公开(公告)号：US10984295B2

公开(公告)日：2021-04-20

申请号：US16590121

申请日：2019-10-01

Applicant: Adobe Inc.

Inventor： Zhaowen Wang ,  Luoqi Liu ,  Hailin Jin

IPC: G06K9/68 ,  G06K9/00 ,  G06K9/66 ,  G06K9/46 ,  G06T3/40 ,  G06K9/52 ,  G06T7/60 ,  G06N3/04 ,  G06K9/62

Abstract: Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.

公开(公告)号：US10467508B2

公开(公告)日：2019-11-05

申请号：US15962514

申请日：2018-04-25

Applicant: Adobe Inc.

Inventor： Zhaowen Wang ,  Luoqi Liu ,  Hailin Jin

IPC: G06K9/68 ,  G06K9/00 ,  G06K9/66 ,  G06K9/46 ,  G06T3/40 ,  G06K9/52 ,  G06T7/60 ,  G06K9/62 ,  G06N3/04

Abstract: Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.

公开(公告)号：US10699166B2

公开(公告)日：2020-06-30

申请号：US15853120

申请日：2017-12-22

Applicant: Adobe Inc.

Inventor： Zhaowen Wang ,  Luoqi Liu ,  Hailin Jin

IPC: G06K9/62 ,  G06K9/66 ,  G06K9/46 ,  G06N3/04 ,  G06K9/68

Abstract: Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.

公开(公告)号：US20200034671A1

公开(公告)日：2020-01-30

申请号：US16590121

申请日：2019-10-01

Applicant: Adobe Inc.

Inventor： Zhaowen Wang ,  Luoqi Liu ,  Hailin Jin

IPC: G06K9/68 ,  G06K9/46 ,  G06N3/04 ,  G06K9/62 ,  G06K9/00 ,  G06K9/66 ,  G06T3/40 ,  G06K9/52 ,  G06T7/60

Abstract: Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.