METHOD FOR GENERATING AN ENCODED IMAGE, COMPUTER PROGRAM, STORAGE MEDIUM, AND ELECTRONIC IMAGE ANALYSIS DEVICE

Abstract

Method for generating an encoded image 1, wherein a camera system provides a camera image 2, wherein the camera image 2 comprises anonymous image sections 3 without personal data and sensitive image sections 4 containing personal data, wherein the camera image 2 is analyzed based on an image recognition algorithm to detect the sensitive image sections 4, wherein an encoded image 1 is generated, wherein in order to generate the encoded image 1 the sensitive image sections 4 of the camera image 2 are anonymized and image contents of the sensitive image sections 4 of the camera image are stored in the encoded image 1 in cryptographically encoded form.

Claims

1. A method for generating an encoded image (1), wherein a camera system provides a camera image (2), wherein the camera image (2) comprises anonymous image sections (3) without personal data and sensitive image sections (4) containing personal data, wherein the camera image (2) is analyzed based on an image recognition algorithm to detect the sensitive image sections (4), wherein an encoded image (1) is generated, wherein in order to generate the encoded image (1) the sensitive image sections (4) of the camera image (2) are anonymized and image contents of the sensitive image sections (4) of the camera image are stored in the encoded image (1) in cryptographically encoded form.

2. The method according to claim 1, wherein in order to generate the encoded image (1), the camera image (2) with the anonymized sensitive image sections (4) forms an intermediate image (5), the cryptographically encoded sensitive image sections (4) being include in the intermediate image (5).

3. The method according to claim 1, wherein the cryptographic encoding is based on steganography.

4. The method according to claim 1, wherein the storage of the cryptographically encoded sensitive image sections (4) comprises an invisible storage of the image contents of the sensitive image sections in the encoded image (1), the intermediate image (2), or both.

5. The method according to claim 1, wherein the storage of the cryptographically encoded sensitive image contents (4) in the encoded image (1) and/or intermediate image (5) is based on a least-significant-bits algorithm and/or the intermediate image (5) is stored in DCT coefficients.

6. The method according to claim 1, wherein the cryptographically encoded image contents of the sensitive image contents (4) are included in the image section of the sensitive image contents (4).

7. The method according to claim 1, wherein to generate the encoded image (1) the image contents of the sensitive image sections (4) of the camera image (2) are stored as cryptographically encoded metadata in an encoded image header and/or encoded image attachment.

8. The method according to claim 1, wherein the sensitive image sections (4) include as least one selected from the group consisting of faces, number plates, and private information in textual form.

9. The method according to claim 1, wherein to anonymize one of the sensitive image sections (4) of the camera image (2) the image contents of the sensitive image section (4) are replaced by an average image content (6).

10. The method according to claim 1, wherein the sensitive image section (4) is anonymized by means of a generative adversarial network.

11. The method according to claim 1, wherein the cryptographic encoding is based on an asymmetric encryption.

12. A non-transitory, computer-readable storage medium containing instructions that when executed by a computer cause the computer to control a camera system to provide a camera image (2), wherein the camera image (2) comprises anonymous image sections (3) without personal data and sensitive image sections (4) containing personal data, analyze the camera image (2) based on an image recognition algorithm to detect the sensitive image sections (4), generate an encoded image (1), wherein in order to generate the encoded image (1) the sensitive image sections (4) of the camera image (2) are anonymized and image contents of the sensitive image sections (4) of the camera image are stored in the encoded image (1) in cryptographically encoded form.

14. An electronic image analysis device, configured to obtain a camera image (2), wherein the camera image (2) comprises anonymous image sections (3) without personal data and sensitive image sections (4) containing personal data, analyze the camera image (2) based on an image recognition algorithm to detect the sensitive image sections (4), generate an encoded image (1), wherein in order to generate the encoded image (1) the sensitive image sections (4) of the camera image (2) are anonymized and image contents of the sensitive image sections (4) of the camera image are stored in the encoded image (1) in cryptographically encoded form.

15. The electronic image analysis device according to claim 14, wherein the image recognition module is configure, in order to generate the encoded image (1), to anonymize the sensitive image sections (4) of the camera image (2) in the encoded image (1) and store image contents of the sensitive image sections (4) of the camera image in the encoded image (1) in cryptographically encoded form.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Further advantages, embodiments and effects are obtained from the attached FIGURE and its description. In the drawing

[0025] FIG. 1 shows an exemplary embodiment of a method for generating an encoded image.

DETAILED DESCRIPTION

[0026] FIG. 1 is an exemplary embodiment of a method for generating an encoded image 1 based on a camera image 2. In a method step 100, the camera image 2 is acquired or provided. The camera image 2 is, for example, the camera image of a surveillance camera, and in particular a color image. The camera image preferably comprises anonymous sections 3 and sensitive image sections 4. The anonymous image sections 3 are parts of the camera image 2 without data and/or information that is personal and/or covered by data protection law. For example, trees, pieces of furniture and/or background objects in the camera image 2 are counted as anonymous image sections 3. Sensitive image sections 4 are those sections of the camera image 2 that show personal data and/or information covered by data protection law. For example, faces, dates of birth, textual information and/or number plates are information to be deemed as sensitive image sections 4. The method is used to generate the encoded image 1, so that the encoded image 1 represents sensitive image sections 4 in anonymized form for the general public and/or unauthorized persons.

[0027] In method step 200, an image recognition algorithm is applied to the camera image 2, the image recognition algorithm being designed to recognize and/or detect the sensitive image sections 4 of the camera image 2. The detected sensitive image section 4 is shown highlighted and/or selected in method step 200.

[0028] In method step 300, an intermediate image 5 is generated. The intermediate image 5 is generated by anonymizing the sensitive image section 4. The anonymization in this exemplary embodiment is performed by replacing the actual sensitive image section (face) 4 of the camera image 2 by masking, for example, by blacking out or blurring. Alternatively, the anonymization is performed by replacing the actual sensitive image section 4 by an average face 6. For example, the average face 6 is selected to contain matching skin color, age and/or gender. Due to the anonymization by means of an average face 6, the intermediate images 5 appear to a third party to be highly realistic.

[0029] In method step 400, the encoded image 1 is generated based on the intermediate image 5. For this purpose, the image content of the sensitive image section 4, here the face of the camera image from method step 100 or 200, is cryptographically encoded and/or appended to and/or imprinted on the intermediate image 5 as a watermark 7. The intermediate image 5 together with the cryptographically encoded image content, in particular the watermark 7, forms the encoded image 1. The encoded image 1 can then be made available to third parties in a manner that complies with data protection, as the sensitive image regions are not recognizable to them.