IP Library Granted Patent US 12,380,243
Granted Patent B2
US 12,380,243 · App. 17/862,091 · Granted Aug 5, 2025

Image segmentation for anonymization for image processing

Inventor: Hans-Martin Ramsl (Mannheim, DE)
Assignee: SAP SE
G06F21/6254G06F21/6209G06T7/11G06T11/60G06T2207/20021
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 12,380,243
App. No.
17/862,091
Granted
Aug 5, 2025
Kind
B2
Abstract

An input image is divided into segments. The segments may be reassembled to reform the input image. The order of the segments may be stored in an encrypted database for which approved applications have the decryption key but users do not. This allows the approved applications to determine the order and reform the input image without allowing users to do the same. To further increase the difficulty of reforming the input image, the segments may be transformed. Example transformations include rotation and mirroring. The encrypted database may store an indication of the transformation applied to each segment. The effort of reforming the input image without access to the database is increased substantially. The reformed input image may be stored in transient memory only, without being stored to long-term storage. Thus, the reformed image cannot be accessed from a file system by unauthorized users.

Claims (41)

1. A method comprising:

accessing, by one or more processors, an image;

segmenting, by the one or more processors, the image into a plurality of image segments, the plurality of image segments being usable to generate the image according to an original order, the plurality of image segments comprising a first image segment and a second image segment;

transforming the first image segment using a first transformation;

transforming the second image segment using a second transformation different than the first transformation;

storing the image using a modified order of the plurality of image segments; and

storing encrypted data indicating the original order of the plurality of image segments, the encrypted data indicating that the first transformation was applied to the first image segment and that the second transformation was applied to the second image segment.

2. The method of claim 1 , wherein the first transformation is a rotation.

3. The method of claim 1 , wherein the first transformation is a mirroring.

4. The method of claim 1 , wherein: the image is a 2-dimensional image having a horizontal image size and a vertical image size; and each image segment of the plurality of image segments has a horizontal size less than the horizontal image size and a vertical size less than the vertical image size.

5. The method of claim 1 , wherein each image segment of the plurality of image segments is no larger than ten pixels in any dimension.

6. The method of claim 1 , further comprising: decrypting the encrypted data; reconstructing, from the plurality of image segments and based on the decrypted data, the image; and performing image processing operations using the reconstructed image without storing the reconstructed image to long-term storage.

7. A system comprising:

one or more hardware processors; and

a memory that stores instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

accessing an image;

segmenting the image into a plurality of image segments, the plurality of image segments being usable to generate the image according to an original order, the plurality of image segments comprising a first image segment and a second image segment;

transforming the first image segment using a first transformation;

transforming the second image segment using a second transformation different than the first transformation;

storing the image using a modified order of the plurality of image segments; and

storing encrypted data indicating the original order of the plurality of image segments, the encrypted data indicating that the first transformation was applied to the first image segment and that the second transformation was applied to the second image segment.

8. The system of claim 7 , wherein the first transformation is a rotation.

9. The system of claim 7 , wherein the first transformation is a mirroring.

10. The system of claim 7 , wherein: the image is a 2-dimensional image having a horizontal image size and a vertical image size;

each image segment of the plurality of image segments has a horizontal size less than the horizontal image size and a vertical size less than the vertical image size.

11. The system of claim 7 , wherein each image segment of the plurality of image segments is no larger than ten pixels in any dimension.

12. The system of claim 7 , further comprising:

decrypting the encrypted data; reconstructing, from the plurality of image segments and based on the decrypted data, the image; and performing image processing operations using the reconstructed image without storing the reconstructed image to long-term storage.

13. A non-transitory computer-readable medium that stores instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

accessing an image;

segmenting the image into a plurality of image segments, the plurality of image segments being usable to generate the image according to an original order, the plurality of image segments comprising a first image segment and a second image segment;

transforming the first image segment using a first transformation;

transforming the second image segment using a second transformation different than the first transformation;

storing the image using a modified order of the plurality of image segments; and

storing encrypted data indicating the original order of the plurality of image segments, the encrypted data indicating that the first transformation was applied to the first image segment and that the second transformation was applied to the second image segment.

14. The non-transitory computer-readable medium of claim 13 , wherein the first transformation is a rotation.

15. The non-transitory computer-readable medium of claim 13 , wherein the first transformation is a mirroring.

16. The non-transitory computer-readable medium of claim 13 , wherein: the image is a 2-dimensional image having a horizontal image size and a vertical image size; and each image segment of the plurality of image segments has a horizontal size less than the horizontal image size and a vertical size less than the vertical image size.

17. The non-transitory computer-readable medium of claim 13 , wherein each image segment of the plurality of image segments is no larger than ten pixels in any dimension.

