公开(公告)号：US20210294834A1

公开(公告)日：2021-09-23

申请号：US16821301

申请日：2020-03-17

申请人： ADOBE INC.

发明人： Long Mai ,  Michael Alcorn ,  Baldo Faieta ,  Vladimir Kim

IPC分类号： G06F16/53 ,  G06F16/56 ,  G06K9/62 ,  G06N3/08 ,  G06N20/10

摘要： Systems and methods for performing image search are described. An image search method may include generating a feature vector for each of a plurality of stored images using a machine learning model trained using a rotation loss term, receiving a search query comprising a search image with object having an orientation, generating a query feature vector for the search image using the machine learning model, wherein the query feature vector is based at least in part on the orientation, comparing the query feature vector to the feature vector for each of the plurality of stored images, and selecting at least one stored image of the plurality of stored images based on the comparison, wherein the at least one stored image comprises a similar orientation to the orientation of the object in the search image.

公开(公告)号：US11645328B2

公开(公告)日：2023-05-09

申请号：US16821301

申请日：2020-03-17

申请人： ADOBE INC.

发明人： Long Mai ,  Michael Alcorn ,  Baldo Faieta ,  Vladimir Kim

IPC分类号： G06F16/00 ,  G06F16/56 ,  G06F16/53 ,  G06N20/10 ,  G06N3/084 ,  G06F18/22 ,  G06F18/2113 ,  G06V10/25 ,  G06V10/764 ,  G06V10/82 ,  G06V20/30

CPC分类号： G06F16/56 ,  G06F16/53 ,  G06F18/2113 ,  G06F18/22 ,  G06N3/084 ,  G06N20/10 ,  G06V10/25 ,  G06V10/764 ,  G06V10/82 ,  G06V20/30

摘要： Systems and methods for performing image search are described. An image search method may include generating a feature vector for each of a plurality of stored images using a machine learning model trained using a rotation loss term, receiving a search query comprising a search image with object having an orientation, generating a query feature vector for the search image using the machine learning model, wherein the query feature vector is based at least in part on the orientation, comparing the query feature vector to the feature vector for each of the plurality of stored images, and selecting at least one stored image of the plurality of stored images based on the comparison, wherein the at least one stored image comprises a similar orientation to the orientation of the object in the search image.