公开(公告)号：US20210166013A1

公开(公告)日：2021-06-03

申请号：US16701586

申请日：2019-12-03

Applicant: ADOBE INC.

Inventor： Christopher Alan Tensmeyer ,  Rajiv Jain ,  Curtis Michael Wigington ,  Brian Lynn Price ,  Brian Lafayette Davis

IPC: G06K9/00 ,  G06F3/0488 ,  G06N3/04 ,  G06N3/08 ,  G06K9/22

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

公开(公告)号：US11899927B2

公开(公告)日：2024-02-13

申请号：US17648718

申请日：2022-01-24

Applicant: Adobe Inc.

Inventor： Christopher Alan Tensmeyer ,  Rajiv Jain ,  Curtis Michael Wigington ,  Brian Lynn Price ,  Brian Lafayette Davis

IPC: G06K9/00 ,  G06F3/04883 ,  G06N3/08 ,  G06V30/32 ,  G06V30/228 ,  G06V30/226 ,  G06N3/045 ,  G06V10/82 ,  G06V10/44

CPC classification number: G06F3/04883 ,  G06N3/045 ,  G06N3/08 ,  G06V10/454 ,  G06V10/82 ,  G06V30/228 ,  G06V30/2264 ,  G06V30/2276 ,  G06V30/347

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

公开(公告)号：US11250252B2

公开(公告)日：2022-02-15

申请号：US16701586

申请日：2019-12-03

Applicant: ADOBE INC.

Inventor： Christopher Alan Tensmeyer ,  Rajiv Jain ,  Curtis Michael Wigington ,  Brian Lynn Price ,  Brian Lafayette Davis

IPC: G06K9/00 ,  G06F3/0488 ,  G06N3/04 ,  G06K9/22 ,  G06N3/08

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

公开(公告)号：US20220148326A1

公开(公告)日：2022-05-12

申请号：US17648718

申请日：2022-01-24

Applicant: Adobe Inc.

Inventor： Christopher Alan Tensmeyer ,  Rajiv Jain ,  Curtis Michael Wigington ,  Brian Lynn Price ,  Brian Lafayette Davis

IPC: G06V30/32 ,  G06F3/04883 ,  G06N3/04 ,  G06N3/08 ,  G06V30/228 ,  G06V30/226

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

公开(公告)号：US12229399B2

公开(公告)日：2025-02-18

申请号：US18420444

申请日：2024-01-23

Applicant: Adobe Inc.

Inventor： Christopher Alan Tensmeyer ,  Rajiv Jain ,  Curtis Michael Wigington ,  Brian Lynn Price ,  Brian Lafayette Davis

IPC: G06F3/048 ,  G06F3/04883 ,  G06N3/045 ,  G06N3/08 ,  G06V10/44 ,  G06V10/82 ,  G06V30/226 ,  G06V30/228 ,  G06V30/32

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

公开(公告)号：US20240168625A1

公开(公告)日：2024-05-23

申请号：US18420444

申请日：2024-01-23

Applicant: Adobe Inc.

Inventor： Christopher Alan Tensmeyer ,  Rajiv Jain ,  Curtis Michael Wigington ,  Brian Lynn Price ,  Brian Lafayette Davis

IPC: G06F3/04883 ,  G06N3/045 ,  G06N3/08 ,  G06V10/44 ,  G06V10/82 ,  G06V30/226 ,  G06V30/228 ,  G06V30/32

CPC classification number: G06F3/04883 ,  G06N3/045 ,  G06N3/08 ,  G06V10/454 ,  G06V10/82 ,  G06V30/2264 ,  G06V30/2276 ,  G06V30/228 ,  G06V30/347

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.