中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.021 seconds)

    SYSTEMS AND METHODS TO PROCESS IMAGES FOR SKIN ANALYSIS AND TO VISUALIZE SKIN ANALYSIS
    1.
    发明申请
    SYSTEMS AND METHODS TO PROCESS IMAGES FOR SKIN ANALYSIS AND TO VISUALIZE SKIN ANALYSIS 有权

    公开(公告)号：US20210012493A1

    公开(公告)日：2021-01-14

    申请号：US16996087

    申请日：2020-08-18

    Applicant: L'Oreal

    Inventor： Ruowei JIANG ,  Irina KEZELE ,  Zhi Yu ,  Sophie SEITE ,  Frederic FLAMENT ,  Parham AARABI

    IPC: G06T7/00 ,  G16H50/20 ,  G06Q30/06 ,  A61B5/00

    Abstract: Systems and methods process images to determine a skin condition severity analysis and to visualize a skin analysis such as using a deep neural network (e.g. a convolutional neural network) where a problem was formulated as a regression task with integer-only labels. Auxiliary classification tasks (for example, comprising gender and ethnicity predictions) are introduced to improve performance. Scoring and other image processing techniques may be used (e.g. in assoc. with the model) to visualize results such as highlighting the analyzed image. It is demonstrated that the visualization of results, which highlight skin condition affected areas, can also provide perspicuous explanations for the model. A plurality (k) of data augmentations may be made to a source image to yield k augmented images for processing. Activation masks (e.g. heatmaps) produced from processing the k augmented images are used to define a final map to visualize the skin analysis.

    Convolution neural network based landmark tracker
    3.
    发明授权
    Convolution neural network based landmark tracker 有权

    公开(公告)号：US12299568B2

    公开(公告)日：2025-05-13

    申请号：US17528294

    申请日：2021-11-17

    Applicant: L'Oreal

    Inventor： Tian Xing Li ,  Zhi Yu ,  Irina Kezele ,  Edmund Phung ,  Parham Aarabi

    IPC: G06T7/00 ,  G06N3/047 ,  G06N3/08 ,  G06N3/082 ,  G06T5/20 ,  G06T7/11 ,  G06T7/143 ,  G06T19/00 ,  G06V10/764 ,  G06V10/771 ,  G06V10/82 ,  G06V40/16

    Abstract: There are provided systems and methods for facial landmark detection using a convolutional neural network (CNN). The CNN comprises a first stage and a second stage where the first stage produces initial heat maps for the landmarks and initial respective locations for the landmarks. The second stage processes the heat maps and performs Region of Interest-based pooling while preserving feature alignment to produce cropped features. Finally, the second stage predicts from the cropped features a respective refinement location offset to each respective initial location. Combining each respective initial location with its respective refinement location offset provides a respective final coordinate (x,y) for each respective landmark in the image. Two-stage localization design helps to achieve fine-level alignment while remaining computationally efficient. The resulting architecture is both small enough in size and inference time to be suitable for real-time web applications such as product simulation and virtual reality.

    Convolution neural network based landmark tracker
    5.
    发明授权
    Convolution neural network based landmark tracker 有权

    公开(公告)号：US11227145B2

    公开(公告)日：2022-01-18

    申请号：US16854993

    申请日：2020-04-22

    Applicant: L'Oreal

    Inventor： Tian Xing Li ,  Zhi Yu ,  Irina Kezele ,  Edmund Phung ,  Parham Aarabi

    IPC: G06T7/00 ,  G06K9/00 ,  G06T7/143 ,  G06T7/11 ,  G06N3/04 ,  G06N3/08 ,  G06T5/20 ,  G06T19/00

    Abstract: There are provided systems and methods for facial landmark detection using a convolutional neural network (CNN). The CNN comprises a first stage and a second stage where the first stage produces initial heat maps for the landmarks and initial respective locations for the landmarks. The second stage processes the heat maps and performs Region of Interest-based pooling while preserving feature alignment to produce cropped features. Finally, the second stage predicts from the cropped features a respective refinement location offset to each respective initial location. Combining each respective initial location with its respective refinement location offset provides a respective final coordinate (x,y) for each respective landmark in the image. Two-stage localization design helps to achieve fine-level alignment while remaining computationally efficient. The resulting architecture is both small enough in size and inference time to be suitable for real-time web applications such as product simulation and virtual reality.

