IP Library Granted Patent US 12,499,547
Granted Patent B2
US 12,499,547 · App. 17/184,601 · Granted Dec 16, 2025

Image processing device, image processing method and storage medium for shortening processing of image processing

Inventors: Kazuyuki Itagaki (Tokyo, JP); Takashi Nagao (Kanagawa, JP)
Assignees: FUJIFILM Corporation; FUJIFILM Business Innovation Corp.
G06T7/11G06T5/00G06T2207/20021G06T2207/20072
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,499,547
App. No.
17/184,601
Granted
Dec 16, 2025
Kind
B2
Abstract

An image processing device configured to execute image processing, using respective objects of an object group in which objects configured to execute image processing are connected in a form of a directed acyclic graph, the image processing device including: a division section configured to divide image data into plural items of divisional image data; a control section configured to effect control to cause plural arithmetic devices to execute, in parallel, respective partial processing routines, each of the partial processing routines including image processing to be carried out on a corresponding item of the divisional image data that is stored in a predetermined storage area; and a notification section configured to, in a case in which an item of divisional image data that corresponds to a partial processing routine is stored in the storage area, notify the control section that the item of divisional image data has been stored.

Claims (42)

1 . An image processing device configured to execute image processing, using respective objects of an object group in which a plurality of objects configured to execute image processing are connected in a form of a directed acyclic graph, the image processing device comprising a processor configured to:

divide image data, which is an object of the image processing, into a plurality of items of divisional image data;

effect control to cause a plurality of arithmetic devices to execute, in parallel, respective partial processing routines, each of the partial processing routines comprising image processing to be carried out on a corresponding item of the divisional image data that is stored in a predetermined storage area; and

in a case in which an item of divisional image data that corresponds to a partial processing routine is stored in the storage area, notify that the item of divisional image data has been stored in the storage area,

wherein the processor is configured to control the plurality of arithmetic devices to start an execution of the image processing on the corresponding item of the divisional image data each time the corresponding item of the divisional image data has been stored in the storage area,

wherein the processor carries out the notification by storing, in a notification queue that is configured to be referenced processor, notification information that indicates that the item of divisional image data has been stored in the storage area.

2 . The image processing device of claim 1 , wherein, in a case in which there is no partial processing routine that is executable and the notification information is not stored in the notification queue, the processor transitions to a sleep state, and, in a case in which the notification information is stored in the notification queue during a state in which the processor has transitioned to the sleep state, the processor transitions to an active state and effects the control.

3 . The image processing device of claim 1 , wherein the processor effects the control by storing a partial processing routine that is executable, in a task queue that is configured to be referenced by the plurality of arithmetic devices.

4 . An image processing method executed by an image processing device comprising a processor configured to execute image processing using respective objects of an object group in which a plurality of objects configured to execute image processing are connected in a form of a directed acyclic graph, the image processing method comprising:

dividing image data, which is an object of the image processing, into a plurality of items of divisional image data;

effecting control to cause a plurality of arithmetic devices to execute, in parallel, respective partial processing routines, each of the partial processing routines comprising image processing to be carried out on a corresponding item of the divisional image data that is stored in a predetermined storage area; and

in a case in which an item of divisional image data that corresponds to a partial processing routine is stored in the storage area, notifying that the item of divisional image data has been stored in the storage area,

wherein the processor is configured to control the plurality of arithmetic devices to start an execution of the image processing on the corresponding item of the divisional image data each time the corresponding item of the divisional image data has been stored in the storage area,

wherein the notifying is performed by storing, in a notification queue that is configured to be referenced, notification information that indicates that the item of divisional image data has been stored in the storage area.

5 . The image processing method of claim 4 , wherein, in a case in which there is no partial processing routine that is executable and the notification information is not stored in the notification queue, the processor transitions to a sleep state, and, in a case in which the notification information is stored in the notification queue during a state in which the processor has transitioned to the sleep state, the processor transitions to an active state and effects the control.

6 . The image processing method of claim 4 , wherein the processor effects the control by storing a partial processing routine that is executable in a task queue that is configured to be referenced by the plurality of arithmetic devices.

