns and such that each pixel receives the light of a single light ray via the system. The light rays, each associated with their pixel, form intersections in the object space, and the optics are configured so as to minimize the greatest distance between any point of the object space and the closest of the intersections of these light rays. Optical elements are aligned and arranged in rows and columns parallel respectively to the rows and columns of the matrix sensor, forming the intersections in the object field, the distances separating the rows and/or columns being irregular.

Abstract: The invention relates to a device for acquisition of images for a biometric system, which includes an optical assembly and at least one imager for acquisition of an image of an object to be analysed presented in front of the assembly at a non-determined distance from the latter. The assembly includes at least one diaphragm with a coded aperture. The optical assembly allows acquisition by the sensor(s) of an image of the object capable of being exploited to deduce therefrom the searched biometric information, and of an image of the object acquired via the coded aperture of the diaphragm. The device also includes a processing unit to determine the distance of the object to be analysed as a function of the image of the object acquired via the coded aperture of the diaphragm.

Abstract: A system for acquiring an image of veins of a finger includes a camera designed to acquire an image of said finger when it is passed in front of it, a lighting device designed to illuminate said finger and a control unit for controlling the illumination intensity of said lighting device. Also, at least one system measures the transmission power of said finger upstream of the camera with respect to the passage of said finger towards said camera, said control unit being designed to control the illumination intensity of said lighting device according to the transmission power measured by said measuring system. Additionally, a method for acquiring images of veins of a finger is provided.

Abstract: The invention relates to a device and to a method for validating whether an object is an element (5) of the human body, comprising at least the following steps: illuminating with at least one first light source (1) and with at least one second light source (2) an object that it is desired to validate is or is not a human body element; acquiring an image with an image sensor (3), the pixels of said image being associated with at least two characteristic values of a first color component and of a second color component, respectively; implementing validating processing dependant on comparisons between the values of the second component of the pixels in a zone of interest of the image and values of the first component of said pixels; validating or not the authenticity of the object (5) depending on the result of the validating processing.

Abstract: A plenoptic camera including an optical system receiving light issuing from an object field in which there is an object space intended to be processed via the camera. A matrix photosensitive sensor is composed of pixels arranged in rows and columns and such that each pixel receives the light of a single light ray via the system. The light rays, each associated with their pixel, form intersections in the object space, and the optics are configured so as to minimize the greatest distance between any point of the object space and the closest of the intersections of these light rays. Optical elements are aligned and arranged in rows and columns parallel respectively to the rows and columns of the matrix sensor, forming the intersections in the object field, the distances separating the rows and/or columns being irregular.

Abstract: The invention relates to a method, for determining a distance between an object with respect to an imaging system, improving the reconstruction of images of objects imaged by an imaging system and improving the resolution of the images obtained.

Abstract: The invention relates to a device and to a method for validating whether an object is an element (5) of the human body, comprising at least the following steps: illuminating with at least one first light source (1) and with at least one second light source (2) an object that it is desired to validate is or is not a human body element; acquiring an image with an image sensor (3), the pixels of said image being associated with at least two characteristic values of a first colour component and of a second colour component, respectively; implementing validating processing dependant on comparisons between the values of the second component of the pixels in a zone of interest of the image and values of the first component of said pixels; validating or not the authenticity of the object (5) depending on the result of the validating processing.

Abstract: A method of detecting a venous network in a portion of a human body, the method comprising the steps of capturing an infrared image of said human body portion in order to reveal a venous network of said human body portion; analyzing contrast in the infrared image in order to determine contrast characteristics of the infrared image; and determining whether the human body portion is real on the basis of contrast characteristics determined in the infrared image and of contrast characteristics determined from reference human body portions. A method of biometric recognition with a prior stage of detecting whether a portion of a human body is real.

Abstract: A method for segmenting fingers may include: a capture step during which the acquisition device captures an image of the fingers and of the sight; a computing step during which the processing unit computes the unrolled phase image from the image of the thus captured; a derivation step during which, for each pixel of the phase image thus computed, the processing unit computes the derivative of the phase along the isointensity axis of the sight; a regionalisation step during which the processing unit associates each pixel where the derivative of the phase has been computed with a region grouping all the adjoining pixels step by step where the derivative of the phase has the same polarity; and a recognition step during which the location of each finger is recognised from the analysis of the regions thus determined.

Abstract: A device for capturing an image representing a print of a part of the body of a person, the capture device may include: a base layer; a reference electrode covering the base layer; electronic capsules fixed in the form of a matrix on the reference electrode, each electronic capsule consisting of a microcapsule filled with a liquid medium and particles with two different colors and opposite electrical charges; a support plate covering the electronic capsules and serving as a support for said part; a camera intended to take an image of the electronic capsules; and an active electrode intended to come into contact with said part and electrically connected to a voltage source delivering a non-zero electrical voltage.

Abstract: The invention concerns an antifraud device (100) for validating the use of a real part of a body as an imprint-bearing substrate (150) and comprising: a control unit (106), a sensor (102) intended to capture the image of an imprint carried by the substrate (150) placed on said sensor (102), a movement module (104) on which said sensor (102) is mounted and which is intended to move said sensor (102), an analysis module (108) intended to receive the data representing an image of an imprint captured before the movement of said sensor (102) and an image of an imprint (200) captured after the movement of said sensor (102) and to analyze them, and a decision-making module (110) intended to make a decision as to whether or not the substrate (150) is a real part of a body, from information transmitted by the analysis module (108).

Abstract: A system for acquiring an image of veins of a finger includes a camera designed to acquire an image of said finger when it is passed in front of it, a lighting device designed to illuminate said finger and a control unit for controlling the illumination intensity of said lighting device. Also, at least one system measures the transmission power of said finger upstream of the camera with respect to the passage of said finger towards said camera, said control unit being designed to control the illumination intensity of said lighting device according to the transmission power measured by said measuring system. Additionally, a method for acquiring images of veins of a finger is provided.