    CONVOLUTION NEURAL NETWORK BASED LANDMARK TRACKER
    6.
    发明申请
    CONVOLUTION NEURAL NETWORK BASED LANDMARK TRACKER 审中-公开

    公开(公告)号：US20200342209A1

    公开(公告)日：2020-10-29

    申请号：US16854993

    申请日：2020-04-22

    Applicant: L'Oreal

    Inventor： Tian Xing LI ,  Zhi Yu ,  Irina Kezele ,  Edmund Phung ,  Parham Aarabi

    IPC: G06K9/00 ,  G06T7/11 ,  G06T7/143 ,  G06T5/20 ,  G06T19/00 ,  G06N3/04 ,  G06N3/08

    Abstract: There are provided systems and methods for facial landmark detection using a convolutional neural network (CNN). The CNN comprises a first stage and a second stage where the first stage produces initial heat maps for the landmarks and initial respective locations for the landmarks. The second stage processes the heat maps and performs Region of Interest-based pooling while preserving feature alignment to produce cropped features. Finally, the second stage predicts from the cropped features a respective refinement location offset to each respective initial location. Combining each respective initial location with its respective refinement location offset provides a respective final coordinate (x,y) for each respective landmark in the image. Two-stage localization design helps to achieve fine-level alignment while remaining computationally efficient. The resulting architecture is both small enough in size and inference time to be suitable for real-time web applications such as product simulation and virtual reality.

    Lightweight real-time facial alignment network model selection process
    7.
    发明授权
    Lightweight real-time facial alignment network model selection process 有权

    公开(公告)号：US12272110B2

    公开(公告)日：2025-04-08

    申请号：US17685691

    申请日：2022-03-03

    Applicant: L'OREAL

    Inventor： Zihao Chen ,  Zhi Yu ,  Parham Aarabi

    IPC: G06V10/20 ,  G06Q30/0601 ,  G06V10/24 ,  G06V10/70 ,  G06V10/776 ,  G06V10/82 ,  G06V40/16

    Abstract: With Convolutional Neural Networks (CNN), facial alignment networks (FAN) have achieved significant accuracy on a wide range of public datasets, which comes along with larger model size and expensive computation costs, making it infeasible to adapt them to real-time applications on edge devices. There is provided a model compression approach on FAN using One-Shot Neural Architecture Search to overcome this problem while preserving performance criteria. Methods and devices provide efficient training and searching (on a single GPU), and resultant models can deploy to run real-time in browser-based applications on edge devices including tablets and smartphones. The compressed models provide comparable cutting-edge accuracy, while having a 30 times smaller model size and can run 40.7 ms per frame in a popular browser on a popular smartphone and OS.

    LIGHTWEIGHT REAL-TIME FACIAL ALIGNMENT WITH ONE-SHOT NEURAL ARCHITECTURE SEARCH
    9.
    发明申请
    LIGHTWEIGHT REAL-TIME FACIAL ALIGNMENT WITH ONE-SHOT NEURAL ARCHITECTURE SEARCH 有权

    公开(公告)号：US20220284688A1

    公开(公告)日：2022-09-08

    申请号：US17685691

    申请日：2022-03-03

    Applicant: L'OREAL

    Inventor： Zihao CHEN ,  Zhi Yu ,  Parham Aarabi

    IPC: G06V10/24 ,  G06V10/82 ,  G06V10/70 ,  G06V10/776 ,  G06V40/16 ,  G06Q30/06

    Abstract: With Convolutional Neural Networks (CNN), facial alignment networks (FAN) have achieved significant accuracy on a wide range of public datasets, which comes along with larger model size and expensive computation costs, making it infeasible to adapt them to real-time applications on edge devices. There is provided a model compression approach on FAN using One-Shot Neural Architecture Search to overcome this problem while preserving performance criteria. Methods and devices provide efficient training and searching (on a single GPU), and resultant models can deploy to run real-time in browser-based applications on edge devices including tablets and smartphones. The compressed models provide comparable cutting-edge accuracy, while having a 30 times smaller model size and can run 40.7 ms per frame in a popular browser on a popular smartphone and OS.

Patent Agency Ranking