IP Library Granted Patent US 12,242,529
Granted Patent B2
US 12,242,529 · App. 17/481,534 · Granted Mar 4, 2025

Historical image search

Inventors: Cheranellore Vasudevan (Bastrop, TX); Swaminathan Balasubramanian (Troy, MI); Sibasis Das (Kolkata, IN); Radha Mohan De (Howrah, IN)
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
G06F16/532G06F16/538G06F16/55G06F16/583G06V10/40
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 12,242,529
App. No.
17/481,534
Granted
Mar 4, 2025
Kind
B2
Abstract

A method, computer system, and a computer program product for historical image search is provided. The present invention may include receiving an image search criteria. The present invention may also include generating a composite image search query based on the received image search criteria. The present invention may further include searching for a matching historical image based on the generated composite image search query. The present invention may also include returning a historical image search result.

Claims (49)

1. A computer-implemented method, comprising:

receiving an image search criteria including at least one reference image and at least one contextual data;

generating a composite image search query including a synthetic image sketch based on a plurality of transformed segments from the at least one reference image, wherein the plurality of transformed segments include modifications based on the at least one contextual data;

searching for a matching historical image based on the generated composite image search query; and

returning a historical image search result.

2. The method of claim 1 , further comprising:

classifying at least one object detected in the at least one reference image;

modifying the classified at least one object detected in the at least one reference image based on the at least one contextual data; and

generating the synthetic image sketch including the modified at least one object detected in the at least one reference image.

3. The method of claim 1 , further comprising:

assigning an object classifier to an object detected in the at least one reference image;

determining a family of the object associated with the assigned object classifier;

selecting an aging algorithm based on the determined family of the object detected in the at least one reference image; and

transforming the object based on the selected aging algorithm.

4. The method of claim 1 , wherein the synthetic image sketch further comprises an aged back version of the at least one reference image, and wherein the aged back version of the at least one reference image includes modifying at least one object detected in the at least one reference image based on age.

5. The method of claim 1 , wherein the generated composite image search query further comprises at least one metadata added to the synthetic image sketch to describe the at least one contextual data associated with the matching historical image.

6. A computer system for historical image search, comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:

receiving an image search criteria including at least one reference image and at least one contextual data;

generating a composite image search query including a synthetic image sketch based on a plurality of transformed segments from the at least one reference image, wherein the plurality of transformed segments include modifications based on the at least one contextual data;

searching for a matching historical image based on the generated composite image search query; and

returning a historical image search result.

7. The computer system of claim 6 , further comprising:

classifying at least one object detected in the at least one reference image;

modifying the classified at least one object detected in the at least one reference image based on the at least one contextual data; and

generating the synthetic image sketch including the modified at least one object detected in the at least one reference image.

8. The computer system of claim 6 , further comprising:

assigning an object classifier to an object detected in the at least one reference image;

determining a family of the object associated with the assigned object classifier;

selecting an aging algorithm based on the determined family of the object detected in the at least one reference image; and

transforming the object based on the selected aging algorithm.

9. The computer system of claim 6 , wherein the synthetic image sketch further comprises an aged back version of the at least one reference image, and wherein the aged back version of the at least one reference image includes modifying at least one object detected in the at least one reference image based on age.

10. The computer system of claim 6 , wherein the generated composite image search query further comprises at least one metadata added to the synthetic image sketch to describe the at least one contextual data associated with the matching historical image.

11. A computer program product for historical image search, comprising:

one or more computer-readable storage media and program instructions collectively stored on the one or more computer-readable storage media, the program instructions executable by a processor to cause the processor to perform a method comprising:

receiving an image search criteria including at least one reference image and at least one contextual data;

generating a composite image search query including a synthetic image sketch based on a plurality of transformed segments from the at least one reference image, wherein the plurality of transformed segments include modifications based on the at least one contextual data;

searching for a matching historical image based on the generated composite image search query; and

returning a historical image search result.

12. The computer program product of claim 11 , further comprising:

classifying at least one object detected in the at least one reference image;

modifying the classified at least one object detected in the at least one reference image based on the at least one contextual data; and

generating the synthetic image sketch including the modified at least one object detected in the at least one reference image.

13. The computer program product of claim 11 , further comprising:

assigning an object classifier to an object detected in the at least one reference image;

determining a family of the object associated with the assigned object classifier;

selecting an aging algorithm based on the determined family of the object detected in the at least one reference image; and

transforming the object based on the selected aging algorithm.

14. The computer program product of claim 11 , wherein the synthetic image sketch further comprises an aged back version of the at least one reference image, and wherein the aged back version of the at least one reference image includes modifying at least one object detected in the at least one reference image based on age.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 22, 2021
From: VASUDEVAN, CHERANELLORE; BALASUBRAMANIAN, SWAMINATHAN; DAS, SIBASIS; DE, RADHA MOHAN
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 057559/0818 →
Continuity (1)
Related Publication 20230090269A1 · Mar 23, 2023
References Cited (17)
US 6725427B2 · Freeman · 2004 [cited by applicant]
US 10650188B2 · Kasina · 2020 [cited by examiner]
US 11809822B2 · Lin · 2023 [cited by examiner]
US 20090100046A1 · Huck · 2009 [cited by applicant]
US 20110235908A1 · Ke · 2011 [cited by examiner]
US 20140012857A1 · Moraleda · 2014 [cited by examiner]
US 20140355835A1 · Rodriguez-Serrano · 2014 [cited by examiner]
US 20180373955A1 · Soldevila · 2018 [cited by examiner]
US 20210004716A1 · Song · 2021 [cited by applicant]
CN 107423442A · 2020 [cited by applicant]
Ancestry, “Finding and Saving Photos”, Retrieved from Internet on Sep. 10, 2021, 4 Pages. https://support.ancestry.com/s/article/Searching-for-Photos. [cited by applicant]
Bongen, “Metaphotographs: On Representing Digital Photo Collections.”, University of Illinois at Urbana-Champaign, 2010, 88 pages. [cited by applicant]
Echihabi et al., “New Trends in High-D Vector Similarity Search: AI driven, Progressive, and Distributed”, Proceedings of the VLDB Endowment, vol. No. ISSN 21508097, 4 Pages. [cited by applicant]
Monaghan et al., “Generating useful photo context metadata for the semantic web.” 7th International Conference on Mobile Data Management (MDM'06). IEEE, 2006, 9 Pages. [cited by applicant]
Nguyen et al. “NowAndThen: a social network-based photo recommendation tool supporting reminiscence.” Proceedings of the 15th International Conference on Mobile and Ubiquitous Multimedia. Dec. 12-15, 2016, 10 Pages. [cited by applicant]
Zhao, “Compositing-aware Image Search”, The Chinese University of Hong Kong, ByteDance AI Lab, Adobe Research, Tencent Youtu Lab, Last Update: Aug. 18, 2018, 4 Pages. https://hszhao.github.io/projects/cais/. [cited by applicant]
Mell et al., “The NIST Definition of Cloud Computing”, Recommendations of the National Institute of Standards and Technology, NIST Special Publication 800-145, Sep. 2011, 7 pages. [cited by applicant]