Abstract: The present disclosure relates to a method and device for evaluating a fit of visual equipment. In an embodiment, the method (105) includes receiving (110) an image(s) of a face of a user, identifying (115) a subset of eyeglasses from a database that satisfy a preliminary fit threshold, determining (120) an eyeglass rim plane of a candidate eyeglass, determining (125) an eyeglass pads plane of the candidate eyeglass, generating (130) at least one 2D profile of a nose of the user, generating (140) at least one 2D profile of a nasal section of a frame of the candidate eyeglass, virtually docking (150) the candidate eyeglass on the nose of the face of the user, calculating (170), when the virtually docked candidate eyeglass satisfies a secondary fit threshold, a final fit of the virtually docked candidate eyeglass, the final fit being defined by at least one of a comfort criterion and/or an aesthetic criterion.

Abstract: A method for determining, for a given person, an optical equipment among a set comprising a plurality of optical equipments. The method further includes collecting a plurality of N reference datasets associated to at least one corresponding reference person and collecting a given dataset associated to the given person. Each dataset is indicative of a relative ranking of at least two optical equipments forming a reference subset of the set of optical equipments. The method further includes, based on the given dataset, selecting, among the plurality of N reference datasets, a group of R reference datasets, and predicting at least one optical equipment for the given person among the plurality of optical equipments.

Abstract: A server includes processing circuitry configured to receive one or more images, the one or more images including one or more representations of people. Additionally, the processing circuitry is configured to apply a neural network to the one or more images, wherein the neural network classifies at least one aesthetic component of each image of the one or more images, an aesthetic component score being generated for each image in the one or more images. Further, the processing circuitry is configured to generate a user eyewear equipment profile for a user, the user being matched to a persona from a personae database, each persona in the personae database being linked to one or more persona eyewear equipment profiles, the one or more persona eyewear equipment profiles being based on the aesthetic component score, and select eyewear equipment for the user based on the generated user eyewear equipment profile.

Abstract: The present disclosure relates to determining visual equipment for a patient or user. In an embodiment, a machine learning-based approach considers the face of a user in context of a database of labeled faces and visual equipment, each of the labeled images reflected the aesthetic value of a proposed visual equipment relative to the face of the patient or user.

Abstract: A method implemented by computer means for determining at least one optical parameter of a lens of eyewear adapted for a person, the method comprising: —an image reception step, during which at least a first image and a second image are received, the first image comprising a front view of the face of the person with at least one part of an eye of the person being directly visible, and the second image comprising a front view of the face of the person with said part of the eye of the person being visible through at least part of the lens, and —an optical parameter determination step, during which at least one optical parameter of the lens is determined based on a comparison between said part on the first and the second image.

Abstract: A server includes processing circuitry configured to receive one or more images, the one or more images including one or more representations of people. Additionally, the processing circuitry is configured to apply a neural network to the one or more images, wherein the neural network classifies at least one aesthetic component of each image of the one or more images, an aesthetic component score being generated for each image in the one or more images. Further, the processing circuitry is configured to generate a user eyewear equipment profile for a user, the user being matched to a persona from a personae database, each persona in the personae database being linked to one or more persona eyewear equipment profiles, the one or more persona eyewear equipment profiles being based on the aesthetic component score, and select eyewear equipment for the user based on the generated user eyewear equipment profile.

Abstract: A method implemented by computer means for determining at least one optical parameter of a lens of eyewear adapted for a person, the method comprising: —an image reception step, during which at least a first image and a second image are received, the first image comprising a front view of the face of the person with at least one part of an eye of the person being directly visible, and the second image comprising a front view of the face of the person with said part of the eye of the person being visible through at least part of the lens, and —an optical parameter determination step, during which at least one optical parameter of the lens is determined based on a comparison between said part on the first and the second image.