IP Library Granted Patent US 12,400,289
Granted Patent B2
US 12,400,289 · App. 17/245,191 · Granted Aug 26, 2025

Object stitching image generation

Inventors: Prateek Goyal (Indore, IN); Seema Nagar (Bangalore, IN); Manish Anand Bhide (Hyderabad, IN); Kuntal Dey (Rampurhat, IN)
Assignee: International Business Machines Corporation
G06T3/4038G06F18/2132G06F18/214G06N3/08G06N5/02
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 12,400,289
App. No.
17/245,191
Granted
Aug 26, 2025
Kind
B2
Abstract

A method includes receiving, by a computing device, concepts of a domain; determining, by the computing device, objects relevant to the concepts; generating, by the computing device, a new image by stitching the relevant objects together; determining, by the computing device, whether the new image is accurate or inaccurate; and in response to determining the new image is inaccurate, propagating, by the computing device, the inaccurate new image back to a convolutional neural network (CNN).

Claims (38)

1. A method, comprising:

receiving, by a computing device, a user input comprising concepts of a domain;

determining, by the computing device, objects relevant to the concepts, wherein the relevant objects are not included in the user input;

generating, by the computing device, a new image by stitching the relevant objects together;

generating, by the computing device using a generative adversarial network (GAN), scene graphs to connect the relevant objects to the concepts of the domain;

determining, by the computing device, whether the new image is accurate or inaccurate using the scene graphs generated by the GAN; and

in response to determining the new image is inaccurate, propagating, by the computing device, the inaccurate new image back to a convolutional neural network (CNN).

2. The method of claim 1 , further comprising, in response to determining the new image is accurate, labeling, by the computing device, the accurate new image as a real image, wherein the labeling comprises a descriptor for the concepts of the domain, the domain, and the relevant objects related to the accurate new image; and

storing the label in a knowledge base.

3. The method of claim 1 , wherein the determining the relevant objects include using a concatenation layer of the CNN.

4. The method of claim 3 , wherein the concatenation layer links the concepts together with the relevant objects using domain knowledge.

5. The method of claim 1 , wherein the stitching the objects together includes overlapping the relevant objects so that a field of view of each relevant object overlaps to generate an image with a wider field of view wider than the field of view of each object.

6. The method of claim 1 , further comprising receiving the new image at the GAN and determining whether the new image is accurate or inaccurate.

7. The method of claim 6 , wherein the GAN includes a generator and a discriminator.

8. The method of claim 7 , wherein the determining the new image is accurate or inaccurate includes training the discriminator using the scene graphs from accurate images.

9. The method of claim 8 , further comprising verifying, by the computing device, accuracy of the scene graphs by applying a knowledge base to the scene graphs.

10. The method of claim 1 , wherein the new image is an existing image enriched by the relevant objects and wherein the relevant objects are selected based on a link between the relevant objects and the concepts of the domain.

11. The method of claim 1 , wherein the computing device includes software provided as a service in a cloud environment.

12. A computer program product comprising one or more computer readable storage media having program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:

receive a user input comprising concepts of a domain;

determine objects relevant to the concepts, wherein the relevant objects are not included in the user input;

generate a new image by stitching the relevant objects together;

determine whether the new image is accurate or inaccurate; and

in response to determining the new image is accurate, label the new image as an accurate new image.

13. The computer program product of claim 12 , wherein a convolutional neural network (CNN) receives the concepts and wherein the relevant objects are selected from a plurality of sources.

14. The computer program product of claim 13 , wherein CNN includes a convolutional layer and the program instructions are executable to filter out less relevant objects with respect to the concepts using a centrality value within the convolutional layer.

15. The computer program product of claim 12 , wherein the program instructions are executable to automatically receive the concepts using computer vision.

16. A system comprising:

a processor, a computer readable memory, 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 to:

receive a user input comprising concepts of a domain;

determine objects relevant to the concepts, wherein the relevant objects are not included in the user input;

generate a new image by stitching the relevant objects together;

apply scene graphs to the new image; and

in response to determining the new image does not match the scene graphs, propagate the new image back to a convolutional neural network (CNN).

17. The system of claim 16 , wherein the CNN includes a subsampling layer which filters out less relevant objects with respect to the concepts.

18. The system of claim 17 , wherein the subsampling layer filters out less relevant objects by down-sampling.

19. The system of claim 18 , wherein the program instructions are further executable to arrange an output of the subsampling layer as a vector.