18. The non-transitory computer-readable medium of claim 13 , wherein the operations further comprise:

decrypting the encrypted data; reconstructing, from the plurality of image segments and based on the decrypted data, the image; and performing image processing operations using the reconstructed image without storing the reconstructed image to long-term storage.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 11, 2022
From: RAMSL, HANS-MARTIN
To: SAP SE
Reel/Frame 060477/0146 →
Continuity (1)
Related Publication 20240012936A1 · Jan 11, 2024
References Cited (54)
US 10210551B1 · Todd · 2019 [cited by applicant]
US 11263391B2 · Potts et al. · 2022 [cited by applicant]
US 11675808B2 · Jacob et al. · 2023 [cited by applicant]
US 11755602B2 · Smith et al. · 2023 [cited by applicant]
US 11837000B1 · Ramsl · 2023 [cited by applicant]
US 11947529B2 · Gasper et al. · 2024 [cited by applicant]
US 12008050B2 · Brener et al. · 2024 [cited by applicant]
US 20140293366A1 · Ozawa · 2014 [cited by examiner]
US 20150003666A1 · Wang et al. · 2015 [cited by applicant]
US 20150278593A1 · Panferov et al. · 2015 [cited by applicant]
US 20150379343A1 · Powell et al. · 2015 [cited by applicant]
US 20170039253A1 · Bond · 2017 [cited by applicant]
US 20170371970A1 · Bharti et al. · 2017 [cited by applicant]
US 20180165289A1 · Ramsl et al. · 2018 [cited by applicant]
US 20180288079A1 · Muddu et al. · 2018 [cited by applicant]
US 20190018904A1 · Russell et al. · 2019 [cited by applicant]
US 20190065877A1 · Kalyuzhny et al. · 2019 [cited by applicant]
US 20190244094A1 · Ramsl · 2019 [cited by applicant]
US 20200134420A1 · Spooner · 2020 [cited by applicant]
US 20200293276A1 · Ballinger et al. · 2020 [cited by applicant]
US 20200380274A1 · Shin et al. · 2020 [cited by applicant]
US 20210224403A1 · Amthor · 2021 [cited by examiner]
US 20210232579A1 · Schechter et al. · 2021 [cited by applicant]
US 20210342399A1 · Sisto et al. · 2021 [cited by applicant]
US 20210365807A1 · Ramsl · 2021 [cited by applicant]
US 20220129498A1 · Kilaru et al. · 2022 [cited by applicant]
US 20220171008A1 · Zeller · 2022 [cited by examiner]
US 20230004977A1 · Cepek et al. · 2023 [cited by applicant]
US 20230062307A1 · Ramsl · 2023 [cited by applicant]
US 20230096118A1 · Ramsl · 2023 [cited by applicant]
US 20230162257A1 · Bhagat et al. · 2023 [cited by applicant]
US 20230186020A1 · Rayles · 2023 [cited by applicant]
US 20240013004A1 · Ramsl · 2024 [cited by applicant]
US 20240028646A1 · Ramsl · 2024 [cited by applicant]
“Bipartite graph”, Wkipedia, [Online]. Retrieved from the Internet: <URL: https://en.wikipedia.org/wiki/Bipartite_graph>, (Accessed Jun. 23, 2022), 10 pgs. [cited by applicant]
Guo, Qingyu, et al., “A Survey on Knowledge Graph-Based Recommender Systems”, arXiv:2003.00911v1, (Feb. 28, 2020), 17 pgs. [cited by applicant]
Karani, Dhruvil, “Introduction to Word Embedding and Word2Vec”, Published in Towards Data Science, [Online]. Retrieved from the Internet <URL: https://towardsdatascience.com/introduction-to-word-embedding-and-word2vec-6… [cited by applicant]
Lopez, Frederico, et al., “Augmenting the User-Item Graph with Textual Similarity Models”, arXiv:2109.09358v1, (Sep. 20, 2021), 12 pgs. [cited by applicant]
U.S. Appl. No. 17/746,451 U.S. Pat. No. 11,837,000, filed May 17, 2022, OCR Using 3-Dimensional Interpolation. [cited by applicant]
U.S. Appl. No. 17/860,912, filed Jul. 8, 2022, Automatic Data Card Generation. [cited by applicant]
U.S. Appl. No. 17/870,565, filed Jul. 21, Textual Similarity Model for Graph-Based Metadata. [cited by applicant]
“U.S. Appl. No. 17/746,451, Notice of Allowance mailed Oct. 12, 2023”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 17/860,912, Examiner Interview Summary mailed Aug. 12, 2024”, 2 pgs. [cited by applicant]
“U.S. Appl. No. 17/860,912, Non Final Office Action mailed Jul. 2, 2024”, 16 pgs. [cited by applicant]
“U.S. Appl. No. 17/860,912, Response filed Aug. 13, 2024 to Non Final Office Action mailed Jul. 2, 2024”, 12 pgs. [cited by applicant]
“U.S. Appl. No. 17/870,565, Examiner Interview Summary mailed Apr. 2, 2024”, 3 pgs. [cited by applicant]
“U.S. Appl. No. 17/870,565, Examiner Interview Summary mailed Dec. 8, 2023”, 3 pgs. [cited by applicant]
“U.S. Appl. No. 17/870,565, Final Office Action mailed Feb. 26, 2024”, 20 pgs. [cited by applicant]
“U.S. Appl. No. 17/870,565, Non Final Office Action mailed Jul. 16, 2024”, 21 pgs. [cited by applicant]
“U.S. Appl. No. 17/870,565, Non Final Office Action mailed Oct. 19, 2023”, 19 pgs. [cited by applicant]
“U.S. Appl. No. 17/870,565, Response filed Apr. 9, 24 to Final Office Action mailed Feb. 26, 2024”, 13 pgs. [cited by applicant]
“U.S. Appl. No. 17/870,565, Response filed Aug. 23, 24 to Non Final Office Action mailed Jul. 16, 2024”, 18 pgs. [cited by applicant]
“U.S. Appl. No. 17/870,565, Response filed Dec. 14, 23 to Non Final Office Action mailed Oct. 19, 2023”, 15 pgs. [cited by applicant]
Ozuysal, Mustafa, et al., “Fast Keypoint Recognition using Random Ferns”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, (2010), 14 pgs. [cited by applicant]