Idemia Identity & Security France

Dora Csillag

Maxime Thiebaut

Cécile Jourdas

Vincent Despiegel

Ashutosh Gokarn

The present invention relates to a method for processing a plurality of candidate annotations of a given instance of an image, each candidate annotation being defined as a closed shape matching the instance, characterized in that the method comprises performing, by a processing unit () of a server (), steps of:

Methods for processing a plurality of candidate annotations of a given instance of an image, and for learning parameters of a computational model

This invention concerns a method of learning parameters of a convolutional neural network (CNN) through data processing means () of at least one server (), for detecting items of interest visible in images, from at least one image learning database in which said items of interest, as well as characteristic geometric structures are already annotated, the CNN comprising an encoding layer for generating a representation vector of the detected items of interest, the method being characterized in that said representation vector comprises, for at least a first item of interest category to be detected, at least one descriptive value of at least a characteristic geometric structure of said first item of interest category. The present invention also relates to a process for detecting items of interest visible in an image and a method for associating items of interest visible in an image.

Parameter training method for a convolutional neural network and method for detecting items of interest visible in an image and for associating items of interest visible in an image

A parameter training method for a convolutional neural network, CNN, for detecting items of interest visible in images by a data processor of at least one server. The method is implemented based on a plurality of training image databases. The items of interest are already annotated, the CNN being a CNN common to the plurality of training image databases and having a common core and a plurality of encoding layers, each one specific to one of the plurality of training image databases. The method is also for detecting items of interest visible in an image.

Parameter training method for a convolutional neural network and method for detecting items of interest visible in an image

The present invention relates to a method for association of items of interest visible in a video consisting of a sequence of K images, characterized in that it comprises the implementation by data processing means of a terminal of steps of: association of each item of interest from a first category visible in a kimage of said video with an item of interest from a second category, different from the first category, visible in said kimage; calculation of an association cost for a plurality of pairs of an item of interest from the first category visible in at least one image of the video with an item of interest from the second category visible in at least one image of the video, depending on at least the counters of association of pairs of one item of interest from the first category with one item of interest from the second category; use of a combinatorial optimization algorithm depending on the calculated association costs so as to reassociate each item of interest from the first category visible in said kimage with an item of interest from the second category visible in said k; updating of the association counters.

Method for association of items of interest visible in a video

A method for processing a stream of video images to search for information therein, in particular detect predefined objects and/or a motion, comprising the steps of:

Growing community of inventors

Courbevoie, France

Dora Csillag