利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

7 条记录 (耗时 0.013 秒)

    SYSTEM IMPROVEMENT FOR DEEP NEURAL NETWORKS
    2.
    发明申请
    SYSTEM IMPROVEMENT FOR DEEP NEURAL NETWORKS 有权

    公开(公告)号：US20210089831A1

    公开(公告)日：2021-03-25

    申请号：US16816893

    申请日：2020-03-12

    申请人： FotoNation Limited

    发明人： Alexandru MALAESCU ,  Adrian Dorin CAPATA ,  Mihai CIUC ,  Alina SULTANA ,  Dan FILIP ,  Liviu-Cristian DUTU

    IPC分类号： G06K9/62 ,  G06N3/04 ,  G06N3/08

    摘要： The technology relates to tuning a data translation block (DTB) including a generator model and a discriminator model. One or more processors may be configured to receive training data including an image in a second domain. The image in the second domain may be transformed into a first domain with a generator model. The transformed image may be processed to determine one or more outputs with one or more deep neural networks (DNNs) trained to process data in the first domain. An original objective function for the DTB may be updated based on the one or more outputs. The generator and discriminator models may be trained to satisfy the updated objective function.

    Facial features tracker with advanced training for natural rendering of human faces in real-time
    3.
    发明申请
    Facial features tracker with advanced training for natural rendering of human faces in real-time 审中-公开

    公开(公告)号：US20190279393A1

    公开(公告)日：2019-09-12

    申请号：US15912946

    申请日：2018-03-06

    申请人： FotoNation Limited

    发明人： Mihai CIUC ,  Stefan PETRESCU ,  Emanuela HALLER ,  Florin OPREA ,  Alexandru NICOLAESCU ,  Florin NANU ,  Iulian PALADE

    IPC分类号： G06T7/73 ,  G06K9/00 ,  G06T13/40

    摘要： Tracking units for facial features with advanced training for natural rendering of human faces in real-time are provided. An example device receives a video stream, and upon detecting a visual face, selects a 3D model from a comprehensive set of head orientation classes. The device determines modifications to the selected 3D model to describe the face, then projects a 2D model of tracking points of facial features based on the 3D model, and controls, actuates, or animates hardware based on the facial features tracking points. The device can switch among an example comprehensive set of 35 different head orientation classes for each video frame, based on suggestions computed from a previous video frame or from yaw and pitch angles of the visual head orientation. Each class of the comprehensive set is trained separately based on a respective collection of automatically marked images for that head orientation class.

    FACIAL FEATURES TRACKER WITH ADVANCED TRAINING FOR NATURAL RENDERING OF HUMAN FACES IN REAL-TIME
    4.
    发明申请
    FACIAL FEATURES TRACKER WITH ADVANCED TRAINING FOR NATURAL RENDERING OF HUMAN FACES IN REAL-TIME 审中-公开

    公开(公告)号：US20200334853A1

    公开(公告)日：2020-10-22

    申请号：US16921723

    申请日：2020-07-06

    申请人： FotoNation Limited

    发明人： Mihai CIUC ,  Stefan PETRESCU ,  Emanuela HALLER ,  Florin OPREA ,  Alexandru NICOLAESCU ,  Florin NANU ,  Iulian PALADE

    IPC分类号： G06T7/73 ,  G06T13/40 ,  G06K9/00

    摘要： Tracking units for facial features with advanced training for natural rendering of human faces in real-time are provided. An example device receives a video stream, and upon detecting a visual face, selects a 3D model from a comprehensive set of head orientation classes. The device determines modifications to the selected 3D model to describe the face, then projects a 2D model of tracking points of facial features based on the 3D model, and controls, actuates, or animates hardware based on the facial features tracking points. The device can switch among an example comprehensive set of 35 different head orientation classes for each video frame, based on suggestions computed from a previous video frame or from yaw and pitch angles of the visual head orientation. Each class of the comprehensive set is trained separately based on a respective collection of automatically marked images for that head orientation class.

    Partial face detector red-eye filter method and apparatus
    5.
    发明申请
    Partial face detector red-eye filter method and apparatus 审中-公开
    部分面部检测器红眼滤波器的方法和装置

    公开(公告)号：US20170070649A1

    公开(公告)日：2017-03-09

    申请号：US15232538

    申请日：2016-08-09

    申请人： FotoNation Limited

    发明人： Florin NANU ,  Eran STEINBERG ,  Stefan PETRESCU ,  Mihnea GANGEA ,  Adrian CAPATA ,  Mihai CIUC ,  Adrian ZAMFIR ,  Peter CORCORAN ,  Alexei POSOSIN ,  Petronel BIGIOI ,  Alexandru DRIMBAREAN

    IPC分类号： H04N1/62 ,  G06K9/46 ,  G06K9/00 ,  G06T7/40 ,  G06T5/00

    CPC分类号： H04N1/624 ,  G06K9/00248 ,  G06K9/0061 ,  G06K9/4614 ,  G06T5/005 ,  G06T7/90 ,  G06T2207/30216 ,  H04N1/62 ,  H04N5/2354

    摘要： A digital camera has an integral flash and stores and displays a digital image. Under certain conditions, a flash photograph taken with the camera may result in a red-eye phenomenon due to a reflection within an eye of a subject of the photograph. A digital apparatus has a red-eye filter which analyzes at least one partial face region identified within the digital image for the red-eye phenomenon and modifies the image to eliminate the red-eye phenomenon by changing the red area to black. The modification of the image is enabled when a photograph is taken under conditions indicative of the red-eye phenomenon. The modification is subject to anti-falsing analysis which further examines the area around the red-eye area for indicia of the eye of the subject. The detection and correction can be optimized for performance and quality by operating on subsample versions of the image when appropriate.

    摘要翻译： 数码相机具有整体闪光灯，并存储和显示数字图像。 在某些条件下，用相机拍摄的闪光照片可能会由于照片中的对象的眼睛内的反射而导致红眼现象。 数字设备具有红眼滤光器，其分析在数字图像中识别的至少一个部分面部区域用于红眼现象，并通过将红色区域改变为黑色来修改图像以消除红眼现象。 当在指示红眼现象的条件下拍摄照片时，能够进行图像的修改。 该修改受到反假冒分析的限制，该分析进一步检查红眼区域周围区域的标记对象的眼睛。 通过在适当的情况下对图像的子样本版本进行操作，可以对性能和质量进行优化。

    METHODS AND SYSTEMS TO PREDICT ACTIVITY IN A SEQUENCE OF IMAGES
    6.
    发明申请
    METHODS AND SYSTEMS TO PREDICT ACTIVITY IN A SEQUENCE OF IMAGES 有权

    公开(公告)号：US20220019776A1

    公开(公告)日：2022-01-20

    申请号：US16929051

    申请日：2020-07-14

    申请人： FotoNation Limited

    发明人： Alexandru MALAESCU ,  Dan FILIP ,  Mihai CIUC ,  Liviu-Cristian DUTU ,  Madalin DUMITRU-GUZU

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06T7/00

    摘要： A method to determine activity in a sequence of successively acquired images of a scene, comprises: acquiring the sequence of images; for each image in the sequence of images, forming a feature block of features extracted from the image and determining image specific information including a weighting for the image; normalizing the determined weightings to form a normalized weighting for each image in the sequence of images; for each image in the sequence of images, combining the associated normalized weighting and associated feature block to form a weighted feature block; passing a combination of the weighted feature blocks through a predictive module to determine an activity in the sequence of images; and outputting a result comprising the determined activity in the sequence of images.