Granted Patent B2

US 12,613,996 · App. 18/624,199 · Granted Apr 28, 2026

Inventors: Anjela Spreen (Hewitt, TX); Geetha P. Nagarajan (Plano, TX); Salomon K. Kabongo (Bloomington, IL)

Assignee: State Farm Mutual Automobile Insurance Company

G06F21/6254G06F21/1066G06T5/70G06V30/1448G06V40/172G06V2201/10

Abstract

Claims (52)

1 . An image de-identification computer system for identifying and removing personally identifiable information from images, the computer system comprising at least one processor in communication with at least one memory device, wherein the at least one processor programmed to:

receive a plurality of images; and

for each image of the plurality of images, the at least one processor is programmed to:

retrieve the image;

execute at least one model to analyze the retrieved image to detect one or more representations of individuals in the image;

identify one or more items of text in the retrieved image;

analyze the one or more items of text to detect one or more personally identifiable items of text from the one or more items of text;

identify one or more personally identifiable items of text to obscure based upon one or more security settings;

update the retrieved image to obscure at least one of the one or more items of personally identifiable text and the one or more representations of individuals in the image, wherein obscuring includes altering pixels within a predetermined number of pixels of the pixels identified as forming the at least one of the one or more items of personally identifiable text and the one or more representations of individuals in the image; and

provide the updated image.

2 . The computer system of claim 1 , where in the at least one processor is further programmed to obscure the at least one of the one or more items of personally identifiable text and the one or more representations of individuals in the image.

3 . The computer system of claim 1 , wherein to obscure the one or more representations of individuals in the image, the at least one processor is further programmed to mask a plurality of pixels to cover each face of the one or more representations of individuals in the image.

4 . The computer system of claim 1 , wherein the at least one model is trained to recognize a face of an individual in a reflection.

5 . The computer system of claim 1 , wherein the at least one processor is further programmed to remove one or more pieces of metadata associated with the retrieved image.

6 . The computer system of claim 5 , wherein the at least one processor is further programmed to determine the one or more pieces of metadata to remove based upon the one or more security settings.

7 . The computer system of claim 1 , wherein the at least one processor is further programmed to:

detect one or more items of copyrighted information in the retrieved image; and

obscure the one or more items of copyrighted information in the retrieved image.

8 . The computer system of claim 7 , wherein the at least one processor is further programmed to determine whether or not to obscure the one or more items of copyrighted information based upon the one or more security settings.

9 . The computer system of claim 1 , wherein the one or more security settings include a plurality of levels of security, and wherein each level of security of the plurality of levels of security indicates different items to be obscured.

10 . A computer-implemented method for identifying and removing personally identifiable information from images, the method performed by a de -identification computer device including at least one processor in communication with at least one memory device, the method comprising:

receiving a plurality of images; and

for each image of the plurality of images, the method further comprises:

retrieving the image;

executing at least one model to analyze the retrieved image to detect one or more representations of individuals in the image;

identifying one or more items of text in the retrieved image;

analyzing the one or more items of text to detect one or more personally identifiable items of text from the one or more items of text;

identifying one or more personally identifiable items of text to obscure based upon one or more security settings;

updating the retrieved image to obscure at least one of the one or more items of personally identifiable text and the one or more representations of individuals in the image, wherein obscuring comprises altering pixels within a predetermined number of pixels of the pixels identified as forming the at least one of the one or more items of personally identifiable text and the one or more representations of individuals in the image; and

providing the updated image.

11 . The computer-implemented method of claim 10 , wherein the one or more security settings include a plurality of levels of security, and wherein each level of security of the plurality of levels of security indicates different items to be obscured.

12 . The computer-implemented method of claim 10 , wherein to obscure the one or more representations of individuals in the image, the method further comprises masking a plurality of pixels to cover each face of the one or more representations of individuals in the image.

13 . The computer-implemented method of claim 10 further comprising removing one or more pieces of metadata associated with the retrieved image.

14 . The computer-implemented method of claim 10 further comprising:

detecting one or more items of copyrighted information in the retrieved image; and

obscuring the one or more items of copyrighted information in the retrieved image.

15 . The computer-implemented method of claim 10 , wherein the at least one model is trained to recognize a face of an individual in a reflection.

16 . At least one non-transitory computer-readable media having computer-executable instructions embodied thereon for identifying and removing personally identifiable information from images, wherein when executed by an image computing device including at least one processor in communication with at least one memory device, the computer-executable instructions cause the at least one processor to:

receive a plurality of images; and

for each image of the plurality of images, the computer-executable instructions also cause the at least one processor to:

retrieve the image;

execute at least one model to analyze the retrieved image to detect one or more representations of individuals in the image;

identify one or more items of text in the retrieved image;

analyze the one or more items of text to detect one or more personally identifiable items of text from the one or more items of text;

identify one or more personally identifiable items of text to obscure based upon one or more security settings;

update the retrieved image to obscure at least one of the one or more items of personally identifiable text and the one or more representations of individuals in the image, wherein obscuring includes altering pixels within a predetermined number of pixels of the pixels identified as forming the at least one of the one or more items of personally identifiable text and the one or more representations of individuals in the image; and

provide the updated image.

17 . The media of claim 16 , wherein the one or more security settings include a plurality of levels of security, and wherein each level of security of the plurality of levels of security indicates different items to be obscured.

18 . The media of claim 16 , the computer-executable instructions also cause the at least one processor to remove one or more pieces of metadata associated with the retrieved image.

19 . The media of claim 16 , the computer-executable instructions also cause the at least one processor to:

detect one or more items of copyrighted information in the retrieved image; and

obscure the one or more items of copyrighted information in the retrieved image.

Assignments (1)

Continuity (3)

References Cited (12)