7 . A non-transitory storage medium storing a program that causes a computer to execute image processing using respective objects of an object group in which a plurality of objects configured to execute image processing are connected in a form of a directed acyclic graph, the image processing comprising:

dividing image data, which is an object of the image processing, into a plurality of items of divisional image data;

effecting control to cause a plurality of arithmetic devices to execute, in parallel, respective partial processing routines, each of the partial processing routines comprising image processing to be carried out on a corresponding item of the divisional image data that is stored in a predetermined storage area; and

in a case in which an item of divisional image data that corresponds to a partial processing routine is stored in the storage area, notifying that the item of divisional image data has been stored in the storage area,

wherein the computer is configured to control the plurality of arithmetic devices to start an execution of the image processing on the corresponding item of the divisional image data each time the corresponding item of the divisional image data has been stored in the storage area,

wherein the notifying is performed by storing, in a notification queue that is configured to be referenced, notification information that indicates that the item of divisional image data has been stored in the storage area.

8 . The non-transitory storage medium of claim 7 , wherein, in a case in which there is no partial processing routine that is executable and the notification information is not stored in the notification queue, the computer transitions to a sleep state, and, in a case in which the notification information is stored in the notification queue during a state in which the computer has transitioned to the sleep state, the computer transitions to an active state and effects the control.

9 . The non-transitory storage medium of claim 7 , wherein the computer effects the control by storing a partial processing routine that is executable in a task queue that is configured to be referenced by the plurality of arithmetic devices.

10 . An image processing device configured to execute image processing, using respective objects of an object group in which a plurality of objects configured to execute image processing are connected in a form of a directed acyclic graph, the image processing device comprising a processor configured to:

divide image data, which is an object of the image processing, into a plurality of items of divisional image data;

effect control to cause a plurality of arithmetic devices to execute, in parallel, respective partial processing routines, each of the partial processing routines comprising image processing to be carried out on a corresponding item of the divisional image data that is stored in a predetermined storage area; and

in a case in which an item of divisional image data that corresponds to a partial processing routine is stored in the storage area, notify that the item of divisional image data has been stored in the storage area,

wherein the processor is configured to control the plurality of arithmetic devices to start an execution of the image processing on the corresponding item of the divisional image data each time the corresponding item of the divisional image data has been stored in the storage area,

wherein the processor carries out the notification by storing, in a notification queue that is configured to be referenced processor, notification information that indicates that the item of divisional image data has been stored in the storage area, and

in a case in which there is no partial processing routine that is executable and the notification information is not stored in the notification queue, the processor transitions to a sleep state, and, in a case in which the notification information is stored in the notification queue during a state in which the processor has transitioned to the sleep state, the processor transitions to an active state and effects the control.

11 . An image processing method executed by an image processing device comprising a processor configured to execute image processing using respective objects of an object group in which a plurality of objects configured to execute image processing are connected in a form of a directed acyclic graph, the image processing method comprising:

dividing image data, which is an object of the image processing, into a plurality of items of divisional image data;

effecting control to cause a plurality of arithmetic devices to execute, in parallel, respective partial processing routines, each of the partial processing routines comprising image processing to be carried out on a corresponding item of the divisional image data that is stored in a predetermined storage area; and

in a case in which an item of divisional image data that corresponds to a partial processing routine is stored in the storage area, notifying that the item of divisional image data has been stored in the storage area, wherein the processor is configured to control the plurality of arithmetic devices to start an execution of the image processing on the corresponding item of the divisional image data each time the corresponding item of the divisional image data has been stored in the storage area, wherein the notifying is performed by storing, in a notification queue that is configured to be referenced, notification information that indicates that the item of divisional image data has been stored in the storage area, and in a case in which there is no partial processing routine that is executable and the notification information is not stored in the notification queue, the processor transitions to a sleep state, and, in a case in which the notification information is stored in the notification queue during a state in which the processor has transitioned to the sleep state, the processor transitions to an active state and effects the control.

12 . A non-transitory storage medium storing a program that causes a computer to execute image processing using respective objects of an object group in which a plurality of objects configured to execute image processing are connected in a form of a directed acyclic graph, the image processing comprising:

dividing image data, which is an object of the image processing, into a plurality of items of divisional image data;

effecting control to cause a plurality of arithmetic devices to execute, in parallel, respective partial processing routines, each of the partial processing routines comprising image processing to be carried out on a corresponding item of the divisional image data that is stored in a predetermined storage area; and

in a case in which an item of divisional image data that corresponds to a partial processing routine is stored in the storage area, notifying that the item of divisional image data has been stored in the storage area,

wherein the computer is configured to control the plurality of arithmetic devices to start an execution of the image processing on the corresponding item of the divisional image data each time the corresponding item of the divisional image data has been stored in the storage area,

wherein the notifying is performed by storing, in a notification queue that is configured to be referenced, notification information that indicates that the item of divisional image data has been stored in the storage area, and

in a case in which there is no partial processing routine that is executable and the notification information is not stored in the notification queue, the computer transitions to a sleep state, and, in a case in which the notification information is stored in the notification queue during a state in which the computer has transitioned to the sleep state, the computer transitions to an active state and effects the control.

