Abstract: A method of analysis of defects of a type from among a plurality of types of defects between two samples based on an image of each sample characteristic of a type of defect from among the plurality of types of defects includes: for each sample, creating a minimap including bins and representative of a type of defect whose resolution is less than the image of the sample, each bin of the minimap being associated with pixels of the image of the sample and having a score dependent on the pixels and representative of the quantity of a type of defects; determining the distance between each minimap representing the same type or types of defects, the distance between two minimaps being defined as the minimum distance between two minimaps by considering the following transformations: a rotation and/or a symmetry so that each distance between two minimaps is associated with a transformation.

Abstract: A photoluminescence measurement device may include: a sample holder; a detector configured to collect a photoluminescence signal; a processing unit configured to process a signal collected by the detector; and a support disposed facing a rear face of the sample holder, opposite to the front face, and on one face, called the main face, of which rests at least one radiation source for emitting light radiation illuminating the rear face and likely to be collected, by transparency of the sample holder with respect to the light radiation, by the detector.

Abstract: A generative adversarial network performs face anonymization. In a first step, an input image showing a face to be anonymized is received. Furthermore, an input vector with control data for face anonymization is received. The generative adversarial network then generates an output image in which the face is anonymized in accordance with the control data of the input vector.

Abstract: A method of analysis of defects of a type from among a plurality of types of defects between two samples based on an image of each sample characteristic of a type of defect from among the plurality of types of defects includes: for each sample, creating a minimap including bins and representative of a type of defect whose resolution is less than the image of the sample, each bin of the minimap being associated with pixels of the image of the sample and having a score dependent on the pixels and representative of the quantity of a type of defects; determining the distance between each minimap representing the same type or types of defects, the distance between two minimaps being defined as the minimum distance between two minimaps by considering the following transformations: a rotation and/or a symmetry so that each distance between two minimaps is associated with a transformation.