AI Face Editing with Similarity Threshold Authentication

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image editing technologies using AI models often edit faces without consent, violating privacy and ethical norms, necessitating a solution to ensure that only authorized edits are made.

Innovation Solution

An electronic device employs an AI model to edit faces only if the edited face is similar to an authenticated face, using a similarity score greater than or equal to a threshold value, ensuring that only authorized edits are performed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If AI model edits face in image, then face editing capability is improved, but privacy and ethical violations occur when editing without consent

Engineering Contradiction:

Improveface editing capabilityVSAvoidprivacy violation

Core Design Contradiction:

Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary authentication of the face before allowing AI editing. The user must verify their identity through facial recognition or other authentication methods before the editing function becomes available, ensuring that only the authenticated person can edit their own face image.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system calculates and provides feedback on the similarity score between the edited face and the authenticated face. This feedback mechanism allows the system to monitor and control the editing process, ensuring that the edited results remain consistent with the original authenticated identity and do not create harmful alterations.

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If AI model edits face to be totally different, then editing creativity is improved, but face recognition accuracy deteriorates

Engineering Contradiction:

Improveediting creativityVSAvoidface recognition accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system adjusts the similarity threshold parameter to balance editing creativity and face recognition accuracy. By setting an appropriate threshold value, the system allows sufficient creative freedom for face editing while ensuring that the edited face maintains enough similarity to the original for accurate recognition and authentication purposes.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260004557A1Electronic device and method for editing face included in image using artificial intelligence model in the electronic device

Publication Date: 2026.01.01 SAMSUNG ELECTRONICS CO LTD

AI summary

An electronic device includes: a communication circuit; a display; at least one processor; and memory storing instructions, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: based on editing of a face included in a first image being identified, transfer, to an AI model, editing information including first information associated with the face included in the first image, the first information obtained by training a characteristic of the face selected for editing, based on receiving from the AI model a second image in which the face included in the first image is edited using the editing information, obtain a score related to a similarity between an edited face included in the second image and the face included in the first image, and based on the obtained score being greater than or equal to a threshold value, store the second image.