Abstract: System for processing images including a main neural network, preferably convolution-based (CNN), and at least one preprocessing neural network, preferably convolution-based, upstream of the main neural network, for carrying out before processing by the main neural network at least one parametric transformation f, differentiable with respect to its parameters, this transformation being applied to at least part of the pixels of the image and being of the form p?=f(V(p),?) where p is a processed pixel of the original image or of a decomposition of this image, p? the pixel of the transformed image or of its decomposition, V(p) is a neighborhood of the pixel p, and ? a vector of parameters, the preprocessing neural network having at least part of its learning which is performed simultaneously with that of the main neural network.

Abstract: A method for the surveillance of a place using a network of image sensors connected to a biometric recognition device so arranged as to retrieve biometric features of persons from images supplied by the sensors and to compare the biometric features retrieved from images provided by distinct sensors in order to detect therefrom the presence of the same person according to a score of proximity between the biometric features, with the method comprising the steps of determining positional information and temporal information representing a split time between the two images and checking consistency between the newly determined positional and temporal information and the previously stored positional and temporal information.

Abstract: A database stores a number N of biometric data representatives which correspond to a set of characteristics of said biometric data. Acquired biometric data is obtained. Then, transformed biometric data is obtained by transforming the acquired biometric data according to said set of characteristics. Next, N deviation values are obtained by applying a comparison between the transformed biometric data and the N representatives in the database. Finally, a vector representing the acquired biometric data is obtained, the representation vector having a number of components less than or equal to N, said components being determined in relation to said N deviation values.

Abstract: A database stores a number N of biometric data representatives which correspond to a set of characteristics of said biometric data. Acquired biometric data is obtained. Then, transformed biometric data is obtained by transforming the acquired biometric data according to said set of characteristics. Next, N deviation values are obtained by applying a comparison between the transformed biometric data and the N representatives in the database. Finally, a vector representing the acquired biometric data is obtained, the representation vector having a number of components less than or equal to N, said components being determined in relation to said N deviation values.