Assignments (3)
CORRECTIVE ASSIGNMENT TO CORRECT THE RECEIVING PARTYS DATA PREVIOUSLY RECORDED ON REEL 55450 FRAME 716. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT OF ASSIGNORS INTEREST. Recorded Jun 5, 2024
From: ITAGAKI, KAZUYUKI; NAGAO, TAKASHI
To: FUJIFILM CORPORATION; FUJI XEROX CO., LTD.
Reel/Frame 067624/0034 →
CHANGE OF NAME Recorded May 14, 2021
From: FUJI XEROX CO., LTD.
To: FUJIFILM BUSINESS INNOVATION CORP.
Reel/Frame 056237/0088 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 2, 2021
From: ITAGAKI, KAZUYUKI; NAGAO, TAKASHI
To: FUJIFILM CORPORATION
Reel/Frame 055450/0716 →
Priority Claims (1)
JP 2018-163784 · Aug 31, 2018 · national
Continuity (2)
Continuation PCTJP2019033091 · Aug 23, 2019
Related Publication 20210183067A1 · Jun 17, 2021
References Cited (32)
US 7602392B2 · Nagao · 2009 [cited by examiner]
US 7602394B2 · Seki et al. · 2009 [cited by applicant]
US 10650481B2 · Nagao · 2020 [cited by examiner]
US 10795725B2 · Nagao · 2020 [cited by examiner]
US 10878526B2 · Itagaki · 2020 [cited by examiner]
US 11341599B2 · Nagao · 2022 [cited by examiner]
US 20090327669A1 · Imada · 2009 [cited by examiner]
US 20110078691A1 · Yildiz · 2011 [cited by examiner]
US 20110283093A1 · Imada · 2011 [cited by examiner]
US 20160358312A1 · Kolb, V · 2016 [cited by examiner]
US 20180365793A1 · Nagao · 2018 [cited by examiner]
US 20190019270A1 · Takemoto · 2019 [cited by examiner]
US 20210183067A1 · Itagaki · 2021 [cited by examiner]
CN 1873685 · 2006 [cited by applicant]
CN 1873690 · 2006 [cited by applicant]
CN 108463836 · 2018 [cited by applicant]
JP 4491026 · 2010 [cited by applicant]
JP 2010146055 · 2010 [cited by applicant]
JP 2014238683 · 2014 [cited by applicant]
WO 2017163441 · 2017 [cited by applicant]
WO WO2017163441A1 · 2017 [cited by examiner]
Machine translation of WO2017163441, Filed Jul. 27, 2016, Published Sep. 28, 2018, Available online at https://patentscope.wipo.int/search/en/detail.jsf?docId=WO2017163441&_cid=P11-LKO9GF-75182-1 (Year: 2016). [cited by examiner]
Google translation of Takahashi, CN187690B, originally published Dec. 6, 2006, and was originally cited by applicant in IDS submitted on Jul. 5, 2024 (Year: 2006). [cited by examiner]
Google Patent translation of CN108463836A, cited by applicant in IDS submitted on Feb. 26, 2025, English translation available online https://patents.google.com/patent/CN108463836A/en?oq=CN108463836A, Obtained May 26, 2… [cited by examiner]
“Office Action of Japan Counterpart Application” with English translation thereof, issued on Sep. 14, 2021, p. 1-p. 5. [cited by applicant]
“International Search Report (Form PCT/ISA/210) of PCT/JP2019/033091,” mailed on Nov. 26, 2019, with English translation thereof, pp. 1-5. [cited by applicant]
“Written Opinion of the International Searching Authority (Form PCT/ISA/237) of PCT/ JP2019/033091,” mailed on Nov. 26, 2019, with English translation thereof, pp. 1-10. [cited by applicant]
Office Action of China Counterpart Application, with English translation thereof, issued on May 28, 2024, pp. 1-11. [cited by applicant]
“Office Action of China Counterpart Application”, issued on Oct. 1, 2024, with English translation thereof, p. 1-p. 12. [cited by applicant]
“Decision of Refusal of China Counterpart Application”, with English translation thereof, issued on Nov. 30, 2024, pp. 1-13. [cited by applicant]
“Reexamination Notice of China Counterpart Application”, issued on May 9, 2025, with English translation thereof, p. 1-p. 15. [cited by applicant]
“Office Action of China Counterpart Application”, issued on Jul. 16, 2025, with partial English translation thereof, pp. 1-25. [cited by applicant]