20. The computer program product of claim 14 , wherein the filtering out less relevant objects comprises down-sampling feature maps of the convolutional later by pooling weights of objects within the feature maps.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 30, 2021
From: GOYAL, PRATEEK; NAGAR, SEEMA; BHIDE, MANISH ANAND; DEY, KUNTAL
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 056094/0814 →
Continuity (1)
Related Publication 20220351331A1 · Nov 3, 2022
References Cited (41)
US 8416302B2 · Zhang et al. · 2013 [cited by applicant]
US 9128909B2 · Brindley · 2015 [cited by applicant]
US 10074200B1 · Yeturu · 2018 [cited by examiner]
US 10713821B1 · Surya · 2020 [cited by examiner]
US 11640708B1 · Blechschmidt · 2023 [cited by examiner]
US 11720942B1 · Bazzani · 2023 [cited by examiner]
US 12195040B1 · Pronovost · 2025 [cited by examiner]
US 12198430B1 · Kottur · 2025 [cited by examiner]
US 20070035562A1 · Azuma et al. · 2007 [cited by applicant]
US 20070146360A1 · Clatworthy · 2007 [cited by examiner]
US 20080266408A1 · Kim · 2008 [cited by examiner]
US 20110255741A1 · Jung · 2011 [cited by examiner]
US 20130077892A1 · Ikeno · 2013 [cited by examiner]
US 20140377702A1 · Nakahara · 2014 [cited by examiner]
US 20180060701A1 · Krishnamurthy · 2018 [cited by examiner]
US 20180244199A1 · Gyori · 2018 [cited by examiner]
US 20180262683A1 · Meler · 2018 [cited by examiner]
US 20190037138A1 · Choe · 2019 [cited by examiner]
US 20200051249A1 · Walters et al. · 2020 [cited by applicant]
US 20200074239A1 · Park · 2020 [cited by examiner]
US 20200097569A1 · Sewak · 2020 [cited by examiner]
US 20200201165A1 · Lock · 2020 [cited by examiner]
US 20200387806A1 · Kaseda · 2020 [cited by examiner]
US 20200401835A1 · Zhao · 2020 [cited by examiner]
US 20210174565A1 · Awasthi · 2021 [cited by examiner]
US 20220014554A1 · Vasu · 2022 [cited by examiner]
US 20220068296A1 · Wilson · 2022 [cited by examiner]
US 20220180491A1 · Shinohara · 2022 [cited by examiner]
US 20220237830A1 · Khodadadeh · 2022 [cited by examiner]
CN 110689086A · 2020 [cited by applicant]
EP 2731081A1 · 2014 [cited by applicant]
Mell et al., “The NIST Definition of Cloud Computing”, NIST, Special Publication 800-145, Sep. 2011, 7 pages. [cited by applicant]
Frid-Adar et al., “GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification”, arXiv:1803.01229v1 [cs.CV], Mar. 3, 2018, 10 pages. [cited by applicant]
Bloice et al., “Augmentor: An Image Augmentation Library for Machine Learning”, arXiv:1708.04680v1, Aug. 11, 2017, 5 pages. [cited by applicant]
Wong et al., “Understanding data augmentation for classification: when to warp?”, arXiv:1609.08764v2 [cs.CV], Nov. 26, 2016, 6 pages. [cited by applicant]
Liu et al., “Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications”, arXiv:2008.02793v2 [cs.CV], Nov. 30, 2020, 22 pages. [cited by applicant]
Khan, “StyleGAN: Use machine learning to generateand customize realistic images”, https://heartbeat.fritz.ai/stylegans-use-machine-learning-to-generate-and-customize-realistic-images-c943388dc672, Jul. 31, 2019, 19 page… [cited by applicant]
Song et al., “Dynamic image stitching for moving object”, Conference Paper; https://www.researchgate.net/publication/314194530, Dec. 2016, 7 pages. [cited by applicant]
Wu et al., “GP-GAN: Towards Realistic High-Resolution Image Blending”, arXiv:1703.07195v3 [cs.CV], Aug. 5, 2019, 11 pages. [cited by applicant]
Xu et al., “Scene Graph Generation by Iterative Message Passing”, arXiv:1701.02426v2 [cs.CV], Apr. 12, 2017, 10 pages. [cited by applicant]
Levin et al., “Seamless Image Stitching in the Gradient Domain”, School of Computer Science and Engineering, downloaded Apr. 29, 2021, 12 pages. [cited by applicant]