公开(公告)号：US20220108445A1

公开(公告)日：2022-04-07

申请号：US17491623

申请日：2021-10-01

Applicant: L'Oreal

Inventor： Yuze ZHANG ,  Ruowei Jiang ,  Parham AARABI

IPC: G06T7/00 ,  A61B5/00

Abstract: Systems, methods and techniques provide for acne localization, counting and visualization. An image is processed using a trained model to identify objects. The model may be a deep learning (e.g. convolutional neural) network configured for object classification with a detection focus on small objects. The image may be a frontal or profile facial image, processed end to end. The model identifies and localizes different types of acne. Instances are counted and visualized such as by annotating the source image. An example annotation is an overlay identifying a type and location of each instance. Counts by acne type assist with scoring. A product and/or service may be recommended in response to the identification of the acne (e.g. the type, localization, counting and/or a score).

公开(公告)号：US20240249504A1

公开(公告)日：2024-07-25

申请号：US18627827

申请日：2024-04-05

Applicant: L'Oreal

Inventor： Zhi YU ,  Yuze ZHANG ,  Ruowei JIANG ,  Jeffrey HOUGHTON ,  Parham AARABI ,  Frederic Antoinin Raymond Serge FLAMENT

IPC: G06V10/764 ,  G06N3/04 ,  G06Q30/0601 ,  G06V10/82 ,  G06V40/16

CPC classification number: G06V10/764 ,  G06N3/04 ,  G06Q30/0631 ,  G06Q30/0643 ,  G06V10/82 ,  G06V40/162 ,  G06V40/168 ,  G06V40/171 ,  G06V40/172

Abstract: There is described a deep learning supervised regression based model including methods and systems for facial attribute prediction and use thereof. An example of use is an augmented and/or virtual reality interface to provide a modified image responsive to facial attribute predictions determined from the image. Facial effects matching facial attributes are selected to be applied in the interface.

公开(公告)号：US20220351416A1

公开(公告)日：2022-11-03

申请号：US17869942

申请日：2022-07-21

Applicant: L'Oreal

Inventor： Eric ELMOZNINO ,  Parham AARABI ,  Yuze ZHANG

IPC: G06T7/90 ,  G06N3/08 ,  G06Q30/06 ,  G06T11/00

Abstract: Provided are systems and methods to perform colour extraction from swatch images and to define new images using extracted colours. Source images may be classified using a deep learning net (e.g. a CNN) to indicate colour representation strength and drive colour extraction. A clustering classifier is trained to use feature vectors extracted by the net. Separately, pixel clustering is useful when extracting the colour. Cluster count can vary according to classification. In another manner, heuristics (with or without classification) are useful when extracting. Resultant clusters are evaluated against a set of (ordered) expected colours to determine a match. Instances of standardized swatch images may be defined from a template swatch image and respective extracted colours using image processing. The extracted colour may be presented in an augmented reality GUI such as a virtual try-on application and applied to a user image such as a selfie using image processing.

公开(公告)号：US20210406996A1

公开(公告)日：2021-12-30

申请号：US17361743

申请日：2021-06-29

Applicant: L'Oreal

Inventor： Zhi YU ,  Yuze ZHANG ,  Ruowei JIANG ,  Jeffrey HOUGHTON ,  Parham AARABI ,  Frederic FLAMENT

IPC: G06Q30/06 ,  G06N3/04 ,  G06K9/00 ,  G06K9/62

Abstract: There is described a deep learning supervised regression based model including methods and systems for facial attribute prediction and use thereof. An example of use is an augmented and/or virtual reality interface to provide a modified image responsive to facial attribute predictions determined from the image. Facial effects matching facial attributes are selected to be applied in the interface

公开(公告)号：US20200342630A1

公开(公告)日：2020-10-29

申请号：US16854975

申请日：2020-04-22

Applicant: L'Oreal

Inventor： Eric ELMOZNINO ,  Parham AARABI ,  Yuze ZHANG

IPC: G06T7/90 ,  G06T11/00 ,  G06Q30/06 ,  G06N3/08

Abstract: Provided are systems and methods to perform colour extraction from swatch images and to define new images using extracted colours. Source images may be classified using a deep learning net (e.g. a CNN) to indicate colour representation strength and drive colour extraction. A clustering classifier is trained to use feature vectors extracted by the net. Separately, pixel clustering is useful when extracting the colour. Cluster count can vary according to classification. In another manner, heuristics (with or without classification) are useful when extracting. Resultant clusters are evaluated against a set of (ordered) expected colours to determine a match. Instances of standardized swatch images may be defined from a template swatch image and respective extracted colours using image processing. The extracted colour may be presented in an augmented reality GUI such as a virtual try-on application and applied to a user image such as a selfie using image processing.