公开(公告)号：US11232286B2

公开(公告)日：2022-01-25

申请号：US17038208

申请日：2020-09-30

Applicant: Huawei Technologies Co., Ltd. ,  Institute of Automation, Chinese Academy of Sciences

Inventor： Qiang Rao ,  Bing Yu ,  Bailan Feng ,  Yibo Hu ,  Xiang Wu ,  Ran He ,  Zhenan Sun

IPC: G06K9/00 ,  G06K9/62 ,  G06T5/00 ,  G06T9/00

Abstract: A method and an apparatus for generating a face rotation image are provided. The method includes: performing pose encoding on an obtained face image based on two or more landmarks in the face image, to obtain pose encoded images; obtaining a plurality of training images each including a face from a training data set, wherein presented rotation angles of the faces included in the plurality of training images are the same; performing pose encoding on a target face image based on two or more landmarks in the target face image in the foregoing similar manner, to obtain pose encoded images, wherein the target face image is obtained based on the plurality of training images; generating a to-be-input signal based on the face image and the foregoing two types of pose encoded images; and inputting the to-be-input signal into an face rotation image generative model to obtain a face rotation image.

公开(公告)号：US10685434B2

公开(公告)日：2020-06-16

申请号：US16068912

申请日：2016-03-30

Applicant: Institute of Automation, Chinese Academy of Sciences

Inventor： Kaiqi Huang ,  Tieniu Tan ,  Ran He ,  Yueying Kao

IPC: G06T7/00 ,  G06N7/00 ,  G06K9/00 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62 ,  H04N17/00

Abstract: The present application discloses a method for assessing aesthetic quality of a natural image based on multi-task deep learning. Said method includes: step 1: automatically learning aesthetic and semantic characteristics of the natural image based on multi-task deep learning; step 2: performing aesthetic categorization and semantic recognition to the results of automatic learning based on multi-task deep learning, thereby realizing assessment of aesthetic quality of the natural image. The present application uses semantic information to assist learning of expressions of aesthetic characteristics so as to assess aesthetic quality more effectively, besides, the present application designs various multi-task deep learning network structures so as to effectively use the aesthetic and semantic information for obtaining highly accurate image aesthetic categorization. The present application can be applied to many fields relating to image aesthetic quality assessment, including image retrieval, photography and album management, etc.